After you ran enough people through your study, you were able to report that you
ID: 3242820 • Letter: A
Question
After you ran enough people through your study, you were able to report that your results were statistically significant and that you would begin seeking funding. Give and defend two reasons why you are still likely to have an unconvincing case. Title: Duration of sleep contributes to Next-Day Pain Report in the General Population Author: R. Edwards, et al. Source: Pain 137 (2008) 202-207. The authors of this study interviewed participants from the general population. These participants recorded both the number of hours they slept during the previous sleep period and the frequency of their pain symptoms. Pain was recorded on a five-point scale. A summary of the resulting data is presented in the table below: A comparison of patients in the 0-3 hour category to those in the 11+ hour category is not statistically significant, despite a difference in means of 0.42. However, a comparison of patients in the 5-hour category to those in the 8-hour category is statistically significant, even though the difference in means is only 0.19. Give a solid reason as to why you think this is so, What practical implication does this have for our understanding of testing results?Explanation / Answer
Answer:
Comparing to the first comparison, second comparison sample size is very large. For large sample sizes, small difference is enough to make significant results. Therefore for large sample size, small difference is enough to make significant result. Sample size plays important role in making significant results.