Principal component analysis

Principal component analysis (PCA) is a popular technique for analyzing large datasets containing a high
number of dimensions/features per observation, increasing the interpretability of data while preserving the
maximum amount of information, and enabling the visualization of multidimensional data. Formally, PCA
is a statistical technique for reducing the dimensionality of a dataset. This is accomplished by linearly
transforming the data into a new coordinate system where (most of) the variation in the data can be
described with fewer dimensions than the initial data. Many studies use the first two principal components
in order to plot the data in two dimensions and to visually identify clusters of closely related data points.
Principal component analysis has applications in many fields such as population genetics, microbiome
studies, and atmospheric science.[1]

The principal components of a collection of points in

a real coordinate space are a sequence of unit
vectors, where the -th vector is the direction of a line
that best fits the data while being orthogonal to the first
vectors. Here, a best-fitting line is defined as one
that minimizes the average squared perpendicular
distance from the points to the line. These directions
constitute an orthonormal basis in which different
individual dimensions of the data are linearly
uncorrelated. Principal component analysis is the
process of computing the principal components and
using them to perform a change of basis on the data,
sometimes using only the first few principal
components and ignoring the rest.

In data analysis, the first principal component of a set

of variables, presumed to be jointly normally PCA of a multivariate Gaussian distribution
distributed, is the derived variable formed as a linear centered at (1,3) with a standard deviation of 3 in
combination of the original variables that explains the roughly the (0.866, 0.5) direction and of 1 in the
most variance. The second principal component orthogonal direction. The vectors shown are the
explains the most variance in what is left once the eigenvectors of the covariance matrix scaled by
effect of the first component is removed, and we may the square root of the corresponding eigenvalue,
proceed through iterations until all the variance is and shifted so their tails are at the mean.
explained. PCA is most commonly used when many of
the variables are highly correlated with each other and
it is desirable to reduce their number to an independent set.

PCA is used in exploratory data analysis and for making predictive models. It is commonly used for
dimensionality reduction by projecting each data point onto only the first few principal components to
obtain lower-dimensional data while preserving as much of the data's variation as possible. The first
principal component can equivalently be defined as a direction that maximizes the variance of the projected
data. The -th principal component can be taken as a direction orthogonal to the first principal
components that maximizes the variance of the projected data.

For either objective, it can be shown that the principal components are eigenvectors of the data's covariance
matrix. Thus, the principal components are often computed by eigendecomposition of the data covariance
matrix or singular value decomposition of the data matrix. PCA is the simplest of the true eigenvector-based
multivariate analyses and is closely related to factor analysis. Factor analysis typically incorporates more
domain specific assumptions about the underlying structure and solves eigenvectors of a slightly different
matrix. PCA is also related to canonical correlation analysis (CCA). CCA defines coordinate systems that
optimally describe the cross-covariance between two datasets while PCA defines a new orthogonal
coordinate system that optimally describes variance in a single dataset.[2][3][4][5] Robust and L1-norm-
based variants of standard PCA have also been proposed.[6][7][8][5]

History
PCA was invented in 1901 by Karl Pearson,[9] as an analogue of the principal axis theorem in mechanics; it
was later independently developed and named by Harold Hotelling in the 1930s.[10] Depending on the
field of application, it is also named the discrete Karhunen–Loève transform (KLT) in signal processing, the
Hotelling transform in multivariate quality control, proper orthogonal decomposition (POD) in mechanical
engineering, singular value decomposition (SVD) of X (invented in the last quarter of the 19th century[11]),
eigenvalue decomposition (EVD) of XTX in linear algebra, factor analysis (for a discussion of the
differences between PCA and factor analysis see Ch.  7 of Jolliffe's Principal Component Analysis),[12]
Eckart–Young theorem (Harman, 1960), or empirical orthogonal functions (EOF) in meteorological science
(Lorenz, 1956), empirical eigenfunction decomposition (Sirovich, 1987), quasiharmonic modes (Brooks et
al., 1988), spectral decomposition in noise and vibration, and empirical modal analysis in structural
dynamics.

Intuition
PCA can be thought of as fitting a p-dimensional ellipsoid to the data, where each axis of the ellipsoid
represents a principal component. If some axis of the ellipsoid is small, then the variance along that axis is
also small.

To find the axes of the ellipsoid, we must first center the values of each variable in the dataset on 0 by
subtracting the mean of the variable's observed values from each of those values. These transformed values
are used instead of the original observed values for each of the variables. Then, we compute the covariance
matrix of the data and calculate the eigenvalues and corresponding eigenvectors of this covariance matrix.
Then we must normalize each of the orthogonal eigenvectors to turn them into unit vectors. Once this is
done, each of the mutually-orthogonal unit eigenvectors can be interpreted as an axis of the ellipsoid fitted
to the data. This choice of basis will transform the covariance matrix into a diagonalized form, in which the
diagonal elements represent the variance of each axis. The proportion of the variance that each eigenvector
represents can be calculated by dividing the eigenvalue corresponding to that eigenvector by the sum of all
eigenvalues.

Biplots and scree plots (degree of explained variance) are used to explain findings of the PCA.

Details
PCA is defined as an orthogonal linear transformation that transforms the data to a new coordinate system
such that the greatest variance by some scalar projection of the data comes to lie on the first coordinate
(called the first principal component), the second greatest variance on the second coordinate, and so on.[12]

Consider an data matrix, X, with column-wise zero empirical mean (the sample mean of each
column has been shifted to zero), where each of the n rows represents a different repetition of the
experiment, and each of the p columns gives a particular kind of feature (say, the results from a particular
sensor).
Mathematically, the transformation is defined by a set of size of p-
dimensional vectors of weights or coefficients
that map each row vector of X to a
new vector of principal component scores ,
given by

The above picture is of a scree plot

that is meant to help interpret the
PCA and decide how many
components to retain. The start of
the bend in the line (point of
inflexion) should indicate how many
components are retained, hence in
this example, three factors should
be retained.

in such a way that the individual variables of t considered over the data set successively inherit
the maximum possible variance from X, with each coefficient vector w constrained to be a unit vector
(where is usually selected to be strictly less than to reduce dimensionality).

First component

In order to maximize variance, the first weight vector w(1) thus has to satisfy

Equivalently, writing this in matrix form gives

Since w(1) has been defined to be a unit vector, it equivalently also satisfies

The quantity to be maximised can be recognised as a Rayleigh quotient. A standard result for a positive
semidefinite matrix such as XTX is that the quotient's maximum possible value is the largest eigenvalue of
the matrix, which occurs when w is the corresponding eigenvector.
With w(1) found, the first principal component of a data vector x(i) can then be given as a score t1(i) = x(i) ⋅
w(1) in the transformed co-ordinates, or as the corresponding vector in the original variables, {x(i) ⋅ w(1)}
w(1).

Further components

The k-th component can be found by subtracting the first k − 1 principal components from X:

and then finding the weight vector which extracts the maximum variance from this new data matrix

It turns out that this gives the remaining eigenvectors of XTX, with the maximum values for the quantity in
brackets given by their corresponding eigenvalues. Thus the weight vectors are eigenvectors of XTX.

The k-th principal component of a data vector x(i) can therefore be given as a score tk(i) = x(i) ⋅ w(k) in the
transformed coordinates, or as the corresponding vector in the space of the original variables, {x(i) ⋅ w(k)}
w(k), where w(k) is the kth eigenvector of XTX.

The full principal components decomposition of X can therefore be given as

where W is a p-by-p matrix of weights whose columns are the eigenvectors of XTX. The transpose of W is
sometimes called the whitening or sphering transformation. Columns of W multiplied by the square root of
corresponding eigenvalues, that is, eigenvectors scaled up by the variances, are called loadings in PCA or
in Factor analysis.

Covariances

XTX itself can be recognized as proportional to the empirical sample covariance matrix of the dataset
XT.[12]: 3 0–31 

The sample covariance Q between two of the different principal components over the dataset is given by:

where the eigenvalue property of w(k) has been used to move from line 2 to line 3. However eigenvectors
w(j) and w(k) corresponding to eigenvalues of a symmetric matrix are orthogonal (if the eigenvalues are
different), or can be orthogonalised (if the vectors happen to share an equal repeated value). The product in
the final line is therefore zero; there is no sample covariance between different principal components over
the dataset.

Another way to characterise the principal components transformation is therefore as the transformation to
coordinates which diagonalise the empirical sample covariance matrix.

In matrix form, the empirical covariance matrix for the original variables can be written

The empirical covariance matrix between the principal components becomes

where Λ is the diagonal matrix of eigenvalues λ(k) of XTX. λ(k) is equal to the sum of the squares over the
dataset associated with each component k, that is, λ(k) = Σi tk2 (i) = Σi (x(i) ⋅ w(k))2 .

Dimensionality reduction

The transformation T = X W maps a data vector x(i) from an original space of p variables to a new space of
p variables which are uncorrelated over the dataset. However, not all the principal components need to be
kept. Keeping only the first L principal components, produced by using only the first L eigenvectors, gives
the truncated transformation

where the matrix TL now has n rows but only L columns. In other words, PCA learns a linear
transformation where the columns of p × L matrix form an orthogonal
basis for the L features (the components of representation t) that are decorrelated.[13] By construction, of all
the transformed data matrices with only L columns, this score matrix maximises the variance in the original
data that has been preserved, while minimising the total squared reconstruction error
or .

Such dimensionality reduction can be a very useful step for visualising and processing high-dimensional
datasets, while still retaining as much of the variance in the dataset as possible. For example, selecting L = 2
and keeping only the first two principal components finds the two-dimensional plane through the high-
dimensional dataset in which the data is most spread out, so if the data contains clusters these too may be
most spread out, and therefore most visible to be plotted out in a two-dimensional diagram; whereas if two
directions through the data (or two of the original variables) are chosen at random, the clusters may be
much less spread apart from each other, and may in fact be much more likely to substantially overlay each
other, making them indistinguishable.

Similarly, in regression analysis, the larger the number of explanatory variables allowed, the greater is the
chance of overfitting the model, producing conclusions that fail to generalise to other datasets. One
approach, especially when there are strong correlations between different possible explanatory variables, is
to reduce them to a few principal components and then run the regression against them, a method called
principal component regression.

Dimensionality reduction may also be appropriate when the variables in a dataset are noisy. If each column
of the dataset contains independent identically distributed Gaussian noise, then the columns of T will also
contain similarly identically distributed Gaussian noise (such a distribution is invariant under the effects of
the matrix W, which can be thought of as a high-dimensional
rotation of the co-ordinate axes). However, with more of the total
variance concentrated in the first few principal components
compared to the same noise variance, the proportionate effect of the
noise is less—the first few components achieve a higher signal-to-
noise ratio. PCA thus can have the effect of concentrating much of
the signal into the first few principal components, which can
usefully be captured by dimensionality reduction; while the later
principal components may be dominated by noise, and so disposed
of without great loss. If the dataset is not too large, the significance
of the principal components can be tested using parametric A principal components analysis
bootstrap, as an aid in determining how many principal components scatterplot of Y-STR haplotypes
to retain.[14] calculated from repeat-count values
for 37 Y-chromosomal STR markers
from 354 individuals.
Singular value decomposition PCA has successfully found linear
combinations of the markers that
The principal components transformation can also be associated separate out different clusters
with another matrix factorization, the singular value decomposition corresponding to different lines of
(SVD) of X, individuals' Y-chromosomal genetic
descent.

