Scribd
Upload
413 views

Nonlinear Regression

Some nonlinear models can be transformed into linear regression models through techniques like using polynomial terms or transforming variables, like taking the log of y. While some nonlinear models can be handled this way, other highly nonlinear models require more complex calculations to estimate coefficients. Nonlinear regression techniques allow fitting nonlinear models to data through transformations or more advanced calculations.

Uploaded by

aarthy
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
413 views

Nonlinear Regression

Some nonlinear models can be transformed into linear regression models through techniques like using polynomial terms or transforming variables, like taking the log of y. While some nonlinear models can be handled this way, other highly nonlinear models require more complex calculations to estimate coefficients. Nonlinear regression techniques allow fitting nonlinear models to data through transformations or more advanced calculations.

Uploaded by

aarthy
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 5

Nonlinear Regression

Some

nonlinear models can be modeled by a


polynomial function
A polynomial regression model can be transformed
into linear regression model. For example,
y = w0 + w 1 x + w2 x2 + w 3 x3
convertible to linear with new variables: x 2 = x2, x3= x3
y = w0 + w 1 x + w2 x2 + w 3 x3
Other

functions, such as power function, can also be


transformed to linear model
Some models are intractable nonlinear (e.g., sum of
exponential terms)
possible to obtain least square estimates through
extensive calculation on more complex formulae
April 27, 2016

Data Mining: Concepts and Techniques

Non linear Regression

Actual Data
y=ex
x
0.49
1.632316
0.93
2.534509
1.41
1.75
2.98

4.095955
5.754603
19.68782

y=ex
log y = log e x
log y = x.loge e
log y = x.(1)
log y = x
Y = x ( Where Y is new variable . Y =
log(y))

Non linear Regression


x
0.49
0.93
1.41
1.75
2.98

y
1.632316
2.534509
4.095955
5.754603
19.68782

Y= log(y)
0.212804
0.403894
0.612355
0.760015
1.294198

Y= log(y)

0.49

0.212804

0.93

0.403894

1.41

0.612355

1.75

0.760015

2.98

1.294198

Linear Regression

Linear regression: involves a response variable y and a single


predictor variable x
y = w0 + w1 x

where w0 (y-intercept) and w1 (slope) are regression coefficients

Method of least squares: estimates the best-fitting straight line


| D|

w
1

(x
i 1

x )( yi y )

| D|

(x
i 1

x )2

w yw x
0
1

Multiple linear regression: involves more than one predictor


variable
Training data is of the form (X1, y1), (X2, y2),, (X|D|, y|D|)
Ex. For 2-D data, we may have: y = w 0 + w1 x1+ w2 x2
Solvable by extension of least square method
Many nonlinear functions can be transformed into the above

April 27, 2016

Data Mining: Concepts and Techniques

Other Regression-Based
Models
Generalized linear model:

Foundation on which linear regression can be applied to


modeling categorical response variables
Variance of y is a function of the mean value of y, not a
constant

Logistic regression: models the prob. of some event occurring


as a linear function of a set of predictor variables
Poisson regression: models the data that exhibit a Poisson
distribution

Log-linear models: (for categorical data)


Approximate discrete multidimensional prob. distributions
Also useful for data compression and smoothing

Regression trees and model trees


Trees to predict continuous values rather than class labels

April 27, 2016

Data Mining: Concepts and Techniques

You might also like