In: Statistics and Probability
In a telephone survey of 800 registered voters, the data are cross classified both by gender of respondent and by respondent’s opinion on an environmental bond issue.
Bond issue
For Against
Men 450 150
Women 160 40
We want to know whether there is good evidence that one’s gender influences whether a person is for or against the bond issue. Use the chi-square test to answer this question. State the hypotheses, discuss conditions, perform calculations, and report your conclusions. (Please Type)
Solution:
Given: We have to test whether there is good evidence that one’s gender influences whether a person is for or against the bond issue.
That is we have to test if Gender and Bond issue are independent or not.
Thus we use following steps:
Step 1) State H0 and H1:
H0: Gender and Bond issue are independent
Vs
H1: Gender and Bond issue are not independent.
Step 2) Find Chi-square test statistic:
Where
Oij = Observed frequencies for ith row and jth column.
Eij = Expected frequencies for ith row and jth column.
Where
Thus we need to make following table:
Bond Issue | |||
Gender | For | Against | Total |
Men | 450 | 150 | R1 =600 |
Women | 160 | 40 | R2 =200 |
Total | C1 = 610 | C2 =190 | N = 800 |
Thus we need to make following table:
Oij | Eij | Oij^2/Eij |
450 | 457.5 | 442.623 |
150 | 142.5 | 157.8947 |
160 | 152.5 | 167.8689 |
40 | 47.5 | 33.68421 |
N = 800 |
Thus
Step 3) Find Chi-square critical value:
df = (R-1)X(C-1) =(2-1)X(2-1) = 1X1 = 1
df = 1
level of significance = 0.05
Chi-square critical value = 3.841
Step 4) Decision Rule:
Reject H0, if Chi-square test statistic value > Chi-square
critical value = 3.841, otherwise we fail to reject H0.
Since Chi-square test statistic value = < Chi-square critical value = 3.841,we fail to reject H0.
Step 5) Conclusion:
Gender and Bond issue are independent
That is there is no evidence that one’s gender influences whether a person is for or against the bond issue.