In: Statistics and Probability
In the book Business Research Methods (5th ed.), Donald R. Cooper and C. William Emory discuss studying the relationship between on-the-job accidents and smoking. Cooper and Emory describe the study as follows:
Suppose a manager implementing a smoke-free workplace policy is interested in whether smoking affects worker accidents. Since the company has complete reports of on-the-job accidents, she draws a sample of names of workers who were involved in accidents during the last year. A similar sample from among workers who had no reported accidents in the last year is drawn. She interviews members of both groups to determine if they are smokers or not.
The sample results are given in the following table.
On-the-Job Accident | ||||||
Smoker | Yes | No | Row Total | |||
Heavy | 10 | 5 | 15 | |||
Moderate | 7 | 10 | 17 | |||
Nonsmoker | 17 | 17 | 34 | |||
Column total | 34 | 32 | 66 | |||
Expected counts are below observed counts | ||||||
Accident | No Accident | Total | ||||
Heavy | 10 | 5 | 15 | |||
7.73 | 7.27 | |||||
Moderate | 7 | 10 | 17 | |||
8.76 | 8.24 | |||||
Nonsmoker | 17 | 17 | 34 | |||
17.52 | 16.48 | |||||
Total | 34 | 32 | 66 | |||
Chi-Sq = 2.14, DF = 2, P-Value = 0.343 | ||||||
(a) For each row and column total in the above
table, find the corresponding row/column percentage. (Round
your answers to 2 decimal places.)
Row 1 | % |
Row 2 | % |
Row 3 | % |
Column 1 | % |
Column 2 | % |
(b) For each cell in the above table, find the
corresponding cell, row, and column percentages. (Round
your answers to 2 decimal places.)
Accident | No Accident | ||
Heavy | Cell= % | Cell= % | |
Row= % | Row= % | ||
Column= % | Column= % | ||
Moderate | Cell= % | Cell= % | |
Row= % | Row= % | ||
Column= % | Column= % | ||
Nonsmoker | Cell= % | Cell= % | |
Row= % | Row= % | ||
Column= % | Column= % | ||
(c) Use the MINITAB output in the above to test
the hypothesis that the incidence of on-the-job accidents is
independent of smoking habits. Set ? = .01.
(Click to select)RejectDo not reject
H0.
(d) Is there a difference in on-the-job
accident occurrences between smokers and nonsmokers?
Conclude there is (Click to select)no differencedifference between smokers and nonsmokers.
a)
Row 1 | 15/66=0.227273 | 22.7% |
Row 2 | 17/66=0.257576 | 25.8% |
Row 3 | 34/66=515152 | 51.5% |
Column 1 | 34/66=515152 | 51.5% |
Column 2 | 32/66=0.484848 | 48.5% |
b) Cell %: (Observation value/ Total) *100
Row %: (Observation value/ Row sum)*100
Column %: (Observation value/ Column sum) *100
Accident | No accident | ||
Heavy | Cell | 15.2% | 7.6% |
Row | 66.7% | 33.3% | |
Column | 29.4% | 15.6% | |
Moderate | Cell | 10.6% | 15.2% |
Row | 41.2% | 58.8% | |
Column | 20.6% | 31.3% | |
Nonsmoker | Cell | 25.8% | 25.8% |
Row | 50.0% | 50.0% | |
Column | 50.0% | 53.1% |
c)
P-value: 0.343 S, at 0.01 significant level Reject H0.
d) The test statistic is significant and rejects H0.
Conclude there is no difference between smokers and nonsmokers.