Blood cadmium level in the elderly population: perspective for the cause of inconsistent results

Han et al1 investigated the association between blood cadmium levels (B-Cd) and depression in 395 people, aged 60 years or older. Survey was conducted three times, and positive association between B-Cd and depression was only observed in the first visit. The authors used the Korean version of the Short Form Generic Depression Scale test (SGDS-K) for screening depression and logistic regression model was used for the analysis. I present my speculation on their statistical inconsistency.

First, the authors well recognised the relatively small number of participants and depression cases, especially in the second and the third visit data. Even in the first visit data, the number of depression cases was only 50. In their tables 3–5, wide ranges of 95% CIs were observed. There is a limitation in the total number of events for logistic regression analysis.2 Peduzzi et al3 simulated the effect of...

from #AlexandrosSfakianakis via Alexandros G.Sfakianakis on Inoreader http://ift.tt/1VXR6Ah
via IFTTT