In: Statistics and Probability
In a study of eating disorders among adolescent girls, a researcher asked each of the subjects whether they would prefer to gain weight, lose weight, or maintain their present weight. For White girls: 34 want to reduce weight, 66 would like to maintain weight, and 31 want to gain weight; For African- American girls: 23 want to reduce weight, 44 would like to maintain weight, 68 want to gain weight.
You are asked to examine whether race influences adolescent girls' attitude towards their weight, i.e. Perform the following:
a. State the hypotheses (4pts)
b. Set up the contingency table, along with the marginal row and
marginal column (10pts)
c. Use the 6-steps hypothesis test to determine whether race
influences attitude towards weight(26pts)
Chi-square test of independence
Solution:
Part a
Here, we have to use chi square test for independence of two categorical variables.
Null hypothesis: H0: Race does not influence attitude towards weight.
Alternative hypothesis: Ha: Race influences attitude towards weight.
Part b
Calculation tables for test statistic are given as below:
Observed Frequencies |
||||
Column variable |
||||
Row variable |
Reduce weight |
maintain weight |
Gain weight |
Total |
White Girls |
34 |
66 |
31 |
131 |
African American Girls |
23 |
44 |
68 |
135 |
Total |
57 |
110 |
99 |
266 |
Part c
We assume level of significance = α = 0.05
Test statistic formula is given as below:
Chi square = ∑[(O – E)^2/E]
Where, O is observed frequencies and E is expected frequencies.
E = row total * column total / Grand total
We are given
Number of rows = r = 2
Number of columns = c = 3
Degrees of freedom = df = (r – 1)*(c – 1) = 1*2 = 2
α = 0.05
Critical value = 5.991464547
(by using Chi square table or excel)
Calculation tables for test statistic are given as below:
Observed Frequencies |
||||
Column variable |
||||
Row variable |
Reduce weight |
maintain weight |
Gain weight |
Total |
White Girls |
34 |
66 |
31 |
131 |
African American Girls |
23 |
44 |
68 |
135 |
Total |
57 |
110 |
99 |
266 |
Expected Frequencies |
||||
Column variable |
||||
Row variable |
Reduce weight |
maintain weight |
Gain weight |
Total |
White Girls |
28.07142857 |
54.17293233 |
48.7556391 |
131 |
African American Girls |
28.92857143 |
55.82706767 |
50.2443609 |
135 |
Total |
57 |
110 |
99 |
266 |
Calculations |
||
(O - E) |
||
5.928571 |
11.82707 |
-17.7556 |
-5.92857 |
-11.8271 |
17.75564 |
(O - E)^2/E |
||
1.25209 |
2.582093 |
6.46618 |
1.214991 |
2.505586 |
6.274589 |
Chi square = ∑[(O – E)^2/E] = 20.29552888
P-value = 0.0000392
(By using Chi square table or excel)
P-value < α = 0.05
So, we reject the null hypothesis
There is sufficient evidence to conclude that Race influences attitude towards weight.