Chi Square Test
Chi Square Test
Chi Square Test
Chi square is applicable in analyzing data in descriptive research. The chisquare test determines the significant difference between the observed and expected
frequencies of independent variables. The symbol of chi-square is known as the
dancing x2. Chi-square considers the practical and theoretical importance in a set of
observations.
When the researcher is interested to determine if 2 or more categories show
significant difference, then the chi-square test is used. It compares a set of observed
and expected frequencies from independent samples.
DEFINITION OF CHI-SQUARE
Chi-square (x2) may be defined as the sum of the difference of observed and
expected frequencies divided by the expected frequency. The definition is denoted by
this formula (Ferguson, 1976):
x2 = (O E)
E
where:
x2 = Chi-square
O = Observed frequency
E = Expected frequency
Chi-square is a descriptive measure of the discrepancy values between observed
frequency and expected frequency. The larger the discrepancies between O and E, the
larger the chi-square value obtained. If observed and expected frequencies show no
discrepancies at all, the chi-square value is zero.
Bear in mind that the chi-square value is always a positive number.
USES OF CHI-SQUARE
1. chi-square is used in descriptive research if the researcher wants to determine
the significant difference between the obser4ved and expected or theoretical
frequencies from independent variables.
2. It is used to test the goodness of fit where a theoretical distribution is fitted to
some data, i.e., the fitting of normal curve.
3. It is used to test the hypothesis that the variance of a normal population is equal
to a given value.
4. It is also used for the construction of confidence interval for variance.
Table 1
Computation of Chi-square in One-Way Classification of the Responses of
Women and Mean if Divorce be Applied in the Philippines
Response
O
E
OE
W M Both W
M W
M
(O E)
W M
(O E)2
E
W
M
Both
Yes
15
24
12
12 -3
-3
0.75
0.75
1.50
No
12
14
7 -5
-5
25
25
3.57
3.57
7.14
9 13
22
11
11 -2
-2
0.36
0.36
0.72
4.68
4.68
9.36**
Undecide
d
Total
30 30 60
30
*Significant at .01 level
30
df = (r 1) (C 1)
= (3 1) (2 1)
= (2) (1)
df = 2
df.012(2) = 9.210
Bear in mind that if a computation of expected frequency is correct, 0 E equals
zero because the sum of observed frequency is equal to the sum of expected
frequency.
7. Interpretation. The computed x2 value obtained is 9.36, which is significant at .
01 level. To be significant at .01 level having two degrees of freedom, the
computed x2 is equal to or greater than the tabular value of 9.210. since the x2
computed value is greater than 9,210, the results showed significant difference in
the responses of women and men to the question: can divorce be applied in the
Philippines?. This means that responses of women and men really differ from
each other, thus, the null hypothesis (H0) is rejected.
INDEPENDENCE IN A 2 X 2 TABLE
Impendence in a 2 x 2 table chi-square or fourfold table involves two variables to
test if these variables are independent from each other. These variables are usually
nominal. The values are arranged in the form of a 2 x 2 which is composed of two rows
( R ) and two columns ( C ). Table 2 presents the 2 x 2 table with two rows and two
columns.
Table 2
Computation of Chi-Square in a 2 x 2 Table with Two Rows and Two Columns
Job Performance
Satisfactory
25
45
Unsatisfactory
15
55
40
100
Table 3
Computation of Chi-square in a 2 x 2 Table between Job Performance and
Teachers Board Examination
Job Performance
Satisfactory
25
45
Unsatisfactory
15
55
40
100
OE
(O E) 2
(O E)2
E
Total
20
27
-7
49
1.8148
40
33
49
1.4848
25
18
49
2.7222
15
22
-7
49
2.2273
100
100
8.2491 or 8.25
df = (R 1 ) (C 1)
= (2 1) (2 1) = 1
df.01(1) = 6.64**
A
C
A+C
B
D
A + B Satisfactory20
C + D Unsatisfactory
25
40
55
60
40
B+D
x2 =
Pass
45
N(AD BC)2
(A + B) (C + D)(A + C)(B + D)
55
= 100(20 x 15 40 x 25)2 .
60 x 40 x 45 x 55
= 100(300 1000)2 .
