THE CHI-SQUARE TEST OF INDEPENDENCE

(ONE SAMPLE, TWO CRITERION VARIABLE)

The one-sample test of independence is different from the test of homogeneity. The sample used in
this test consists of members randomly drawn from the same population. This test is used to look into whether
measures taken on two criterion variables are either independent or associated with one in a given population
using such variables as level of education and income, performance in class and IQ etc. The calculation of this
test is similar to the test of goodness-of-fit and the test of homogeneity. The formula is:
( O−E )2
X2 = ∑
E
Where:
2
X = Chi-Square test
O = observed frequency
E = expected frequency
∑ = summation

Example 1. Ninety individuals, male and female, were given a test in psychomotor skills and their scores
were classified into high and low. Using the x 2 - test of independence at .05 level of
significance, the table is shown as follows:

Score
Sex High Low Total
O E O E

Male 18 28 46

Female 32 12 44

Total 50 40 90

Solving Stepwise Method:

Problem: Is there a significant relationship between sex and scores in psychomotor skill?

I. Hypotheses:

H 0: There is no significant relationship between sex and scores in psychomotor skill.

H a: There is a significant relationship between sex and scores in psychomotor skill.

II. Level of Significance:

α = .05
df = (c-1) (r-1)
= (2-1) (2-1)
=(1) (1)
=1
 2
X .05 = 3.841 tabular value
III. Statistics:

2
X – test of independence

Computation

Score
Sex High Low Total
O E O E

Male 18 (25.56) 28 (20.44) 46

Female 32 (24.44) 12 (19.56) 44

Total 50 40 90

For expected values: Multiply the column total to the row total and divide the product by the grand total.
50 x 46 40 x 46
= 25.56 = 20.44
90 90
50 x 44 40 x 44
90
= 24.44 90
= 19.56
( O−E )2
X =∑
2
E
( 18−25.56 )2 ( 32−24.44 )2 ( 28−20.44 )2 ( 12−19.56 )2
= + + +
25.56 24.44 20.44 19.56
= 2.236 + 2.338 + 2.796 + 2.922
X 2 = 10.3921= 10.39
Decision Rule: If the X 2 computed value is greater than the X 2 tabular value, reject H 0.
IV & V -Decision & Conclusion: The X 2 computed value of10.39 is greater than the X 2 tabular value
of 3.841 at .05 level of significance with one degree of freedom. This leads to the confirmation of the
research hypothesis which means that a significant relationship exists between sex and score in
psychomotor skill. It implies that the female’s high scores are more in psychomotor skills than their
male counterpart.

2. Determine if gender is related to work performance as indicated by the data below:

WORK PERFORMANCE
GENDER
Low Average High
Male 35 46 53
Female 30 57 48
Test the hypothesis using the 0.05 level.
Problem: Is gender related to work performance?
I. Hypotheses:

H 0: Gender is not related to work performance.

 Ha: Gender is related to work performance.

II. Level of Significance:

α = .05
df = (c-1) (r-1)
= (3-1) (2-1)
=(2) (1)
=2
2
X .05 = 5.99 tabular value
III. Test Statistic:

2
X – test of independence

Computation
WORK PERFORMANCE
GENDER
Low Average High Total
Male 35 46 53 134
Female 30 57 48 135
Total 65 103 101 269

For expected values: Multiply the column total to the row total and divide the product by the grand total.
65 x 134 103 x 135
35: = 32.38 57: = 51.69
269 269
65 x 135 101 x 134
30: 269 = 32.62 53: 269
= 50.31
103 x 134 101 x 135
46: 269
=51.31 48: 269
= 50.69

( O−E )2
X =∑
2
E
( 35−32.38 )2 ( 30−32.62 )2 ( 46−51.31 )2 ( 57−51.69 )2 ( 53−50.31 )2 ( 48−50.69 )2
= + + + + +
32.38 32.62 51.31 51.69 50.31 50.69
= .2120 + .2104 +.5495+.5455 + .1438 +.1428
X = 1.80 = 1.8
2

or
O E O-E (O-E)2 (O-E)2/E
35 32.38 2.62 6.8644 0.2120
30 32.62 -2.62 6.8644 0.2104
46 51.31 -5.31 28.1961 0.5495
57 51.69 5.31 28.1961 0.5455
53 50.31 2.69 7.2361 0.1438
48 50.69 -2.69 7.2361 0.1428
1.80
Decision Rule: If the X 2 computed value is greater than the X 2 tabular value, reject H 0.
IV. Decision: Fail to reject Ho since the X 2 computed value of 1.80 is lesser than the X 2 tabular value
of 5.99 at .05 level of significance with 2 degree of freedom.
V -Conclusion: Gender is not related to work performance.

CHI-SQUARE TABULAR VALUE

Relationship between IQ level and Educational Attainment

Post
  Secondary Tertiary Total
Graduate
Low IQ level 58 25 12 95
Average 46 48 26 120
High 20 62 41 123
Total 124 135 79 338