CHAPTER 3 o If the data have exactly two modes, the data are bimodal.

o If the data have more than two modes, the data are multimodal.
DESCRIPTIVE STATISTICS: NUMERICAL MEASURES

Numerical Measures
 Weighted Mean
 If the measures are computed for data from a sample, they are called sample statistics.
o In some instances the mean is computed by giving each observation a weight that
 If the measures are computed for data from a population, they are called population
reflects its relative importance.
parameters.
o The choice of weights depends on the application.
 A sample statistic is referred to as the point estimator of the corresponding population
o The weights might be the number of credit hours earned for each grade, as in GPA.
parameter.
o In other weighted mean computations, quantities such as pounds, dollars, or
Measures of Location volume are frequently used.
 Mean ∑ w i xi
o The mean provides a measure of central location. o x́=
o The mean of a data set is the average of all the data values. ∑ wi
o The sample mean x́ is the point estimator of the population mean µ. where: xi = value of observation i
wi = weight for observation I
o Sample Mean: x́=
∑ xi Numerator: sum of the weighted data values
n Denominator: sum of the weights
 Geometric Mean
o Population Mean: μ=
∑ xi o The geometric mean is calculated by finding the nth root of the product of n values.
N o It is often used in analyzing growth rates in financial data (where using the
where: Sxi = sum of the values of the N observations arithmetic mean will provide misleading results).
N = number of observations in the population o It should be applied anytime you want to determine the mean rate of change over
 Median several successive periods (be it years, quarters, weeks, . . .).
o The median of a data set is the value in the middle when the data items are o Other common applications include: changes in populations of species, crop yields,
arranged in ascending order. pollution levels, and birth and death rates.
o Whenever a data set has extreme values, median is the preferred measure of central o x́ g =√n ( x 1 ) ( x 2 ) …( x n)
location.
o The median is the measure of location most often reported for annual income and = [(x1)(x2)…(xn)]1/n
property value data.  Percentiles
o A few extremely large incomes or property values can inflate the mean. o A percentile provides information about how the data are spread over the interval
o For an odd number of observations, arrange it in ascending order and the middle from the smallest value to the largest value.
o Admission test scores for colleges and universities are frequently reported in terms
value is the median.
o For an even number of observations, arrange it in ascending order and the average of percentiles.
o The pth percentile of a data set is a value such that at least p percent of the items
of the middle two values is the median.
take on this value or less and at least (100 - p) percent of the items take on this
 Trimmed Mean
value or more.
o Another measure sometimes used when extreme values are present
o Arrange the data in ascending order.
o It is obtained by deleting a percentage of the smallest and largest values from a data
o Compute Lp, the location of the pth percentile.
set and then computing the mean of the remaining values.
Lp = (p/100)(n + 1)
o For example, the 5% trimmed mean is obtained by removing the smallest 5% and
 Quartiles
the largest 5% of the data values and then computing the mean of the remaining
o Quartiles are specific percentiles.
values.
o First Quartile = 25th Percentile
 Mode
o The mode of a data set is the value that occurs with greatest frequency. o Second Quartile = 50th Percentile = Median
o The greatest frequency can occur at two or more different values. o Third Quartile = 75th Percentile
 σ
Measures of Variability
 It is often desirable to consider measures of variability (dispersion), as well as measures
o Population CoV:
[ μ
x 100 ] %

of location. Measures of Distribution Shape, Relative Location, and Detecting Outliers

 For example, in choosing supplier A or supplier B we might consider not only the  Distribution Shape
average delivery time for each, but also the variability in delivery time for each. o Skewness
 Range  An important measure of the shape of a distribution is called skewness.
o The range of a data set is the difference between the largest and smallest data  The formula for the skewness of sample data is
3
values. n x i−x́
o Range = Largest value – Smallest value
o It is the simplest measure of variability.

