Question

One researcher was disturbed by the tendency for female employees to overtime more than male employees. For this he took a sample of 12 female employees and 10 male employees. The table below is data on how many hours were spent overtime a week. Using a non-parametric test and a 95% confidence level, can it be concluded that female employees are overtime more than male employees?

Female (hour)	Male (hour)
13	10
17	6
14	8
12	10
10	12
9	13
15	11
16	9
11	5
8	11
9
7

Answer 1

We can use the non-parametric test-Mann-Whitney-Wilcoxon U- test here.

H0: There is no significan difference between the average over time by females and males

H1: Average over time done by female>average over time done by male.

The combined ordered pair is written below

	5	6	7	8	8	8	9	9	10	10	10	11	11	11	12	12	13	13	14	15	16	17
	m	m	f	f	m	m	m	f	f	m	m	m	m	f	f	m	m	f	f	f	f	f
R1(female)			3	5				7.5	10					13	15.5			17.5	19	20	21	22
R2(male)	1	2			5	5	7.5			10	10	13	13			15.5	17.5

R1= Sum of rank of female=3+5+7.5+10+13+15.5+17.5+19+20+21+22=153.5

R2= Sum of rank of male = 1+2+5+5+7.5+10+10+13+13+15.5+17.5 = 99.5

U1 = = 44.5

U2= = 75.5

Test statistic U = 44.5

From the table of U, the crcal value is 34

Here U>34(Critical value) Hence do not reject H0.

There is no enough evidence to conclude that female employees are overtime more than male employees.