Appleton, D. R., French, J. M., and Vanderpump, M. P. J. (1996). "Ignoring a Covariate: An Example of Simpson’s Paradox," The American Statistician, 50, No. 4, 340-341.
Tunbridge, W. M. G., Evered, D. C., Hall, R., Appleton, D. R., Brewis, M., Clark, F., Grimley, E. J., Young, E., Bird, T., and Smith, P. A. (1977). "The Spectrum of Thyroid Disease in a Community: The Whickham Survey," Clinical Endocrinology, 7, 481-493.
A survey concerned with thyroid and heart disease was conducted in 1972-74 in a district near Newcastle, United Kingdom by Tunbridge et al (1977). A follow-up study of the same subjects was conducted twenty years later by Vanderpump et al (1996). Here we explore data from the survey on the smoking habits of 1314 women who were classified as being a current smoker or as never having smoked at the time of the original survey. Of interest is whether or not they survived until the second survey.
The following tables summarize the results of the experiment:
Table 1: Relationship between smoking habits and 20-year survival in 1314 women.
|
Survival Status |
Smoking Status |
|
|
Yes |
No |
|
|
Dead |
139 |
230 |
|
Alive |
443 |
502 |
|
Survival Status |
Age Group (Years) |
|||||
|
18-44 |
44-64 |
above 64 |
||||
|
Smoker |
Non-smoker |
Smoker |
Non-smoker |
Smoker |
Non-smoker |
|
|
Dead |
19 |
13 |
78 |
52 |
42 |
165 |
|
Alive |
269 |
327 |
167 |
147 |
7 |
28 |
Q1a) Use the information in Table 1 to calculate the following proportions. Of the women who died during the 20-year period, what proportion were smokers? Of the women who were still alive after the 20 years, what proportion were smokers? [Results]
b) Calculate the following proportions using the data in Table 2. Of those women who were 18-44 years old at the time of the original survey and who died before the follow-up survey, what proportion were smokers? What were the similar proportions for the 44-64 and above-64 age groups? [Results]
Q2a) From the data in Table 1, compute the overall percentage of smokers who died and the percentage of non-smokers who died. Do the data from this table suggest that smoking or non-smoking women live longer? Comment. [Results]
b) Using the information in Table 2, compute the percentage of smokers and non-smokers in each of the three age groups who died. Do the data from this table suggest that smoking or non-smoking women live longer? Comment. [Results]
c) Compare your results from Part a and Part b. How can you explain any apparent contradictions? [Results]
Initiated by: Sumithra Ramaswamy
Completed by: Sumithra Ramaswamy
Picture created by: Petra Graham