Professional Documents
Culture Documents
FOR
MANAGEMENT –II
Measures of Association,
Goodness-of-Fit Tests and
Contingency Tables
Measures of Association
Measures of association provide a means of summarizing the size
of the association between two variables.
There are two main classes of measure of association: symmetric
and asymmetric.
𝑃1 + 𝑃2 + ⋯ + 𝑃𝐾 = 1
If the null hypothesis is true and the sample size is large enough
that the expected values are at least 5, then the random variable
associated with
𝐾
𝑂𝑖 − 𝐸𝑖 2
𝜒2 =
𝐸𝑖
𝑖=1
is known as a chi-square random variable, and has, to a good
approximation, a chi-square distribution with (K - 1) degrees of
freedom.
Goodness-of-Fit Test: SPECIFIED
PROBABILITIES
Goodness-of-Fit Test: SPECIFIED
PROBABILITIES
The null hypothesis is that the probabilities are the same for the
three categories. The test of this hypothesis is based on the
following:
i1 Ei
. . . except that the number of degrees of freedom for
the chi-square random variable is
Degrees of Freedom (K m 1)
Where K is the number of categories
Contingency Tables
Contingency Tables
Used to classify sample observations according to a
pair of attributes
Also called a cross-classification or cross-tabulation
table
Assume r categories for attribute A and c categories
for attribute B
Then there are (r x c) possible cross-classifications
r x c Contingency Table
Characteristic B
H0 : No associatio n exists
between the two attributes in the population
The Chi-Square Test Statistic
r c (Oij Eij )2
2
with d.f. (r 1)(c 1)
i1 j1 Eij
where:
Oij = observed frequency in cell (i, j)
Eij = expected frequency in cell (i, j)
r = number of rows
c = number of columns
The appropriate test is a chi-square test with (r-1)(c-1) degrees of
freedom
Test for Association
(continued)
Let Ri and Cj be the row and column totals
The expected number of observations in cell row i and
column j, given that H0 is true, is
R iC j
Eij
n
A test of association at a significance level is based
on the chi-square distribution and the following decision
rule
r c (Oij Eij )2
Reject H0 if χ 2 χ(r2 1)c1),α
i1 j1 Eij
Relationship between Undergraduate Degree
and MBA Major
One way to solve the problem is to consider that there are two
variables: undergraduate degree and MBA major. Both are
nominal. The values of the undergraduate degree are BA, BEng,
BBA, and other. The values of MBA major are accounting, finance,
and marketing. The problem objective is to analyze the relationship
between the two variables. Specifically, we want to know whether
one variable is related to the other.
The null hypothesis will specify that there is no relationship
between the two variables. We state this in the following way:
𝐻0 : The two variables are independent
The alternative hypothesis specifies one variable affects the other,
expressed as
𝐻1 : The two variables are dependent
Relationship between Undergraduate Degree
and MBA Major
Assuming that the null hypothesis is true (the two variables are
independent), we can compute the estimated joint probabilities. To
produce the expected values, we multiply the estimated joint
probabilities by the sample size, 𝑛 = 152.
Relationship between Undergraduate Degree
and MBA Major
2 = 𝜒2
𝜒 2 > 𝜒𝑣,𝛼 6,0.05 = 12.6
Because 𝜒 2 = 14.70, we reject the null hypothesis and conclude
that there is evidence of a relationship between undergraduate
degree and MBA major.
The p-value of the test statistic is P(𝜒 2 > 14.70)= 0.0227.
Unfortunately, we cannot determine the p-value manually.