Here Σ is an n-by-p rectangular diagonal matrix of positive numbers σ(k), called the singular values of X; U
is an n-by-n matrix, the columns of which are orthogonal unit vectors of length n called the left singular
vectors of X; and W is a p-by-p matrix whose columns are orthogonal unit vectors of length p and called
the right singular vectors of X.

In terms of this factorization, the matrix XTX can be written

where is the square diagonal matrix with the singular values of X and the excess zeros chopped off that
satisfies . Comparison with the eigenvector factorization of XTX establishes that the right
singular vectors W of X are equivalent to the eigenvectors of XTX, while the singular values σ(k) of are
equal to the square-root of the eigenvalues λ(k) of XTX.

Using the singular value decomposition the score matrix T can be written

so each column of T is given by one of the left singular vectors of X multiplied by the corresponding
singular value. This form is also the polar decomposition of T.

Efficient algorithms exist to calculate the SVD of X without having to form the matrix XTX, so computing
the SVD is now the standard way to calculate a principal components analysis from a data matrix, unless
only a handful of components are required.
As with the eigen-decomposition, a truncated n × L score matrix TL can be obtained by considering only
the first L largest singular values and their singular vectors:

The truncation of a matrix M or T using a truncated singular value decomposition in this way produces a
truncated matrix that is the nearest possible matrix of rank L to the original matrix, in the sense of the
difference between the two having the smallest possible Frobenius norm, a result known as the Eckart–
Young theorem [1936].

Further considerations
The singular values (in Σ) are the square roots of the eigenvalues of the matrix XTX. Each eigenvalue is
proportional to the portion of the "variance" (more correctly of the sum of the squared distances of the
points from their multidimensional mean) that is associated with each eigenvector. The sum of all the
eigenvalues is equal to the sum of the squared distances of the points from their multidimensional mean.
PCA essentially rotates the set of points around their mean in order to align with the principal components.
This moves as much of the variance as possible (using an orthogonal transformation) into the first few
dimensions. The values in the remaining dimensions, therefore, tend to be small and may be dropped with
minimal loss of information (see below). PCA is often used in this manner for dimensionality reduction.
PCA has the distinction of being the optimal orthogonal transformation for keeping the subspace that has
largest "variance" (as defined above). This advantage, however, comes at the price of greater computational
requirements if compared, for example, and when applicable, to the discrete cosine transform, and in
particular to the DCT-II which is simply known as the "DCT". Nonlinear dimensionality reduction
techniques tend to be more computationally demanding than PCA.

PCA is sensitive to the scaling of the variables. If we have just two variables and they have the same
sample variance and are completely correlated, then the PCA will entail a rotation by 45° and the "weights"
(they are the cosines of rotation) for the two variables with respect to the principal component will be equal.
But if we multiply all values of the first variable by 100, then the first principal component will be almost
the same as that variable, with a small contribution from the other variable, whereas the second component
will be almost aligned with the second original variable. This means that whenever the different variables
have different units (like temperature and mass), PCA is a somewhat arbitrary method of analysis.
(Different results would be obtained if one used Fahrenheit rather than Celsius for example.) Pearson's
original paper was entitled "On Lines and Planes of Closest Fit to Systems of Points in Space" – "in space"
implies physical Euclidean space where such concerns do not arise. One way of making the PCA less
arbitrary is to use variables scaled so as to have unit variance, by standardizing the data and hence use the
autocorrelation matrix instead of the autocovariance matrix as a basis for PCA. However, this compresses
(or expands) the fluctuations in all dimensions of the signal space to unit variance.

Mean subtraction (a.k.a. "mean centering") is necessary for performing classical PCA to ensure that the first
principal component describes the direction of maximum variance. If mean subtraction is not performed, the
first principal component might instead correspond more or less to the mean of the data. A mean of zero is
needed for finding a basis that minimizes the mean square error of the approximation of the data.[15]

Mean-centering is unnecessary if performing a principal components analysis on a correlation matrix, as the

data are already centered after calculating correlations. Correlations are derived from the cross-product of
two standard scores (Z-scores) or statistical moments (hence the name: Pearson Product-Moment
Correlation). Also see the article by Kromrey & Foster-Johnson (1998) on "Mean-centering in Moderated
Regression: Much Ado About Nothing". Since covariances are correlations of normalized variables (Z- or
standard-scores) a PCA based on the correlation matrix of X is equal to a PCA based on the covariance
matrix of Z, the standardized version of X.
PCA is a popular primary technique in pattern recognition. It is not, however, optimized for class
separability.[16] However, it has been used to quantify the distance between two or more classes by
calculating center of mass for each class in principal component space and reporting Euclidean distance
between center of mass of two or more classes.[17] The linear discriminant analysis is an alternative which
is optimized for class separability.

Table of symbols and abbreviations

Symbol Meaning Dimensions Indices

data matrix, consisting of the set of all data vectors, one vector per
row

the number of row vectors in the data set scalar

the number of elements in each row vector (dimension) scalar

the number of dimensions in the dimensionally reduced subspace,

scalar

vector of empirical means, one mean for each column j of the data
matrix
vector of empirical standard deviations, one standard deviation for
each column j of the data matrix

vector of all 1's

deviations from the mean of each column j of the data matrix

z-scores, computed using the mean and standard deviation for each
row m of the data matrix

covariance matrix

correlation matrix

matrix consisting of the set of all eigenvectors of C, one eigenvector

per column

diagonal matrix consisting of the set of all eigenvalues of C along its

principal diagonal, and 0 for all other elements ( note used above )

matrix of basis vectors, one vector per column, where each basis
vector is one of the eigenvectors of C, and where the vectors in W
are a sub-set of those in V

matrix consisting of n row vectors, where each vector is the

projection of the corresponding data vector from matrix X onto the
basis vectors contained in the columns of matrix W.

Properties and limitations of PCA

Properties

Some properties of PCA include:[12]

 Property 1: For any integer q, 1 ≤ q ≤ p, consider the orthogonal linear transformation

where is a q-element vector and is a (q × p) matrix, and let be the

variance-covariance matrix for . Then the trace of , denoted , is maximized by
taking , where consists of the first q columns of is the transpose of .

Property 2: Consider again the orthonormal transformation

with and defined as before. Then is minimized by taking

where consists of the last q columns of .

The statistical implication of this property is that the last few PCs are not simply unstructured left-overs after
removing the important PCs. Because these last PCs have variances as small as possible they are useful in
their own right. They can help to detect unsuspected near-constant linear relationships between the
elements of x, and they may also be useful in regression, in selecting a subset of variables from x, and in
outlier detection.

Property 3: (Spectral decomposition of Σ)

Before we look at its usage, we first look at diagonal elements,

Then, perhaps the main statistical implication of the result is that not only can we decompose the combined
variances of all the elements of x into decreasing contributions due to each PC, but we can also decompose
the whole covariance matrix into contributions from each PC. Although not strictly decreasing,
the elements of will tend to become smaller as increases, as is nonincreasing for
increasing , whereas the elements of tend to stay about the same size because of the normalization
constraints: .

Limitations

As noted above, the results of PCA depend on the scaling of the variables. This can be cured by scaling
each feature by its standard deviation, so that one ends up with dimensionless features with unital
variance.[18]

The applicability of PCA as described above is limited by certain (tacit) assumptions[19] made in its
derivation. In particular, PCA can capture linear correlations between the features but fails when this
assumption is violated (see Figure 6a in the reference). In some cases, coordinate transformations can
restore the linearity assumption and PCA can then be applied (see kernel PCA).
Another limitation is the mean-removal process before constructing the covariance matrix for PCA. In
fields such as astronomy, all the signals are non-negative, and the mean-removal process will force the
mean of some astrophysical exposures to be zero, which consequently creates unphysical negative
fluxes,[20] and forward modeling has to be performed to recover the true magnitude of the signals.[21] As
an alternative method, non-negative matrix factorization focusing only on the non-negative elements in the
matrices, which is well-suited for astrophysical observations.[22][23][24] See more at Relation between PCA
and Non-negative Matrix Factorization.

PCA is at a disadvantage if the data has not been standardized before applying the algorithm to it. PCA
transforms original data into data that is relevant to the principal components of that data, which means that
the new data variables cannot be interpreted in the same ways that the originals were. They are linear
interpretations of the original variables. Also, if PCA is not performed properly, there is a high likelihood of
information loss.[25]

PCA relies on a linear model. If a dataset has a pattern hidden inside it that is nonlinear, then PCA can
actually steer the analysis in the complete opposite direction of progress.[26] Researchers at Kansas State
University discovered that the sampling error in their experiments impacted the bias of PCA results. "If the
number of subjects or blocks is smaller than 30, and/or the researcher is interested in PC's beyond the first,
it may be better to first correct for the serial correlation, before PCA is conducted".[27] The researchers at
Kansas State also found that PCA could be "seriously biased if the autocorrelation structure of the data is
not correctly handled".[27]

PCA and information theory

Dimensionality reduction results in a loss of information, in general. PCA-based dimensionality reduction

tends to minimize that information loss, under certain signal and noise models.

Under the assumption that

that is, that the data vector is the sum of the desired information-bearing signal and a noise signal one
can show that PCA can be optimal for dimensionality reduction, from an information-theoretic point-of-
view.

In particular, Linsker showed that if is Gaussian and is Gaussian noise with a covariance matrix
proportional to the identity matrix, the PCA maximizes the mutual information between the desired
information and the dimensionality-reduced output .[28]

If the noise is still Gaussian and has a covariance matrix proportional to the identity matrix (that is, the
components of the vector are iid), but the information-bearing signal is non-Gaussian (which is a
common scenario), PCA at least minimizes an upper bound on the information loss, which is defined
as[29][30]
The optimality of PCA is also preserved if the noise is iid and at least more Gaussian (in terms of the
Kullback–Leibler divergence) than the information-bearing signal .[31] In general, even if the above signal
model holds, PCA loses its information-theoretic optimality as soon as the noise becomes dependent.

Computing PCA using the covariance method

The following is a detailed description of PCA using the covariance method (see also here (http://www.cs.o
tago.ac.nz/cosc453/student_tutorials/principal_components.pdf)) as opposed to the correlation method.[32]

The goal is to transform a given data set X of dimension p to an alternative data set Y of smaller dimension
L. Equivalently, we are seeking to find the matrix Y, where Y is the Karhunen–Loève transform (KLT) of
matrix X:

Organize the data set

Suppose you have data comprising a set of observations of p variables, and you want to reduce the data so
that each observation can be described with only L variables, L < p. Suppose further, that the data are
arranged as a set of n data vectors with each representing a single grouped observation of the
p variables.

Write as row vectors, each with p elements.

Place the row vectors into a single matrix X of dimensions n × p.

Calculate the empirical mean

Find the empirical mean along each column j = 1, ..., p.

Place the calculated mean values into an empirical mean vector u of dimensions p × 1.

