Rapid responses are electronic comments to the editor. They enable our users to debate issues raised in articles published on bmj.com. A rapid response is first posted online. If you need the URL (web address) of an individual response, simply click on the response headline and copy the URL from the browser window. A proportion of responses will, after editing, be published online and in the print journal as letters, which are indexed in PubMed. Rapid responses are not indexed in PubMed and they are not journal articles. The BMJ reserves the right to remove responses which are being wilfully misrepresented as published articles.
In response to Parker, question b) is both correct and meaningful.
As outlined in the answers, the 95% confidence interval for the relative
risk does not include unity; therefore the null hypothesis would be
rejected in favour of the alternative at the 5% level of significance.
The statistical hypotheses are constructed before data collection. A
statement with regards magnitude and direction of risk, including that
proposed by Parker, is made after statistical hypothesis testing has been
performed. As such it would represent an inference based on observation
of the data collected. Therefore, it would be incorrect to state that the
“reported increased risk of fatal coronary heart disease was statistically
significant at the 5% level of significance”.
It is not essential to describe the reference group in question b).
Through the stem question b) makes explicit reference to the risk
described in the scenario, namely the relative risk.
Competing interests:
None declared
Competing interests:
No competing interests
01 October 2009
Philip M Sedgwick
senior lecturer in medical statistics
St Georges, University of London, London SW17 0RE
Admittedly pedantic, but there is a word missing in b. For answer b
to have any meaning the word “increased” should be added so that the
answer reads “The reported INCREASED risk of fatal coronary heart disease
is statistically significant at the 5% level” , and to be totally correct
the answer should include a description of in which group compared to
which other group, just as answer “a” does.
Author's reply
In response to Parker, question b) is both correct and meaningful.
As outlined in the answers, the 95% confidence interval for the relative
risk does not include unity; therefore the null hypothesis would be
rejected in favour of the alternative at the 5% level of significance.
The statistical hypotheses are constructed before data collection. A
statement with regards magnitude and direction of risk, including that
proposed by Parker, is made after statistical hypothesis testing has been
performed. As such it would represent an inference based on observation
of the data collected. Therefore, it would be incorrect to state that the
“reported increased risk of fatal coronary heart disease was statistically
significant at the 5% level of significance”.
It is not essential to describe the reference group in question b).
Through the stem question b) makes explicit reference to the risk
described in the scenario, namely the relative risk.
Competing interests:
None declared
Competing interests: No competing interests