 Skewness =
(n−1)(n−2)
∑ s [ ]
Skewness can be easily computed using statistical software. (Chapter 2)
o It is very sensitive to the smallest and largest data values.
 Interquartile Range  z-Scores
o The interquartile range of a data set is the difference between the third quartile and o The z-score is often called the standardized value.
the first quartile. o It denotes the number of standard deviations a data value xi is from the mean.
o It is the range for the middle 50% of the data. xi −x́
o It overcomes the sensitivity to extreme data values.
o z i=
s
 Variance o Excel’s STANDARDIZE function can be used to compute the z-score.
o The variance is a measure of variability that utilizes all the data. o An observation’s z-score is a measure of the relative location of the observation in
o It is based on the difference between the value of each observation (xi) and the a data set.
mean ( x́ for a sample,  for a population). o A data value less than the sample mean will have a z-score less than zero.
o The variance is useful in comparing the variability of two or more variables. o A data value greater than the sample mean will have a z-score greater than zero.
o The variance is the average of the squared differences between each data value and o A data value equal to the sample mean will have a z-score of zero.
the mean.  Chebyshev’s Theorem

o Sample Variance: s2=

∑ ( x i−x́ ) 2 o At least (1 - 1/z2) of the items in any data set will be within z standard deviations of
the mean, where z is any value greater than 1.
n−1 o Chebyshev’s theorem requires z > 1, but z need not be an integer.

o Population Variance: σ 2=
∑ ( xi −μ ) 2 o At least 75% of the data values must be within z = 2 standard deviations of the
mean.
N o At least 89% of the data values must be within z = 3 standard deviations of the
 Standard Deviation
mean.
o The standard deviation of a data set is the positive square root of the variance.
o At least 94% of the data values must be within z = 4 standard deviations of the
o It is measured in the same units as the data, making it more easily interpreted than
mean.
the variance.
 Empirical Rule
o Sample SD: s = √ s2 o When the data are believed to approximate a bell-shaped distribution:
o Population SD:  = √   2  The empirical rule can be used to determine the percentage of data values that
must be within a specified number of standard deviations of the mean.
 Coefficient of Variation  The empirical rule is based on the normal distribution, which is covered in
o The coefficient of variation indicates how large the standard deviation is in relation Chapter 6.
to the mean. o For data having a bell-shaped distribution:
s
o Sample CoV:
[ x́
x 100 ] %



Approximately 68% of the data values will be within +/- 1 standard deviation
of its mean.
Approximately 95% of the data values will be within +/- 2 standard deviations
of its mean.
  Almost all of the data values will be within +/- 3 standard deviations of its s xy
mean. o Sample CC: r xy=
 Detecting Outliers sx s y
o An outlier is an unusually small or unusually large value in a data set. σ xy
o A data value with a z-score less than -3 or greater than +3 might be considered an o Population CC: ρ xy=
σxσ y
outlier.
o It might be: o The coefficient can take on values between -1 and +1.
 an incorrectly recorded data value o Values near -1 indicate a strong negative linear relationship.
 a data value that was incorrectly included in the data set o Values near +1 indicate a strong positive linear relationship.
 a correctly recorded unusual data value that belongs in the data set o The closer the correlation is to zero, the weaker the relationship.

Five-Number Summaries and Box Plots Data Dashboards: Adding Numerical Measures to Improve Effectiveness
 Summary statistics and easy-to-draw graphs can be used to quickly summarize large  Data dashboards are not limited to graphical displays.
quantities of data.  The addition of numerical measures, such as the mean and standard deviation of KPIs,
 Five-Number Summary to a data dashboard is often critical.
o Smallest Value  Dashboards are often interactive.
o First Quartile  Drilling down refers to functionality in interactive dashboards that allows the user to
o Median access information and analyses at increasingly detailed level.
o Third Quartile
o Largest Value
 Box Plot
o A box plot is a graphical summary of data that is based on a five-number summary.
o A key to the development of a box plot is the computation of the median and the
quartiles Q1 and Q3.
o Box plots provide another way to identify outliers.
o Limits are located (not drawn) using the interquartile range (IQR).
o Data outside these limits are considered outliers
o The locations of each outlier is shown with the symbol

Measures of Association between Two Variables

 Often a manager or decision maker is interested in the relationship between two
variables.
 Covariance
o The covariance is a measure of the linear association between two variables.
o Positive values indicate a positive relationship.
o Negative values indicate a negative relationship.

o Sample Covariance: s xy=

∑ ( x i ¿−x́)( y i − ý) ¿
n−1
o Population Covariance: σ xy =
∑ ( x i ¿−μ x )( y i−μ y ) ¿
N
 Correlation Coefficient
o Correlation is a measure of linear association and not necessarily causation.
o Just because two variables are highly correlated, it does not mean that one variable
is the cause of the other.