Calculate the deviations from the mean

Mean subtraction is an integral part of the solution towards finding a principal component basis that
minimizes the mean square error of approximating the data.[33] Hence we proceed by centering the data as
follows:

Subtract the empirical mean vector from each row of the data matrix X.
Store mean-subtracted data in the n × p matrix B.

where h is an n × 1 column vector of all 1s:

In some applications, each variable (column of B) may also be scaled to have a variance equal to 1 (see Z-
score).[34] This step affects the calculated principal components, but makes them independent of the units
used to measure the different variables.
Find the covariance matrix

Find the p × p empirical covariance matrix C from matrix B:

where is the conjugate transpose operator. If B consists entirely of real numbers, which is
the case in many applications, the "conjugate transpose" is the same as the regular
transpose.
The reasoning behind using n − 1 instead of n to calculate the covariance is Bessel's
correction.

Find the eigenvectors and eigenvalues of the covariance matrix

Compute the matrix V of eigenvectors which diagonalizes the covariance matrix C:

where D is the diagonal matrix of eigenvalues of C. This step will typically involve the use of
a computer-based algorithm for computing eigenvectors and eigenvalues. These algorithms
are readily available as sub-components of most matrix algebra systems, such as SAS,[35]
R, MATLAB,[36][37] Mathematica,[38] SciPy, IDL (Interactive Data Language), or GNU Octave
as well as OpenCV.
Matrix D will take the form of an p × p diagonal matrix, where

is the jth eigenvalue of the covariance matrix C, and

Matrix V, also of dimension p × p, contains p column vectors, each of length p, which

represent the p eigenvectors of the covariance matrix C.
The eigenvalues and eigenvectors are ordered and paired. The jth eigenvalue corresponds
to the jth eigenvector.
Matrix V denotes the matrix of right eigenvectors (as opposed to left eigenvectors). In
general, the matrix of right eigenvectors need not be the (conjugate) transpose of the matrix
of left eigenvectors.

Rearrange the eigenvectors and eigenvalues

Sort the columns of the eigenvector matrix V and eigenvalue matrix D in order of decreasing
eigenvalue.
Make sure to maintain the correct pairings between the columns in each matrix.

Compute the cumulative energy content for each eigenvector

The eigenvalues represent the distribution of the source data's energy among each of the
eigenvectors, where the eigenvectors form a basis for the data. The cumulative energy
content g for the jth eigenvector is the sum of the energy content across all of the
eigenvalues from 1 through j:
Select a subset of the eigenvectors as basis vectors

Save the first L columns of V as the p × L matrix W:

where

Use the vector g as a guide in choosing an appropriate value for L. The goal is to choose a
value of L as small as possible while achieving a reasonably high value of g on a
percentage basis. For example, you may want to choose L so that the cumulative energy g is
above a certain threshold, like 90 percent. In this case, choose the smallest value of L such
that

Project the data onto the new basis

The projected data points are the rows of the matrix

That is, the first column of is the projection of the data points onto the first principal component, the
second column is the projection onto the second principal component, etc.

Derivation of PCA using the covariance method

Let X be a d-dimensional random vector expressed as column vector. Without loss of generality, assume X
has zero mean.

We want to find a d × d orthonormal transformation matrix P so that PX has a diagonal covariance

matrix (that is, PX is a random vector with all its distinct components pairwise uncorrelated).

A quick computation assuming were unitary yields:

Hence holds if and only if were diagonalisable by .

This is very constructive, as cov(X) is guaranteed to be a non-negative definite matrix and thus is
guaranteed to be diagonalisable by some unitary matrix.

Covariance-free computation
In practical implementations, especially with high dimensional data (large p ), the naive covariance method
is rarely used because it is not efficient due to high computational and memory costs of explicitly
determining the covariance matrix. The covariance-free approach avoids the np 2 operations of explicitly
calculating and storing the covariance matrix XTX, instead utilizing one of matrix-free methods, for
example, based on the function evaluating the product XT(X r) at the cost of 2np operations.

Iterative computation

One way to compute the first principal component efficiently[39] is shown in the following pseudo-code,
for a data matrix X with zero mean, without ever computing its covariance matrix.

r = a random vector of length p

r = r / norm(r)
do c times:
s = 0 (a vector of length p )
for each row x in X
s = s + (x ⋅ r) x
λ = r Ts // λ is the eigenvalue
error = |λ ⋅ r − s|
r = s / norm(s)
exit if error < tolerance
return λ, r

This power iteration algorithm simply calculates the vector XT(X r), normalizes, and places the result
back in r. The eigenvalue is approximated by rT (XTX) r, which is the Rayleigh quotient on the unit
vector r for the covariance matrix XTX . If the largest singular value is well separated from the next
largest one, the vector r gets close to the first principal component of X within the number of iterations c,
which is small relative to p , at the total cost 2cnp . The power iteration convergence can be accelerated
without noticeably sacrificing the small cost per iteration using more advanced matrix-free methods, such as
the Lanczos algorithm or the Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG)
method.

Subsequent principal components can be computed one-by-one via deflation or simultaneously as a block.
In the former approach, imprecisions in already computed approximate principal components additively
affect the accuracy of the subsequently computed principal components, thus increasing the error with
every new computation. The latter approach in the block power method replaces single-vectors r and s
with block-vectors, matrices R and S . Every column of R approximates one of the leading principal
components, while all columns are iterated simultaneously. The main calculation is evaluation of the
product XT(X R). Implemented, for example, in LOBPCG, efficient blocking eliminates the
accumulation of the errors, allows using high-level BLAS matrix-matrix product functions, and typically
leads to faster convergence, compared to the single-vector one-by-one technique.

The NIPALS method

Non-linear iterative partial least squares (NIPALS) is a variant the classical power iteration with matrix
deflation by subtraction implemented for computing the first few components in a principal component or
partial least squares analysis. For very-high-dimensional datasets, such as those generated in the *omics
sciences (for example, genomics, metabolomics) it is usually only necessary to compute the first few PCs.
The non-linear iterative partial least squares (NIPALS) algorithm updates iterative approximations to the
leading scores and loadings t1 and r1 T by the power iteration multiplying on every iteration by X on the left
and on the right, that is, calculation of the covariance matrix is avoided, just as in the matrix-free
implementation of the power iterations to XTX, based on the function evaluating the product
XT(X r) = ((X r)TX)T.
The matrix deflation by subtraction is performed by subtracting the outer product, t1 r1 T from X leaving the
deflated residual matrix used to calculate the subsequent leading PCs.[40] For large data matrices, or
matrices that have a high degree of column collinearity, NIPALS suffers from loss of orthogonality of PCs
due to machine precision round-off errors accumulated in each iteration and matrix deflation by
subtraction.[41] A Gram–Schmidt re-orthogonalization algorithm is applied to both the scores and the
loadings at each iteration step to eliminate this loss of orthogonality.[42] NIPALS reliance on single-vector
multiplications cannot take advantage of high-level BLAS and results in slow convergence for clustered
leading singular values—both these deficiencies are resolved in more sophisticated matrix-free block
solvers, such as the Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) method.

Online/sequential estimation

In an "online" or "streaming" situation with data arriving piece by piece rather than being stored in a single
batch, it is useful to make an estimate of the PCA projection that can be updated sequentially. This can be
done efficiently, but requires different algorithms.[43]

PCA and qualitative variables

In PCA, it is common that we want to introduce qualitative variables as supplementary elements. For
example, many quantitative variables have been measured on plants. For these plants, some qualitative
variables are available as, for example, the species to which the plant belongs. These data were subjected to
PCA for quantitative variables. When analyzing the results, it is natural to connect the principal components
to the qualitative variable species. For this, the following results are produced.

Identification, on the factorial planes, of the different species, for example, using different
colors.
Representation, on the factorial planes, of the centers of gravity of plants belonging to the
same species.
For each center of gravity and each axis, p-value to judge the significance of the difference
between the center of gravity and origin.

These results are what is called introducing a qualitative variable as supplementary element. This
procedure is detailed in and Husson, Lê & Pagès 2009 and Pagès 2013. Few software offer this option in
an "automatic" way. This is the case of SPAD (http://www.coheris.com/produits/analytics/logiciel-data-min
ing/) that historically, following the work of Ludovic Lebart, was the first to propose this option, and the R
package FactoMineR (http://factominer.free.fr/).

Applications

Intelligence

The earliest application of factor analysis was in locating and measuring components of human intelligence.
it was believed that intelligence had various uncorrelated components such as spatial intelligence, verbal
intelligence, induction, deduction etc and that scores on these could be adduced by factor analysis from
results on various tests, to give a single index known as the Intelligence Quotient (IQ). The pioneering
statistical psychologist Spearman actually developed factor analysis in 1904 for his two-factor theory of
intelligence, adding a formal technique to the science of psychometrics. In 1924 Thurstone looked for 56
factors of intelligence, developing the notion of Mental Age. Standard IQ tests today are based on this early
work.[44]

Residential differentiation

In 1949, Shevky and Williams introduced the theory of factorial ecology, which dominated studies of
residential differentiation from the 1950s to the 1970s.[45] Neighbourhoods in a city were recognizable or
could be distinguished from one another by various characteristics which could be reduced to three by
factor analysis. These were known as 'social rank' (an index of occupational status), 'familism' or family
size, and 'ethnicity'; Cluster analysis could then be applied to divide the city into clusters or precincts
according to values of the three key factor variables. An extensive literature developed around factorial
ecology in urban geography, but the approach went out of fashion after 1980 as being methodologically
primitive and having little place in postmodern geographical paradigms.

One of the problems with factor analysis has always been finding convincing names for the various
artificial factors. In 2000, Flood revived the factorial ecology approach to show that principal components
analysis actually gave meaningful answers directly, without resorting to factor rotation. The principal
components were actually dual variables or shadow prices of 'forces' pushing people together or apart in
cities. The first component was 'accessibility', the classic trade-off between demand for travel and demand
for space, around which classical urban economics is based. The next two components were 'disadvantage',
which keeps people of similar status in separate neighbourhoods (mediated by planning), and ethnicity,
where people of similar ethnic backgrounds try to co-locate.[46]

About the same time, the Australian Bureau of Statistics defined distinct indexes of advantage and
disadvantage taking the first principal component of sets of key variables that were thought to be important.
These SEIFA indexes are regularly published for various jurisdictions, and are used frequently in spatial
analysis.[47]

Development indexes

PCA has been the only formal method available for the development of indexes, which are otherwise a hit-
or-miss ad hoc undertaking.

The City Development Index was developed by PCA from about 200 indicators of city outcomes in a 1996
survey of 254 global cities. The first principal component was subject to iterative regression, adding the
original variables singly until about 90% of its variation was accounted for. The index ultimately used about
15 indicators but was a good predictor of many more variables. Its comparative value agreed very well with
a subjective assessment of the condition of each city. The coefficients on items of infrastructure were
roughly proportional to the average costs of providing the underlying services, suggesting the Index was
actually a measure of effective physical and social investment in the city.

The country-level Human Development Index (HDI) from UNDP, which has been published since 1990
and is very extensively used in development studies,[48] has very similar coefficients on similar indicators,
strongly suggesting it was originally constructed using PCA.

