Assume that you suspect that a dice has been tampered with. You throw the dice 36 times and record the number of times each value on the dice occurs in the table below. Conduct a hypothesis test to see if this dice is considered to be a fair dice (good dice and, therefore, has not been tampered with) at an α=0.01
Table 1.
Observed frequency (O) of the number of dots of die
Number of dots |
Observed frequency |
1 |
9 |
2 |
5 |
3 |
7 |
4 |
4 |
5 |
3 |
6 |
8 |
2. A large big-box retailer is accused of sex discrimination in promotion decisions. The personnel files show there were 3300 male employees among them 960 were promoted in the past 6 months. During the same time, there were 2700 female employees, and among them, 700 were promoted. Do the data substantiate the claim that this large big-box retailer discriminated against female workers in promotion decisions? Conduct a hypothesis test to evaluate if there is a relationship between promotion decisions and employee’s sex at an α=0.05.
Table 2.
Observed frequency (O) between promotion decision and employee’s sex
Promoted |
Not promoted |
Row total |
|
Male |
960 |
2340 |
3300 |
Female |
700 |
2000 |
2700 |
Column total |
1660 |
4340 |
6000 |
(1)
H0: Null Hypothesis: This dice is considered to be a fair dice (good dice and, therefore, has not been tampered with) (Claim)
HA: Alternative Hypothesis: This dice is considered to be not a fair dice (bad dice and, therefore, has been tampered with)
Test Statistic () is got asfollows:
Observed (O) | Expected (E) | (O - E)2/E |
9 | 6 | 1.500 |
5 | 6 | 0.167 |
7 | 6 | 0.167 |
4 | 6 | 0.667 |
3 | 6 | 1.500 |
8 | 6 | 0.667 |
Total = = | 4.668 |
Degrees of Fredom =6 - 1 = 5
From Table, critical value of = 15.086
Since calculated value of = 4.668 is less than critical value of = 15.086, the difference is not significant. Fail to reject the null hypothesis.
Conclusion:
The data support the claim that this dice is considered to be a
fair dice (good dice and, therefore, has not been tampered
with).
(2)
H0: Null Hypothesis: There is no relationship between promotion
decisions and employee’s sex
HA: Alternative Hypothesis: There is a relationship between promotion decisions and employee’s sex (Claim)
Expected Frequencies are got as follows:
Promoted | Not promoted | Row total | |
Male | 1660 X3300/6000 = 913.00 | 4340 X3300/6000 = 2387.00 | 3300 |
Female | 1660 X2700/6000 = 747.00 | 4340 X2700/6000 = 1953.00 | 2700 |
Column total |
1660 |
4340 | 6000 |
Test Statistc () is got as follows:
Observed (O) | Expected (E) | (O - E)2/E |
960 | 913 | 2.42 |
230 | 2387 | 0.93 |
700 | 747 | 2.96 |
2000 | 1953 | 1.13 |
Total = = | 7.43 |
df = (r - 1) X(c - 1) = (2 - 1) X(2 - 1) = 1
By Technology, p - value = 0.0064
Since p - value = 0.0064 is less than α=0.05, the differenc is significant. Reject null hypothesis.
Conclusion:
The data support the claim that there is a relationship between
promotion decisions and employee’s sex
Assume that you suspect that a dice has been tampered with. You throw the dice 36...