In: Statistics and Probability
3. The following table presents data on the presence and absence of
respiratory distress syndrome (RDS) in two groups of infants. Group
1 consisted of 42 infants whose fetal membrances ruptured 24 hours
or less before delivery, while group 2 was composed of 22 infants
whose membrances ruptured more than 24 hours before delivery. Test
the null hypothesis that the two populations are homogeneous. Let
α=.05. Incidence of respiratory distress syndrome (RDS) in two
groups of infants RDS Group Yes No Total 1 27 15 42 2 7 15 22 Total
34 30 64
Null Hypothesis:Ho: two populations are homogeneous
Alternate Hypothesis:Ho: two populations are not homogeneous
degree of freedom(df) =(rows-1)*(columns-1)= | 1 | |
for 1 df and 0.05 level , critical value χ2= | 3.841 | |
Decision rule : reject Ho if value of test statistic X2>3.841 |
Applying chi square test of Homogeneity: |
Expected | Ei=row total*column total/grand total | yes | No | Total |
Group 1 | 22.31 | 19.69 | 42 | |
Group 2 | 11.69 | 10.31 | 22 | |
total | 34 | 30 | 64 | |
chi square χ2 | =(Oi-Ei)2/Ei | yes | No | Total |
Group 1 | 0.9848 | 1.1161 | 2.1008 | |
Group 2 | 1.8800 | 2.1307 | 4.0107 | |
total | 2.8648 | 3.2468 | 6.1115 | |
test statistic X2 = | 6.1115 |
since test statistic falls in rejection region we reject null hypothesis | ||
we have sufficient evidence to conclude that two populations are not homogeneous |