Population genetics
In 1978 Cavalli-Sforza and others pioneered the use of principal components analysis (PCA) to summarise
data on variation in human gene frequencies across regions. The components showed distinctive patterns,
including gradients and sinusoidal waves. They interpreted these patterns as resulting from specific ancient
migration events.

Since then, PCA has been ubiquitous in population genetics, with thousands of papers using PCA as a
display mechanism. Genetics varies largely according to proximity, so the first two principal components
actually show spatial distribution and may be used to map the relative geographical location of different
population groups, thereby showing individuals who have wandered from their original locations.[49]

PCA in genetics has been technically controversial, in that the technique has been performed on discrete
non-normal variables and often on binary allele markers. The lack of any measures of standard error in
PCA are also an impediment to more consistent usage. In August 2022, the molecular biologist Eran Elhaik
published a theoretical paper in Scientific Reports analyzing 12 PCA applications. He concluded that it was
easy to manipulate the method, which, in his view, generated results that were 'erroneous, contradictory,
and absurd.' Specifically, he argued, the results achieved in population genetics were characterized by
cherry-picking and circular reasoning.[50]

Market research and indexes of attitude

Market research has been an extensive user of PCA. It is used to develop customer satisfaction or customer
loyalty scores for products, and with clustering, to develop market segments that may be targeted with
advertising campaigns, in much the same way as factorial ecology will locate geographical areas with
similar characteristics.[51]

PCA rapidly transforms large amounts of data into smaller, easier-to-digest variables that can be more
rapidly and readily analyzed. In any consumer questionnaire, there are series of questions designed to elicit
consumer attitudes, and principal components seek out latent variables underlying these attitudes. For
example, the Oxford Internet Survey in 2013 asked 2000 people about their attitudes and beliefs, and from
these analysts extracted four principal component dimensions, which they identified as 'escape', 'social
networking', 'efficiency', and 'problem creating'.[52]

Another example from Joe Flood in 2008 extracted an attitudinal index toward housing from 28 attitude
questions in a national survey of 2697 households in Australia. The first principal component represented a
general attitude toward property and home ownership. The index, or the attitude questions it embodied,
could be fed into a General Linear Model of tenure choice. The strongest determinant of private renting by
far was the attitude index, rather than income, marital status or household type.[53]

Quantitative finance

PCA has also been applied to equity portfolios,[54] both to portfolio risk and to risk return. One application
is to reduce portfolio risk, where allocation strategies are applied to the "principal portfolios" instead of the
underlying stocks.[55] A second is to enhance portfolio return, using the principal components to select
stocks with upside potential.

Neuroscience
A variant of principal components analysis is used in neuroscience to identify the specific properties of a
stimulus that increases a neuron's probability of generating an action potential.[56][57] This technique is
known as spike-triggered covariance analysis. In a typical application an experimenter presents a white
noise process as a stimulus (usually either as a sensory input to a test subject, or as a current injected
directly into the neuron) and records a train of action potentials, or spikes, produced by the neuron as a
result. Presumably, certain features of the stimulus make the neuron more likely to spike. In order to extract
these features, the experimenter calculates the covariance matrix of the spike-triggered ensemble, the set of
all stimuli (defined and discretized over a finite time window, typically on the order of 100 ms) that
immediately preceded a spike. The eigenvectors of the difference between the spike-triggered covariance
matrix and the covariance matrix of the prior stimulus ensemble (the set of all stimuli, defined over the
same length time window) then indicate the directions in the space of stimuli along which the variance of
the spike-triggered ensemble differed the most from that of the prior stimulus ensemble. Specifically, the
eigenvectors with the largest positive eigenvalues correspond to the directions along which the variance of
the spike-triggered ensemble showed the largest positive change compared to the variance of the prior.
Since these were the directions in which varying the stimulus led to a spike, they are often good
approximations of the sought after relevant stimulus features.

In neuroscience, PCA is also used to discern the identity of a neuron from the shape of its action potential.
Spike sorting is an important procedure because extracellular recording techniques often pick up signals
from more than one neuron. In spike sorting, one first uses PCA to reduce the dimensionality of the space
of action potential waveforms, and then performs clustering analysis to associate specific action potentials
with individual neurons.

PCA as a dimension reduction technique is particularly suited to detect coordinated activities of large
neuronal ensembles. It has been used in determining collective variables, that is, order parameters, during
phase transitions in the brain.[58]

Relation with other methods

Correspondence analysis

Correspondence analysis (CA) was developed by Jean-Paul Benzécri[59] and is conceptually similar to
PCA, but scales the data (which should be non-negative) so that rows and columns are treated equivalently.
It is traditionally applied to contingency tables. CA decomposes the chi-squared statistic associated to this
table into orthogonal factors.[60] Because CA is a descriptive technique, it can be applied to tables for
which the chi-squared statistic is appropriate or not. Several variants of CA are available including
detrended correspondence analysis and canonical correspondence analysis. One special extension is
multiple correspondence analysis, which may be seen as the counterpart of principal component analysis
for categorical data.[61]

Factor analysis

Principal component analysis creates variables that are linear combinations of the original variables. The
new variables have the property that the variables are all orthogonal. The PCA transformation can be
helpful as a pre-processing step before clustering. PCA is a variance-focused approach seeking to
reproduce the total variable variance, in which components reflect both common and unique variance of the
variable. PCA is generally preferred for purposes of data reduction (that is, translating variable space into
optimal factor space) but not when the goal is to detect the latent construct or factors.
Factor analysis is similar to principal component analysis, in that
factor analysis also involves linear combinations of variables.
Different from PCA, factor analysis is a correlation-focused
approach seeking to reproduce the inter-correlations among
variables, in which the factors "represent the common variance of
variables, excluding unique variance".[62] In terms of the
correlation matrix, this corresponds with focusing on explaining the
off-diagonal terms (that is, shared co-variance), while PCA focuses
on explaining the terms that sit on the diagonal. However, as a side
result, when trying to reproduce the on-diagonal terms, PCA also
tends to fit relatively well the off-diagonal correlations.[12]: 1 58 
Results given by PCA and factor analysis are very similar in most
situations, but this is not always the case, and there are some
problems where the results are significantly different. Factor
analysis is generally used when the research purpose is detecting The above picture is an example of
data structure (that is, latent constructs or factors) or causal the difference between PCA and
Factor Analysis. In the top diagram
modeling. If the factor model is incorrectly formulated or the
the "factor" (e.g., career path)
assumptions are not met, then factor analysis will give erroneous
represents the three observed
results.[63]
variables (e.g., doctor, lawyer,
teacher) whereas in the bottom
K-means clustering diagram the observed variables
(e.g., pre-school teacher, middle
school teacher, high school teacher)
It has been asserted that the relaxed solution of k-means clustering,
are reduced into the component of
specified by the cluster indicators, is given by the principal
interest (e.g., teacher).
components, and the PCA subspace spanned by the principal
directions is identical to the cluster centroid subspace.[64][65]
However, that PCA is a useful relaxation of k-means clustering was not a new result,[66] and it is
straightforward to uncover counterexamples to the statement that the cluster centroid subspace is spanned
by the principal directions.[67]

Non-negative matrix factorization

Non-negative matrix factorization (NMF) is a dimension reduction method where only non-negative
elements in the matrices are used, which is therefore a promising method in astronomy,[22][23][24] in the
sense that astrophysical signals are non-negative. The PCA components are orthogonal to each other, while
the NMF components are all non-negative and therefore constructs a non-orthogonal basis.

In PCA, the contribution of each component is ranked based on the magnitude of its corresponding
eigenvalue, which is equivalent to the fractional residual variance (FRV) in analyzing empirical data.[20]
For NMF, its components are ranked based only on the empirical FRV curves.[24] The residual fractional

eigenvalue plots, that is, as a function of component number given a total of

components, for PCA have a flat plateau, where no data is captured to remove the quasi-static noise, then
the curves drop quickly as an indication of over-fitting (random noise).[20] The FRV curves for NMF is
decreasing
continuously[24] when
the NMF components
are constructed
sequentially,[23]
indicating the
continuous capturing
of quasi-static noise;
then converge to
higher levels than
PCA,[24] indicating the
less over-fitting
property of NMF.
Fractional residual variance (FRV) plots for PCA and NMF;[24] for PCA, the
theoretical values are the contribution from the residual eigenvalues. In comparison,
Iconography of the FRV curves for PCA reaches a flat plateau where no signal are captured
correlations effectively; while the NMF FRV curves decline continuously, indicating a better ability
to capture signal. The FRV curves for NMF also converges to higher levels than
PCA, indicating the less-overfitting property of NMF.

It is often difficult to interpret the principal components when the data include many variables of various
origins, or when some variables are qualitative. This leads the PCA user to a delicate elimination of several
variables. If observations or variables have an excessive impact on the direction of the axes, they should be
removed and then projected as supplementary elements. In addition, it is necessary to avoid interpreting the
proximities between the points close to the center of the factorial plane.

The iconography of correlations, on the contrary, which is not a

projection on a system of axes, does not have these drawbacks. We
can therefore keep all the variables.

The principle of the diagram is to underline the "remarkable"

correlations of the correlation matrix, by a solid line (positive
correlation) or dotted line (negative correlation).

A strong correlation is not "remarkable" if it is not direct, but caused

by the effect of a third variable. Conversely, weak correlations can
be "remarkable". For example, if a variable Y depends on several
independent variables, the correlations of Y with each of them are
Iconography of correlations -
weak and yet "remarkable".
Geochemistry of marine aerosols

Generalizations

Sparse PCA

A particular disadvantage of PCA is that the principal components are usually linear combinations of all
input variables. Sparse PCA overcomes this disadvantage by finding linear combinations that contain just a
few input variables. It extends the classic method of principal component analysis (PCA) for the reduction
of dimensionality of data by adding sparsity constraint on the input variables. Several approaches have been
proposed, including
 a regression framework,[68]
a convex relaxation/semidefinite programming framework,[69]
a generalized power method framework[70]
an alternating maximization framework[71]
forward-backward greedy search and exact methods using branch-and-bound
techniques,[72]
Bayesian formulation framework.[73]

The methodological and theoretical developments of Sparse PCA as well as its applications in scientific
studies were recently reviewed in a survey paper.[74]

Nonlinear PCA

Most of the modern methods for nonlinear

dimensionality reduction find their theoretical and
algorithmic roots in PCA or K-means. Pearson's
original idea was to take a straight line (or plane)
which will be "the best fit" to a set of data points.
Trevor Hastie expanded on this concept by proposing
Principal curves[78] as the natural extension for the
geometric interpretation of PCA, which explicitly
constructs a manifold for data approximation followed
by projecting the points onto it, as is illustrated by Fig.
See also the elastic map algorithm and principal
geodesic analysis.[79] Another popular generalization is
kernel PCA, which corresponds to PCA performed in
a reproducing kernel Hilbert space associated with a
positive definite kernel.