59400000
x2 = 8.25 Significant at .01 level
Another example of a 2 x 2 table is one that determines if the NCEE (National College
Entrance Examination) rating of college students is independent with and without
kindergarten education. The research question is Is there a significant difference in the
achievement of college students who passed and those who failed in the NCEE with
and without kindergarten education? To answer this question, consider the following
steps:
60
135
Total
0.64
OE
(O E) 2
27.7778
-2.2222
4.9382
0.17778
20
22.2222
-2.2222
4.9382
0.22222
45
47.2222
2.2222
4.9382
0.10457
40
37.7778
2.2222
4.9382
0.13072
135
135.0000
30
0.0000
df = (R 1) (C 1)
= (2 1) (2 1)
= (1) (1)
0.63529 or
df = 1
df .01(1) = 6.635**
Career Success
Very Successful
Successful
Unsuccessful
Total
Status
Permanent Temporary Casual
60
35
15
55
45
20
30
40
50
145
120
85
Total
110
120
120
350
Permanent
35
45
40
145
Temporary
15
110
20
120
50
120
120
85
Casual
Successful
350
= 45.572
350
85 x 120
20 =
= 29.143
350
120 x 110
35 =
145 x 120
= 37.7143
30 =
350
350
85 x 110
15 =
120 x 120
= 26.714
40 =
350
= 41.143
350
145 x 120
55 =
= 49.714
85 x 120
= 49.714
50 =
350
= 29.143
350
120 x 120
45 =
= 41.143
350
Table 5
5 x 5 Table or Twenty-Five-Fold Table between Economic Status
and Educational Qualifications of Rural Folks
Educational
Qualifications
Belo
w
Lowe
r
Class
Economic Status
Lowe Above
r
Middl Middl Uppe
Class
e
e
r
Class Class Class Class
Total
15
16
29
70
College
12
18
35
47
13
125
High School
31
39
30
19
11
130
Elementary
48
42
27
13
135
None
Total
50
144
60
166
20
127
8
103
2
60
140
600
Table 5 data determine if the economic status of 600 rural folks is independent
from educational qualifications. The specific research question, Is there a significant
difference between the economic status and educational qualifications or rural folks?
To answer this question, consider the following steps:
1. Null hypothesis. There is no significant difference between the economic status
and educational qualifications of rural folks. Economic status (ES) is independent
from education qualifications (EQ). thus, economic status and educational
qualifications are equal. Ho: ES = EQ
2. Statistical test. Chi-square (2) test
3. Significance level. Let = .01
4. Sampling distribution. N = 600 with df = 6, df = (R-1) (C-1)
5. Rejection region. The null hypothesis (Ho) will be rejected if chi-square ( 2)
value obtained is equal to or greater than the tabular value with df 16 at .01
percent level of significance.
6. Computation. Table 6 shows the present computation of chi-square in a 5 x 5
table between economic status and educational qualifications of rural folks.
Consider the following computation:
3 = 144 x 70 = 16.8
600
7 = 166 x 70 = 19.37
600
15 = 127 x 70 = 14.82
600
16 = 103 x 70 = 12.02
600
29 = 60 x 70 = 7.0
600
5 = 60 x 135 = 13.5
600
2 = 60 x 140 = 14.0
600
Table 6
Computation of Chi-Square (x2) in a 5 x 5 Table between
Economic Status and Educational Qualifications of Rural Folks
(O E)2
E
OE
(O E)2
3
7
15
16
29
12
18
35
47
13
31
39
30
19
11
48
42
27
13
5
50
16.80
19.37
14.82
12.02
7.00
30.00
34.58
26.46
21.46
12.50
31.20
35.97
27.52
22.32
13.00
32.40
37.35
28.57
23.17
13.50
33.60
-13.80
-12.37
0.18
3.98
22.00
-18.00
-16.58
8.54
25.54
0.50
-0.20
3.03
2.48
-3.32
-2.00
15.60
4.65
-1.57
-10.17
-8.50
16.40
190.4400
153.0169
0.0324
15.8404
484.0000
324.0000
274.8964
72.9316
652.2916
0.2500
0.0400
9.1809
6.1504
11.0224
4.0000
243.3600
21.6225
2.4649
103.4289
72.2500
268.9600
11.3367
7.8997
0.0022
1.3178
69.1428
10.8000
7.9496
2.7563
30.3957
0.0200
0.0013
0.2552
0.2235
0.4938
0.3077
7.5111
0.5789
0.0863
4.4639
5.3518
8.0048
60
20
8
2
38.73
29.63
24.03
14.00
21.27
-9.63
-16.03
-12.00
452.4129
92.7369
256.9609
144.0000
11.6812
3.1298
10.6933
10.2857
Total 600
600.00
204.6891 or 204.69**
df = (R 1) (C 1)
= (5 1) (5 1)
= 4 (4)
df = 16
df .01(16) = 32.0**
7. Interpretation. The computed chi-square (2) value is 204.96. This value is
significant at 1 percent level of probability because it is higher than the tabular
value of 32.0 with df 16. This means that economic status depends on the
educational qualifications of rural folks. Therefore, the null hypothesis (H o) is
rejected.