Scribd
Upload
327 views8 pages

Chi-Square Test For Association

The Chi-Square test for association determines if a relationship exists between categorical variables. It compares observed and expected frequencies to calculate a Chi-Square value. If the value is less than the critical value from the Chi-Square distribution table, we fail to reject the null hypothesis that the variables are independent. The example tests if college grade depends on high school exam results, finding the Chi-Square value of 1.55 is less than the critical value of 13.28 so grade and exam results are independent.

Uploaded by

PingotMaganga
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
327 views8 pages

Chi-Square Test For Association

The Chi-Square test for association determines if a relationship exists between categorical variables. It compares observed and expected frequencies to calculate a Chi-Square value. If the value is less than the critical value from the Chi-Square distribution table, we fail to reject the null hypothesis that the variables are independent. The example tests if college grade depends on high school exam results, finding the Chi-Square value of 1.55 is less than the critical value of 13.28 so grade and exam results are independent.

Uploaded by

PingotMaganga
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

CHI-SQUARE TEST

FOR ASSOCIATION
CHI SQUARE TEST FOR ASSOCIATION
The Chi-Square test for independence, also called
Pearsons Chi-Square test or the Chi-Square test of association
is used to discover if there is a relationship between
categorical or nominal
Steps to follow in dealing with Chi-Square test
1. State the Hypothesis
2. Set the level of significance (alpha)
3. Compute the value of the statistical test to the
tabular value
4. Compare the value of the statistical test to the
tabular value
5. Interpret and discuss the result
Example: Does college academic grade depend
on the high school NCAE results for the following 200
students? Use 0.01 level of significance.

Academic NCAE Result


Grade Low Average High
Above 85 13 25 21
75-85 18 31 38
Below 75 14 20 20
Solution:
Step 1: Formulate the Hypothesis
Ho: College academic grade does NOT
depend on the high school NCAE
Ha: The college academic grade depends
on the high school NCAE results
Step 2: Set the level of significance = 0.01
Step 3: Compute the value of the statistical
test.
Calculate 2 using the formula below
continuation..
(0 )2
2 =

where: =observes frequency
=expected frequency
()()
=

a. The first steps to do is obtain the marginal totals of the rows an


d of the columns as indicated below

Academic NCAE Results


Grade Total
Low Average High
Above 85 13 25 21 59
75-85 18 31 38 87
Below 75 14 20 20 54
Total 45 76 79 200
continuation
Compute the expected frequency by multiplying th
e column total and row total divided by the grand total.
76 87
45 59 5 = = 33.06
1 = = 13.28 200
200
76 54
6 = = 20.52
45 87 200
2 = = 19.58
200 79 59
7 = = 23.31
200
45 54
3 = = 12.15 79 87
200 8 = = 34.37
200

76 59 79 54
4 = = 22.42 9 = = 21.33
200
200
c. Calculation of the Chi-Square
Observed Expected

Frequency Frequency

(fo) (fe)
13 13.28 -0.28 0.08 0.01
18 19.58 -1.58 2.50 0.13
14 12.15 1.85 3.42 0.28
25 22.42 2.58 6.66 0.30
31 33.06 -2.06 4.24 0.13
20 20.52 -0.52 0.27 0.01
21 23.21 -2.31 5.34 0.23
38 34.37 3.63 13.18 0.38
20 21.33 -1.33 1.77 0.08
= .
Continuation
Step 4: Compare the value Step 5: Interpret and
of the statistical test to the discuss the result
tabular value. Since the statistical
Statistical value=1.55 value for chi-square is 1.55
Tabular value is less than 13.28 which is
df=( 1)( 1) the tabular value at 0.01
level of probability using 4
where: c=# of columns degrees of freedom.
r=# of rows Therefore,we do NOT reject
df=(3-1)(3-1) the null hypothesis. Hence,
df=4locate college grade does NOT
(Appendix D) depend on the high school
2 = 13.28 NCAE results.

You might also like