In multilinear subspace learning,[80][81][82] PCA is

generalized to multilinear PCA (MPCA) that extracts
features directly from tensor representations. MPCA is Linear PCA versus nonlinear Principal
solved by performing PCA in each mode of the tensor Manifolds[75] for visualization of breast cancer
iteratively. MPCA has been applied to face recognition, microarray data: a) Configuration of nodes and 2D
gait recognition, etc. MPCA is further extended to Principal Surface in the 3D PCA linear manifold.
uncorrelated MPCA, non-negative MPCA and robust The dataset is curved and cannot be mapped
MPCA. adequately on a 2D principal plane; b) The
distribution in the internal 2D non-linear principal
N-way principal component analysis may be surface coordinates (ELMap2D) together with an
performed with models such as Tucker decomposition, estimation of the density of points; c) The same
PARAFAC, multiple factor analysis, co-inertia as b), but for the linear 2D PCA manifold (PCA2D).
analysis, STATIS, and DISTATIS. The "basal" breast cancer subtype is visualized
more adequately with ELMap2D and some
features of the distribution become better resolved
Robust PCA in comparison to PCA2D. Principal manifolds are
produced by the elastic maps algorithm. Data are
While PCA finds the mathematically optimal method available for public competition.[76] Software is
(as in minimizing the squared error), it is still sensitive available for free non-commercial use.[77]
to outliers in the data that produce large errors,
something that the method tries to avoid in the first
place. It is therefore common practice to remove outliers before computing PCA. However, in some
contexts, outliers can be difficult to identify. For example, in data mining algorithms like correlation
clustering, the assignment of points to clusters and outliers is not known beforehand. A recently proposed
generalization of PCA[83] based on a weighted PCA increases robustness by assigning different weights to
data objects based on their estimated relevancy.

Outlier-resistant variants of PCA have also been proposed, based on L1-norm formulations (L1-PCA).[6][4]

Robust principal component analysis (RPCA) via decomposition in low-rank and sparse matrices is a
modification of PCA that works well with respect to grossly corrupted observations.[84][85][86]

Similar techniques

Independent component analysis

Independent component analysis (ICA) is directed to similar problems as principal component analysis, but
finds additively separable components rather than successive approximations.

Network component analysis

Given a matrix , it tries to decompose it into two matrices such that . A key difference from
techniques such as PCA and ICA is that some of the entries of are constrained to be 0. Here is termed
the regulatory layer. While in general such a decomposition can have multiple solutions, they prove that if
the following conditions are satisfied :

1. has full column rank

2. Each column of must have at least zeroes where is the number of columns of
(or alternatively the number of rows of ). The justification for this criterion is that if a node is
removed from the regulatory layer along with all the output nodes connected to it, the result
must still be characterized by a connectivity matrix with full column rank.
3. must have full row rank.

then the decomposition is unique up to multiplication by a scalar.[87]

Discriminant analysis of principal components

Discriminant analysis of principal components (DAPC) is a multivariate method used to identify and
describe clusters of genetically related individuals. Genetic variation is partitioned into two components:
variation between groups and within groups, and it maximizes the former. Linear discriminants are linear
combinations of alleles which best separate the clusters. Alleles that most contribute to this discrimination
are therefore those that are the most markedly different across groups. The contributions of alleles to the
groupings identified by DAPC can allow identifying regions of the genome driving the genetic divergence
among groups[88] In DAPC, data is first transformed using a principal components analysis (PCA) and
subsequently clusters are identified using discriminant analysis (DA).
A DAPC can be realized on R using the package Adegenet. (more info: adegenet on the web (https://adege
net.r-forge.r-project.org/))

Directional component analysis

Directional component analysis (DCA) is a method used in the atmospheric sciences for analysing
multivariate datasets.[89] Like PCA, it allows for dimension reduction, improved visualization and
improved interpretability of large data-sets. Also like PCA, it is based on a covariance matrix derived from
the input dataset. The difference between PCA and DCA is that DCA additionally requires the input of a
vector direction, referred to as the impact. Whereas PCA maximises explained variance, DCA maximises
probability density given impact. The motivation for DCA is to find components of a multivariate dataset
that are both likely (measured using probability density) and important (measured using the impact). DCA
has been used to find the most likely and most serious heat-wave patterns in weather prediction ensembles
,[90] and the most likely and most impactful changes in rainfall due to climate change .[91]

Software/source code
ALGLIB - a C++ and C# library that implements PCA and truncated PCA
Analytica – The built-in EigenDecomp function computes principal components.
ELKI – includes PCA for projection, including robust variants of PCA, as well as PCA-based
clustering algorithms.
Gretl – principal component analysis can be performed either via the pca command or via
the princomp() function.
Julia – Supports PCA with the pca function in the MultivariateStats package
KNIME – A java based nodal arranging software for Analysis, in this the nodes called PCA,
PCA compute, PCA Apply, PCA inverse make it easily.
Maple (software) – The PCA command is used to perform a principal component analysis on
a set of data.
Mathematica – Implements principal component analysis with the PrincipalComponents
command using both covariance and correlation methods.
MathPHP – PHP mathematics library with support for PCA.
MATLAB - The SVD function is part of the basic system. In the Statistics Toolbox, the
functions princomp and pca (R2012b) give the principal components, while the function
pcares gives the residuals and reconstructed matrix for a low-rank PCA approximation.
Matplotlib – Python library have a PCA package in the .mlab module.
mlpack – Provides an implementation of principal component analysis in C++.
mrmath (https://github.com/mikerabat/mrmath) - A high performance math library for Delphi
and FreePascal can perform PCA; including robust variants.
NAG Library – Principal components analysis is implemented via the g03aa routine
(available in both the Fortran versions of the Library).
NMath – Proprietary numerical library containing PCA for the .NET Framework.
GNU Octave – Free software computational environment mostly compatible with MATLAB,
the function princomp gives the principal component.
OpenCV
Oracle Database 12c – Implemented via DBMS_DATA_MINING.SVDS_SCORING_MODE by
specifying setting value SVDS_SCORING_PCA
Orange (software) – Integrates PCA in its visual programming environment. PCA displays a
scree plot (degree of explained variance) where user can interactively select the number of
 principal components.
Origin – Contains PCA in its Pro version.
Qlucore – Commercial software for analyzing multivariate data with instant response using
PCA.
R – Free statistical package, the functions princomp and prcomp can be used for
principal component analysis; prcomp uses singular value decomposition which generally
gives better numerical accuracy. Some packages that implement PCA in R, include, but are
not limited to: ade4, vegan, ExPosition, dimRed, and FactoMineR.
SAS – Proprietary software; for example, see[92]
scikit-learn – Python library for machine learning which contains PCA, Probabilistic PCA,
Kernel PCA, Sparse PCA and other techniques in the decomposition module.
Scilab – Free and open-source, cross-platform numerical computational package, the
function princomp computes principal component analysis, the function pca computes
principal component analysis with standardized variables.
SPSS – Proprietary software most commonly used by social scientists for PCA, factor
analysis and associated cluster analysis.
Weka – Java library for machine learning which contains modules for computing principal
components.

See also
Correspondence analysis (for contingency tables)
Multiple correspondence analysis (for qualitative variables)
Factor analysis of mixed data (for quantitative and qualitative variables)
Canonical correlation
CUR matrix approximation (can replace of low-rank SVD approximation)
Detrended correspondence analysis
Directional component analysis
Dynamic mode decomposition
Eigenface
Expectation–maximization algorithm
Exploratory factor analysis (Wikiversity)
Factorial code
Functional principal component analysis
Geometric data analysis
Independent component analysis
Kernel PCA
L1-norm principal component analysis
Low-rank approximation
Matrix decomposition
Non-negative matrix factorization
Nonlinear dimensionality reduction
Oja's rule
Point distribution model (PCA applied to morphometry and computer vision)
Principal component analysis (Wikibooks)
Principal component regression
Singular spectrum analysis
 Singular value decomposition
Sparse PCA
Transform coding
Weighted least squares

