Key result
Anxiety levels predicting the development of hypertension in middle-aged men may be a chance association, with a 39% likelihood of a type I error given the stated P value of.04.
Why the study?
Does anxiety or tension predict the development of hypertension?
Does anxiety or tension predict the development of hypertension?
Answers are grounded in this paper and cite their sources.
This letter questions the validity of a study linking anxiety to hypertension, highlighting the high probability of type I error due to multiple subgroup analyses.
To the Editor. —The notion that tension or anxiety is a predictor of hypertension has been assumed intuitively and has been studied by many over decades. Yet convincing evidence of such a relationship has not appeared. The recent article by Dr Markovitz and colleagues¹purportedly demonstrates that anxiety levels predict development of hypertension in middle-aged men. However, the findings are open to question on several grounds. First, there was no evidence of a relationship between tension and development of hypertension in women or in older men. Thus, in three of four groups tested, no relationship was seen. Further, the odds of a type I error are substantial. Given the number of subgroups, the number of predictors tested, and the statedPvalue of.04, there is a 39% likelihood of a chance association between some predictor and hypertension. For the .02 value reported with multivariate analysis, there is a 20% likelihood
No takes yet. Share an insight, caveat, or question.
Samuel J. Mann (1994) conducted a letter in Hypertension. Anxiety levels was evaluated on Development of hypertension. Anxiety levels predicting the development of hypertension in middle-aged men may be a chance association, with a 39% likelihood of a type I error given the stated P value of.04.
Synapse has enriched 10 related papers. Consider them for comparative context: