I can't speak to how often this happens, but one of the reasons for inconsistent findings in certain fields (social science, epidemiology, etc.) is that one researcher will control for a variable, meaning in effect that any influence the variable might have on the outcome is removed from consideration, while another researcher treats the same variable as a predictor that might have an independent or interactive effect on the same outcome. This can lead to different conclusions even though, in theory, both researchers' raw data could be telling the same story.
The end of this article is interesting. The math matters, but so does the motive. How we control a variable determines what truth we let through.
Thank you - very well-put!
I can't speak to how often this happens, but one of the reasons for inconsistent findings in certain fields (social science, epidemiology, etc.) is that one researcher will control for a variable, meaning in effect that any influence the variable might have on the outcome is removed from consideration, while another researcher treats the same variable as a predictor that might have an independent or interactive effect on the same outcome. This can lead to different conclusions even though, in theory, both researchers' raw data could be telling the same story.
Insightful, I appreciate your brekdown of this data, though I always wonder about generalising findings from specific age cohorts especialy.
Thank you. That's a very good point. The study focused on older adults - mostly late 50s to mid 60s.
thank you, i'm keeping the curtains shut from now on!!