References
1. Jolliffe, Ian T.; Cadima, Jorge (2016-04-13). "Principal component analysis: a review and
recent developments" (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4792409).
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering
Sciences. 374 (2065): 20150202. Bibcode:2016RSPTA.37450202J (https://ui.adsabs.harvar
d.edu/abs/2016RSPTA.37450202J). doi:10.1098/rsta.2015.0202 (https://doi.org/10.1098%2
Frsta.2015.0202). PMC 4792409 (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4792409).
PMID 26953178 (https://pubmed.ncbi.nlm.nih.gov/26953178).
2. Barnett, T. P. & R. Preisendorfer. (1987). "Origins and levels of monthly and seasonal
forecast skill for United States surface air temperatures determined by canonical correlation
analysis" (https://doi.org/10.1175%2F1520-0493%281987%29115%3C1825%3Aoaloma%3
E2.0.co%3B2). Monthly Weather Review. 115 (9): 1825. Bibcode:1987MWRv..115.1825B (h
ttps://ui.adsabs.harvard.edu/abs/1987MWRv..115.1825B). doi:10.1175/1520-
0493(1987)115<1825:oaloma>2.0.co;2 (https://doi.org/10.1175%2F1520-0493%281987%2
9115%3C1825%3Aoaloma%3E2.0.co%3B2).
3. Hsu, Daniel; Kakade, Sham M.; Zhang, Tong (2008). A spectral algorithm for learning hidden
markov models. arXiv:0811.4413 (https://arxiv.org/abs/0811.4413).
Bibcode:2008arXiv0811.4413H (https://ui.adsabs.harvard.edu/abs/2008arXiv0811.4413H).
4. Markopoulos, Panos P.; Kundu, Sandipan; Chamadia, Shubham; Pados, Dimitris A. (15
August 2017). "Efficient L1-Norm Principal-Component Analysis via Bit Flipping". IEEE
Transactions on Signal Processing. 65 (16): 4252–4264. arXiv:1610.01959 (https://arxiv.org/
abs/1610.01959). Bibcode:2017ITSP...65.4252M (https://ui.adsabs.harvard.edu/abs/2017IT
SP...65.4252M). doi:10.1109/TSP.2017.2708023 (https://doi.org/10.1109%2FTSP.2017.2708
023). S2CID 7931130 (https://api.semanticscholar.org/CorpusID:7931130).
5. Chachlakis, Dimitris G.; Prater-Bennette, Ashley; Markopoulos, Panos P. (22 November
2019). "L1-norm Tucker Tensor Decomposition" (https://doi.org/10.1109%2FACCESS.2019.
2955134). IEEE Access. 7: 178454–178465. arXiv:1904.06455 (https://arxiv.org/abs/1904.06
455). doi:10.1109/ACCESS.2019.2955134 (https://doi.org/10.1109%2FACCESS.2019.2955
134).
6. Markopoulos, Panos P.; Karystinos, George N.; Pados, Dimitris A. (October 2014). "Optimal
Algorithms for L1-subspace Signal Processing". IEEE Transactions on Signal Processing.
62 (19): 5046–5058. arXiv:1405.6785 (https://arxiv.org/abs/1405.6785).
Bibcode:2014ITSP...62.5046M (https://ui.adsabs.harvard.edu/abs/2014ITSP...62.5046M).
doi:10.1109/TSP.2014.2338077 (https://doi.org/10.1109%2FTSP.2014.2338077).
S2CID 1494171 (https://api.semanticscholar.org/CorpusID:1494171).
7. Zhan, J.; Vaswani, N. (2015). "Robust PCA With Partial Subspace Knowledge" (https://doi.or
g/10.1109/tsp.2015.2421485). IEEE Transactions on Signal Processing. 63 (13): 3332–
3347. arXiv:1403.1591 (https://arxiv.org/abs/1403.1591). Bibcode:2015ITSP...63.3332Z (http
s://ui.adsabs.harvard.edu/abs/2015ITSP...63.3332Z). doi:10.1109/tsp.2015.2421485 (https://
doi.org/10.1109%2Ftsp.2015.2421485). S2CID 1516440 (https://api.semanticscholar.org/Co
rpusID:1516440).
 8. Kanade, T.; Ke, Qifa (June 2005). Robust L1 Norm Factorization in the Presence of Outliers
and Missing Data by Alternative Convex Programming. 2005 IEEE Computer Society
Conference on Computer Vision and Pattern Recognition (CVPR'05). Vol. 1. IEEE. p. 739.
CiteSeerX 10.1.1.63.4605 (https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.46
05). doi:10.1109/CVPR.2005.309 (https://doi.org/10.1109%2FCVPR.2005.309). ISBN 978-
0-7695-2372-9. S2CID 17144854 (https://api.semanticscholar.org/CorpusID:17144854).
9. Pearson, K. (1901). "On Lines and Planes of Closest Fit to Systems of Points in Space" (http
s://zenodo.org/record/1430636). Philosophical Magazine. 2 (11): 559–572.
doi:10.1080/14786440109462720 (https://doi.org/10.1080%2F14786440109462720).
S2CID 125037489 (https://api.semanticscholar.org/CorpusID:125037489).
10. Hotelling, H. (1933). Analysis of a complex of statistical variables into principal components.
Journal of Educational Psychology, 24, 417–441, and 498–520.
Hotelling, H (1936). "Relations between two sets of variates". Biometrika. 28 (3/4): 321–377.
doi:10.2307/2333955 (https://doi.org/10.2307%2F2333955). JSTOR 2333955 (https://www.j
stor.org/stable/2333955).
11. Stewart, G. W. (1993). "On the early history of the singular value decomposition" (http://purl.u
mn.edu/1868). SIAM Review. 35 (4): 551–566. doi:10.1137/1035134 (https://doi.org/10.113
7%2F1035134).
12. Jolliffe, I. T. (2002). Principal Component Analysis (http://link.springer.com/10.1007/b98835).
Springer Series in Statistics. New York: Springer-Verlag. doi:10.1007/b98835 (https://doi.org/
10.1007%2Fb98835). ISBN 978-0-387-95442-4.
13. Bengio, Y.; et al. (2013). "Representation Learning: A Review and New Perspectives". IEEE
Transactions on Pattern Analysis and Machine Intelligence. 35 (8): 1798–1828.
arXiv:1206.5538 (https://arxiv.org/abs/1206.5538). doi:10.1109/TPAMI.2013.50 (https://doi.or
g/10.1109%2FTPAMI.2013.50). PMID 23787338 (https://pubmed.ncbi.nlm.nih.gov/2378733
8). S2CID 393948 (https://api.semanticscholar.org/CorpusID:393948).
14. Forkman J., Josse, J., Piepho, H. P. (2019). "Hypothesis tests for principal component
analysis when variables are standardized" (https://doi.org/10.1007%2Fs13253-019-00355-
5). Journal of Agricultural, Biological, and Environmental Statistics. 24 (2): 289–308.
doi:10.1007/s13253-019-00355-5 (https://doi.org/10.1007%2Fs13253-019-00355-5).
15. A. A. Miranda, Y. A. Le Borgne, and G. Bontempi. New Routes from Minimal Approximation
Error to Principal Components (http://www.ulb.ac.be/di/map/yleborgn/pub/NPL_PCA_07.pd
f), Volume 27, Number 3 / June, 2008, Neural Processing Letters, Springer
16. Fukunaga, Keinosuke (1990). Introduction to Statistical Pattern Recognition (https://dl.acm.o
rg/doi/book/10.5555/92131). Elsevier. ISBN 978-0-12-269851-4.
17. Alizadeh, Elaheh; Lyons, Samanthe M; Castle, Jordan M; Prasad, Ashok (2016). "Measuring
systematic changes in invasive cancer cell shape using Zernike moments" (https://pubs.rsc.
org/en/Content/ArticleLanding/2016/IB/C6IB00100A). Integrative Biology. 8 (11): 1183–
1193. doi:10.1039/C6IB00100A (https://doi.org/10.1039%2FC6IB00100A). PMID 27735002
(https://pubmed.ncbi.nlm.nih.gov/27735002).
18. Leznik, M; Tofallis, C. 2005 Estimating Invariant Principal Components Using Diagonal
Regression. (https://uhra.herts.ac.uk/bitstream/handle/2299/715/S56.pdf)
19. Jonathon Shlens, A Tutorial on Principal Component Analysis. (https://arxiv.org/abs/1404.11
00)
20. Soummer, Rémi; Pueyo, Laurent; Larkin, James (2012). "Detection and Characterization of
Exoplanets and Disks Using Projections on Karhunen-Loève Eigenimages". The
Astrophysical Journal Letters. 755 (2): L28. arXiv:1207.4197 (https://arxiv.org/abs/1207.419
7). Bibcode:2012ApJ...755L..28S (https://ui.adsabs.harvard.edu/abs/2012ApJ...755L..28S).
doi:10.1088/2041-8205/755/2/L28 (https://doi.org/10.1088%2F2041-8205%2F755%2F2%2F
L28). S2CID 51088743 (https://api.semanticscholar.org/CorpusID:51088743).
21. Pueyo, Laurent (2016). "Detection and Characterization of Exoplanets using Projections on
Karhunen Loeve Eigenimages: Forward Modeling". The Astrophysical Journal. 824 (2): 117.
arXiv:1604.06097 (https://arxiv.org/abs/1604.06097). Bibcode:2016ApJ...824..117P (https://u
i.adsabs.harvard.edu/abs/2016ApJ...824..117P). doi:10.3847/0004-637X/824/2/117 (https://d
oi.org/10.3847%2F0004-637X%2F824%2F2%2F117). S2CID 118349503 (https://api.seman
ticscholar.org/CorpusID:118349503).
22. Blanton, Michael R.; Roweis, Sam (2007). "K-corrections and filter transformations in the
ultraviolet, optical, and near infrared". The Astronomical Journal. 133 (2): 734–754.
arXiv:astro-ph/0606170 (https://arxiv.org/abs/astro-ph/0606170).
Bibcode:2007AJ....133..734B (https://ui.adsabs.harvard.edu/abs/2007AJ....133..734B).
doi:10.1086/510127 (https://doi.org/10.1086%2F510127). S2CID 18561804 (https://api.sem
anticscholar.org/CorpusID:18561804).
23. Zhu, Guangtun B. (2016-12-19). "Nonnegative Matrix Factorization (NMF) with
Heteroscedastic Uncertainties and Missing data". arXiv:1612.06037 (https://arxiv.org/abs/16
12.06037) [astro-ph.IM (https://arxiv.org/archive/astro-ph.IM)].
24. Ren, Bin; Pueyo, Laurent; Zhu, Guangtun B.; Duchêne, Gaspard (2018). "Non-negative
Matrix Factorization: Robust Extraction of Extended Structures". The Astrophysical Journal.
852 (2): 104. arXiv:1712.10317 (https://arxiv.org/abs/1712.10317).
Bibcode:2018ApJ...852..104R (https://ui.adsabs.harvard.edu/abs/2018ApJ...852..104R).
doi:10.3847/1538-4357/aaa1f2 (https://doi.org/10.3847%2F1538-4357%2Faaa1f2).
S2CID 3966513 (https://api.semanticscholar.org/CorpusID:3966513).
25. "What are the Pros and cons of the PCA?" (https://www.i2tutorials.com/what-are-the-pros-an
d-cons-of-the-pca/). i2tutorials. September 1, 2019. Retrieved June 4, 2021.
26. Abbott, Dean (May 2014). Applied Predictive Analytics. Wiley. ISBN 9781118727966.
27. Jiang, Hong; Eskridge, Kent M. (2000). "Bias in Principal Components Analysis Due to
Correlated Observations" (https://newprairiepress.org/agstatconference/2000/proceedings/1
3/). Conference on Applied Statistics in Agriculture. doi:10.4148/2475-7772.1247 (https://doi.
org/10.4148%2F2475-7772.1247). ISSN 2475-7772 (https://www.worldcat.org/issn/2475-77
72).
28. Linsker, Ralph (March 1988). "Self-organization in a perceptual network". IEEE Computer.
21 (3): 105–117. doi:10.1109/2.36 (https://doi.org/10.1109%2F2.36). S2CID 1527671 (http
s://api.semanticscholar.org/CorpusID:1527671).
29. Deco & Obradovic (1996). An Information-Theoretic Approach to Neural Computing (https://b
ooks.google.com/books?id=z4XTBwAAQBAJ). New York, NY: Springer.
ISBN 9781461240167.
30. Plumbley, Mark (1991). Information theory and unsupervised neural networks.Tech Note
31. Geiger, Bernhard; Kubin, Gernot (January 2013). "Signal Enhancement as Minimization of
Relevant Information Loss". Proc. ITG Conf. On Systems, Communication and Coding.
arXiv:1205.6935 (https://arxiv.org/abs/1205.6935). Bibcode:2012arXiv1205.6935G (https://ui.
adsabs.harvard.edu/abs/2012arXiv1205.6935G).
32. "Engineering Statistics Handbook Section 6.5.5.2" (http://www.itl.nist.gov/div898/handbook/
pmc/section5/pmc552.htm). Retrieved 19 January 2015.
33. A.A. Miranda, Y.-A. Le Borgne, and G. Bontempi. New Routes from Minimal Approximation
Error to Principal Components (http://www.ulb.ac.be/di/map/yleborgn/pub/NPL_PCA_07.pd
f), Volume 27, Number 3 / June, 2008, Neural Processing Letters, Springer
34. Abdi. H. & Williams, L.J. (2010). "Principal component analysis". Wiley Interdisciplinary
Reviews: Computational Statistics. 2 (4): 433–459. arXiv:1108.4372 (https://arxiv.org/abs/11
08.4372). doi:10.1002/wics.101 (https://doi.org/10.1002%2Fwics.101). S2CID 122379222 (h
ttps://api.semanticscholar.org/CorpusID:122379222).
35. "SAS/STAT(R) 9.3 User's Guide" (http://support.sas.com/documentation/cdl/en/statug/6396
2/HTML/default/viewer.htm#statug_princomp_sect001.htm).
36. eig function (http://www.mathworks.com/access/helpdesk/help/techdoc/ref/eig.html#998306)
Matlab documentation
37. "Face Recognition System-PCA based" (https://www.mathworks.com/matlabcentral/fileexch
ange/24634-face-recognition-system-pca-based). www.mathworks.com. 19 June 2023.
38. Eigenvalues function (http://reference.wolfram.com/mathematica/ref/Eigenvalues.html)
Mathematica documentation
39. Roweis, Sam. "EM Algorithms for PCA and SPCA." Advances in Neural Information
Processing Systems. Ed. Michael I. Jordan, Michael J. Kearns, and Sara A. Solla The MIT
Press, 1998.
40. Geladi, Paul; Kowalski, Bruce (1986). "Partial Least Squares Regression:A Tutorial".
Analytica Chimica Acta. 185: 1–17. doi:10.1016/0003-2670(86)80028-9 (https://doi.org/10.10
16%2F0003-2670%2886%2980028-9).
41. Kramer, R. (1998). Chemometric Techniques for Quantitative Analysis (https://books.google.
com/books?id=iBpOzwAOfHYC). New York: CRC Press. ISBN 9780203909805.
42. Andrecut, M. (2009). "Parallel GPU Implementation of Iterative PCA Algorithms". Journal of
Computational Biology. 16 (11): 1593–1599. arXiv:0811.1081 (https://arxiv.org/abs/0811.108
1). doi:10.1089/cmb.2008.0221 (https://doi.org/10.1089%2Fcmb.2008.0221).
PMID 19772385 (https://pubmed.ncbi.nlm.nih.gov/19772385). S2CID 1362603 (https://api.se
manticscholar.org/CorpusID:1362603).
43. Warmuth, M. K.; Kuzmin, D. (2008). "Randomized online PCA algorithms with regret bounds
that are logarithmic in the dimension" (http://www.jmlr.org/papers/volume9/warmuth08a/war
muth08a.pdf) (PDF). Journal of Machine Learning Research. 9: 2287–2320.
44. Kaplan, R.M., & Saccuzzo, D.P. (2010). Psychological Testing: Principles, Applications, and
Issues. (8th ed.). Belmont, CA: Wadsworth, Cengage Learning.
45. Shevky, Eshref; Williams, Marilyn (1949). The Social Areas of Los Angeles: Analysis and
Typology. University of California Press.
46. Flood, J (2000). Sydney divided: factorial ecology revisited. Paper to the APA Conference
2000, Melbourne,November and to the 24th ANZRSAI Conference, Hobart, December 2000.
[1] (https://www.academia.edu/5135339/Sydney_Divided_Factorial_Ecology_Revisited)
47. "Socio-Economic Indexes for Areas" (https://www.abs.gov.au/websitedbs/censushome.nsf/h
ome/seifa). Australian Bureau of Statistics. 2011. Retrieved 2022-05-05.
48. Human Development Reports. "Human Development Index" (https://hdr.undp.org/en/content/
human-development-index-hdi). United Nations Development Programme. Retrieved
2022-05-06.
49. Novembre, John; Stephens, Matthew (2008). "Interpreting principal component analyses of
spatial population genetic variation" (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC398910
8). Nat Genet. 40 (5): 646–49. doi:10.1038/ng.139 (https://doi.org/10.1038%2Fng.139).
PMC 3989108 (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3989108). PMID 18425127
(https://pubmed.ncbi.nlm.nih.gov/18425127).
50. Elhaik, Eran (2022). "Principal Component Analyses (PCA)‑based findings in population
genetic studies are highly biased and must be reevaluated" (https://www.ncbi.nlm.nih.gov/p
mc/articles/PMC9424212). Scientific Reports. 12 (1). 14683.
Bibcode:2022NatSR..1214683E (https://ui.adsabs.harvard.edu/abs/2022NatSR..1214683E).
doi:10.1038/s41598-022-14395-4 (https://doi.org/10.1038%2Fs41598-022-14395-4).
PMC 9424212 (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9424212). PMID 36038559
(https://pubmed.ncbi.nlm.nih.gov/36038559). S2CID 251932226 (https://api.semanticscholar.
org/CorpusID:251932226).
51. DeSarbo, Wayne; Hausmann, Robert; Kukitz, Jeffrey (2007). "Restricted principal
components analysis for marketing research" (https://www.researchgate.net/publication/247
623679). Journal of Marketing in Management. 2: 305–328 – via Researchgate.
52. Dutton, William H; Blank, Grant (2013). Cultures of the Internet: The Internet in Britain (http://
oxis.oii.ox.ac.uk/wp-content/uploads/2014/11/OxIS-2013.pdf) (PDF). Oxford Internet Institute.
p. 6.
53. Flood, Joe (2008). "Multinomial Analysis for Housing Careers Survey" (https://www.academi
a.edu/33218811). Paper to the European Network for Housing Research Conference,
Dublin. Retrieved 6 May 2022.
54. Giorgia Pasini (2017); Principal Component Analysis for Stock Portfolio Management (http
s://ijpam.eu/contents/2017-115-1/12/12.pdf). International Journal of Pure and Applied
Mathematics. Volume 115 No. 1 2017, 153–167
55. Libin Yang. An Application of Principal Component Analysis to Stock Portfolio Management
(https://ir.canterbury.ac.nz/bitstream/handle/10092/10293/thesis.pdf?sequence=1).
Department of Economics and Finance, University of Canterbury, January 2015.
56. Chapin, John; Nicolelis, Miguel (1999). "Principal component analysis of neuronal
ensemble activity reveals multidimensional somatosensory representations". Journal of
Neuroscience Methods. 94 (1): 121–140. doi:10.1016/S0165-0270(99)00130-2 (https://doi.or
g/10.1016%2FS0165-0270%2899%2900130-2). PMID 10638820 (https://pubmed.ncbi.nlm.
nih.gov/10638820). S2CID 17786731 (https://api.semanticscholar.org/CorpusID:17786731).
57. Brenner, N., Bialek, W., & de Ruyter van Steveninck, R.R. (2000).
58. Jirsa, Victor; Friedrich, R; Haken, Herman; Kelso, Scott (1994). "A theoretical model of
phase transitions in the human brain". Biological Cybernetics. 71 (1): 27–35.
doi:10.1007/bf00198909 (https://doi.org/10.1007%2Fbf00198909). PMID 8054384 (https://pu
bmed.ncbi.nlm.nih.gov/8054384). S2CID 5155075 (https://api.semanticscholar.org/CorpusI
D:5155075).
59. Benzécri, J.-P. (1973). L'Analyse des Données. Volume II. L'Analyse des Correspondances.
Paris, France: Dunod.
60. Greenacre, Michael (1983). Theory and Applications of Correspondence Analysis. London:
Academic Press. ISBN 978-0-12-299050-2.
61. Le Roux; Brigitte and Henry Rouanet (2004). Geometric Data Analysis, From
Correspondence Analysis to Structured Data Analysis (https://books.google.com/books?id=a
6bDBUF58XwC). Dordrecht: Kluwer. ISBN 9781402022357.
62. Timothy A. Brown. Confirmatory Factor Analysis for Applied Research Methodology in the
social sciences (https://books.google.com/books?id=JDb3BQAAQBAJ). Guilford Press,
2006
63. Meglen, R.R. (1991). "Examining Large Databases: A Chemometric Approach Using
Principal Component Analysis". Journal of Chemometrics. 5 (3): 163–179.
doi:10.1002/cem.1180050305 (https://doi.org/10.1002%2Fcem.1180050305).
S2CID 120886184 (https://api.semanticscholar.org/CorpusID:120886184).
64. H. Zha; C. Ding; M. Gu; X. He; H.D. Simon (Dec 2001). "Spectral Relaxation for K-means
Clustering" (http://ranger.uta.edu/~chqding/papers/Zha-Kmeans.pdf) (PDF). Neural
Information Processing Systems Vol.14 (NIPS 2001): 1057–1064.
65. Chris Ding; Xiaofeng He (July 2004). "K-means Clustering via Principal Component
Analysis" (http://ranger.uta.edu/~chqding/papers/KmeansPCA1.pdf) (PDF). Proc. Of Int'l
Conf. Machine Learning (ICML 2004): 225–232.
66. Drineas, P.; A. Frieze; R. Kannan; S. Vempala; V. Vinay (2004). "Clustering large graphs via
the singular value decomposition" (http://www.cc.gatech.edu/~vempala/papers/dfkvv.pdf)
(PDF). Machine Learning. 56 (1–3): 9–33. doi:10.1023/b:mach.0000033113.59016.96 (http
s://doi.org/10.1023%2Fb%3Amach.0000033113.59016.96). S2CID 5892850 (https://api.sem
anticscholar.org/CorpusID:5892850). Retrieved 2012-08-02.
67. Cohen, M.; S. Elder; C. Musco; C. Musco; M. Persu (2014). Dimensionality reduction for k-
means clustering and low rank approximation (Appendix B). arXiv:1410.6801 (https://arxiv.or
g/abs/1410.6801). Bibcode:2014arXiv1410.6801C (https://ui.adsabs.harvard.edu/abs/2014a
rXiv1410.6801C).
68. Hui Zou; Trevor Hastie; Robert Tibshirani (2006). "Sparse principal component analysis" (htt
p://www-stat.stanford.edu/~hastie/Papers/spc_jcgs.pdf) (PDF). Journal of Computational
and Graphical Statistics. 15 (2): 262–286. CiteSeerX 10.1.1.62.580 (https://citeseerx.ist.psu.
edu/viewdoc/summary?doi=10.1.1.62.580). doi:10.1198/106186006x113430 (https://doi.org/
10.1198%2F106186006x113430). S2CID 5730904 (https://api.semanticscholar.org/CorpusI
D:5730904).
69. Alexandre d'Aspremont; Laurent El Ghaoui; Michael I. Jordan; Gert R. G. Lanckriet (2007).
"A Direct Formulation for Sparse PCA Using Semidefinite Programming" (http://www.cmap.p
olytechnique.fr/~aspremon/PDF/sparsesvd.pdf) (PDF). SIAM Review. 49 (3): 434–448.
arXiv:cs/0406021 (https://arxiv.org/abs/cs/0406021). doi:10.1137/050645506 (https://doi.org/
10.1137%2F050645506). S2CID 5490061 (https://api.semanticscholar.org/CorpusID:54900
61).
70. Michel Journee; Yurii Nesterov; Peter Richtarik; Rodolphe Sepulchre (2010). "Generalized
Power Method for Sparse Principal Component Analysis" (http://jmlr.csail.mit.edu/papers/vol
ume11/journee10a/journee10a.pdf) (PDF). Journal of Machine Learning Research. 11: 517–
553. arXiv:0811.4724 (https://arxiv.org/abs/0811.4724). Bibcode:2008arXiv0811.4724J (http
s://ui.adsabs.harvard.edu/abs/2008arXiv0811.4724J). CORE Discussion Paper 2008/70.
71. Peter Richtarik; Martin Takac; S. Damla Ahipasaoglu (2012). "Alternating Maximization:
Unifying Framework for 8 Sparse PCA Formulations and Efficient Parallel Codes".
arXiv:1212.4137 (https://arxiv.org/abs/1212.4137) [stat.ML (https://arxiv.org/archive/stat.ML)].
72. Baback Moghaddam; Yair Weiss; Shai Avidan (2005). "Spectral Bounds for Sparse PCA:
Exact and Greedy Algorithms" (http://books.nips.cc/papers/files/nips18/NIPS2005_0643.pdf)
(PDF). Advances in Neural Information Processing Systems. Vol. 18. MIT Press.
73. Yue Guan; Jennifer Dy (2009). "Sparse Probabilistic Principal Component Analysis" (http://j
mlr.csail.mit.edu/proceedings/papers/v5/guan09a/guan09a.pdf) (PDF). Journal of Machine
Learning Research Workshop and Conference Proceedings. 5: 185.
74. Hui Zou; Lingzhou Xue (2018). "A Selective Overview of Sparse Principal Component
Analysis" (https://doi.org/10.1109%2FJPROC.2018.2846588). Proceedings of the IEEE. 106
(8): 1311–1320. doi:10.1109/JPROC.2018.2846588 (https://doi.org/10.1109%2FJPROC.201
8.2846588).
75. A. N. Gorban, A. Y. Zinovyev, "Principal Graphs and Manifolds" (https://arxiv.org/abs/0809.04
90), In: Handbook of Research on Machine Learning Applications and Trends: Algorithms,
Methods and Techniques, Olivas E.S. et al Eds. Information Science Reference, IGI Global:
Hershey, PA, USA, 2009. 28–59.
76. Wang, Y.; Klijn, J. G.; Zhang, Y.; Sieuwerts, A. M.; Look, M. P.; Yang, F.; Talantov, D.;
Timmermans, M.; Meijer-van Gelder, M. E.; Yu, J.; et al. (2005). "Gene expression profiles to
predict distant metastasis of lymph-node-negative primary breast cancer". The Lancet. 365
(9460): 671–679. doi:10.1016/S0140-6736(05)17947-1 (https://doi.org/10.1016%2FS0140-6
736%2805%2917947-1). PMID 15721472 (https://pubmed.ncbi.nlm.nih.gov/15721472).
S2CID 16358549 (https://api.semanticscholar.org/CorpusID:16358549). Data online (https://
www.ihes.fr/~zinovyev/princmanif2006/)
77. Zinovyev, A. "ViDaExpert – Multidimensional Data Visualization Tool" (http://bioinfo-out.curi
e.fr/projects/vidaexpert/). Institut Curie. Paris. (free for non-commercial use)
78. Hastie, T.; Stuetzle, W. (June 1989). "Principal Curves" (https://web.stanford.edu/~hastie/Pap
ers/Principal_Curves.pdf) (PDF). Journal of the American Statistical Association. 84 (406):
502–506. doi:10.1080/01621459.1989.10478797 (https://doi.org/10.1080%2F01621459.198
9.10478797).
79. A.N. Gorban, B. Kegl, D.C. Wunsch, A. Zinovyev (Eds.), Principal Manifolds for Data
Visualisation and Dimension Reduction (https://www.researchgate.net/publication/2716421
70_Principal_Manifolds_for_Data_Visualisation_and_Dimension_Reduction_LNCSE_58),
LNCSE 58, Springer, Berlin – Heidelberg – New York, 2007. ISBN 978-3-540-73749-0
80. Vasilescu, M.A.O.; Terzopoulos, D. (2003). Multilinear Subspace Analysis of Image
Ensembles (http://www.cs.toronto.edu/~maov/tensorfaces/cvpr03.pdf) (PDF). Proceedings of
the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’03). Madison,
WI.
81. Vasilescu, M.A.O.; Terzopoulos, D. (2002). Multilinear Analysis of Image Ensembles:
TensorFaces (http://www.cs.toronto.edu/~maov/tensorfaces/Springer%20ECCV%202002_fil
es/eccv02proceeding_23500447.pdf) (PDF). Lecture Notes in Computer Science 2350;
(Presented at Proc. 7th European Conference on Computer Vision (ECCV'02),
Copenhagen, Denmark). Springer, Berlin, Heidelberg. doi:10.1007/3-540-47969-4_30 (http
s://doi.org/10.1007%2F3-540-47969-4_30). ISBN 978-3-540-43745-1.
82. Vasilescu, M.A.O.; Terzopoulos, D. (June 2005). Multilinear Independent Component
Analysis (http://www.media.mit.edu/~maov/mica/mica05.pdf) (PDF). Proceedings of the
IEEE Conference on Computer Vision and Pattern Recognition (CVPR’05). Vol. 1. San
Diego, CA. pp. 547–553.
83. Kriegel, H. P.; Kröger, P.; Schubert, E.; Zimek, A. (2008). A General Framework for Increasing
the Robustness of PCA-Based Correlation Clustering Algorithms. Scientific and Statistical
Database Management. Lecture Notes in Computer Science. Vol. 5069. pp. 418–435.
CiteSeerX 10.1.1.144.4864 (https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.
4864). doi:10.1007/978-3-540-69497-7_27 (https://doi.org/10.1007%2F978-3-540-69497-7_
27). ISBN 978-3-540-69476-2.
84. Emmanuel J. Candes; Xiaodong Li; Yi Ma; John Wright (2011). "Robust Principal
Component Analysis?". Journal of the ACM. 58 (3): 11. arXiv:0912.3599 (https://arxiv.org/ab
s/0912.3599). doi:10.1145/1970392.1970395 (https://doi.org/10.1145%2F1970392.197039
5). S2CID 7128002 (https://api.semanticscholar.org/CorpusID:7128002).
85. T. Bouwmans; E. Zahzah (2014). "Robust PCA via Principal Component Pursuit: A Review
for a Comparative Evaluation in Video Surveillance". Computer Vision and Image
Understanding. 122: 22–34. doi:10.1016/j.cviu.2013.11.009 (https://doi.org/10.1016%2Fj.cvi
u.2013.11.009).
86. T. Bouwmans; A. Sobral; S. Javed; S. Jung; E. Zahzah (2015). "Decomposition into Low-
rank plus Additive Matrices for Background/Foreground Separation: A Review for a
Comparative Evaluation with a Large-Scale Dataset". Computer Science Review. 23: 1–71.
arXiv:1511.01245 (https://arxiv.org/abs/1511.01245). Bibcode:2015arXiv151101245B (http
s://ui.adsabs.harvard.edu/abs/2015arXiv151101245B). doi:10.1016/j.cosrev.2016.11.001 (htt
ps://doi.org/10.1016%2Fj.cosrev.2016.11.001). S2CID 10420698 (https://api.semanticschola
r.org/CorpusID:10420698).
87. Liao, J. C.; Boscolo, R.; Yang, Y.-L.; Tran, L. M.; Sabatti, C.; Roychowdhury, V. P. (2003).
"Network component analysis: Reconstruction of regulatory signals in biological systems" (h
ttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC307600). Proceedings of the National
Academy of Sciences. 100 (26): 15522–15527. Bibcode:2003PNAS..10015522L (https://ui.a
dsabs.harvard.edu/abs/2003PNAS..10015522L). doi:10.1073/pnas.2136632100 (https://doi.
org/10.1073%2Fpnas.2136632100). PMC 307600 (https://www.ncbi.nlm.nih.gov/pmc/article
s/PMC307600). PMID 14673099 (https://pubmed.ncbi.nlm.nih.gov/14673099).
88. Liao, T.; Jombart, S.; Devillard, F.; Balloux (2010). "Discriminant analysis of principal
components: a new method for the analysis of genetically structured populations" (https://ww
w.ncbi.nlm.nih.gov/pmc/articles/PMC2973851). BMC Genetics. 11: 11:94. doi:10.1186/1471-
2156-11-94 (https://doi.org/10.1186%2F1471-2156-11-94). PMC 2973851 (https://www.ncbi.
nlm.nih.gov/pmc/articles/PMC2973851). PMID 20950446 (https://pubmed.ncbi.nlm.nih.gov/2
0950446).
89. Jewson, S. (2020). "An Alternative to PCA for Estimating Dominant Patterns of Climate
Variability and Extremes, with Application to U.S. and China Seasonal Rainfall" (https://doi.o
rg/10.3390%2Fatmos11040354). Atmosphere. 11 (4): 354. Bibcode:2020Atmos..11..354J (ht
tps://ui.adsabs.harvard.edu/abs/2020Atmos..11..354J). doi:10.3390/atmos11040354 (https://
doi.org/10.3390%2Fatmos11040354).
90. Scher, S.; Jewson, S.; Messori, G. (2021). "Robust Worst-Case Scenarios from Ensemble
Forecasts". Weather and Forecasting. 36 (4): 1357–1373. Bibcode:2021WtFor..36.1357S (ht
tps://ui.adsabs.harvard.edu/abs/2021WtFor..36.1357S). doi:10.1175/WAF-D-20-0219.1 (http
s://doi.org/10.1175%2FWAF-D-20-0219.1). S2CID 236300040 (https://api.semanticscholar.o
rg/CorpusID:236300040).
91. Jewson, S.; Messori, G.; Barbato, G.; Mercogliano, P.; Mysiak, J.; Sassi, M. (2022).
"Developing Representative Impact Scenarios From Climate Projection Ensembles, With
Application to UKCP18 and EURO-CORDEX Precipitation" (http://urn.kb.se/resolve?urn=ur
n:nbn:se:uu:diva-492087). Journal of Advances in Modeling Earth Systems. 15 (1).
doi:10.1029/2022MS003038 (https://doi.org/10.1029%2F2022MS003038).
S2CID 254965361 (https://api.semanticscholar.org/CorpusID:254965361).
92. "Principal Components Analysis" (https://stats.idre.ucla.edu/sas/output/principal-component
s-analysis/). Institute for Digital Research and Education. UCLA. Retrieved 29 May 2018.

Further reading
Jackson, J.E. (1991). A User's Guide to Principal Components (Wiley).
Jolliffe, I. T. (1986). Principal Component Analysis (https://archive.org/details/principalcompo
ne00joll_0/page/487). Springer Series in Statistics. Springer-Verlag. pp. 487 (https://archive.
org/details/principalcompone00joll_0/page/487). CiteSeerX 10.1.1.149.8828 (https://citeseer
x.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.8828). doi:10.1007/b98835 (https://doi.org/1
0.1007%2Fb98835). ISBN 978-0-387-95442-4.
Jolliffe, I. T. (2002). Principal Component Analysis (http://link.springer.com/10.1007/b98835).
Springer Series in Statistics. New York: Springer-Verlag. doi:10.1007/b98835 (https://doi.org/
10.1007%2Fb98835). ISBN 978-0-387-95442-4.
Husson François, Lê Sébastien & Pagès Jérôme (2009). Exploratory Multivariate Analysis
by Example Using R. Chapman & Hall/CRC The R Series, London. 224p. ISBN 978-2-
7535-0938-2
 Pagès Jérôme (2014). Multiple Factor Analysis by Example Using R (https://books.google.c
om/books?id=_RIeBQAAQBAJ&q=%22principal+component+analysis%22). Chapman &
Hall/CRC The R Series London 272 p

External links
University of Copenhagen video by Rasmus Bro (https://www.youtube.com/watch?v=UUxIX
U_Ob6E) on YouTube
Stanford University video by Andrew Ng (https://www.youtube.com/watch?v=ey2PE5xi9-A#t
=2385) on YouTube
A Tutorial on Principal Component Analysis (https://arxiv.org/abs/1404.1100)
A layman's introduction to principal component analysis (https://www.youtube.com/watch?v=
BfTMmoDFXyE) on YouTube (a video of less than 100 seconds.)
StatQuest: StatQuest: Principal Component Analysis (PCA), Step-by-Step (https://www.yout
ube.com/watch?v=FgakZw6K1QQ) on YouTube
See also the list of Software implementations

Retrieved from "https://en.wikipedia.org/w/index.php?title=Principal_component_analysis&oldid=1160912942"