According to one study by Wang and colleagues (2013), smoking cigars has “a positive and independent” effect on testosterone. What is an independent effect and what is the significance of one?

  • $\begingroup$ What study? Paid for by whom? (Independent of something else that you have not mentioned, presumably.) $\endgroup$ Sep 24, 2023 at 21:17
  • $\begingroup$ Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. $\endgroup$
    – Community Bot
    Sep 24, 2023 at 21:17
  • 2
    $\begingroup$ Now that I can read the abstract I see that the results are that smoking is associated with higher testosterone but more smoking is associated with lower testosterone. That is not consistent with the title that says that smoking has a positive effect on testosterone. It would be consistent with high testosterone levels predisposing men to smoking... $\endgroup$ Sep 25, 2023 at 20:42

1 Answer 1


I have seen this terminology used in medical journals. A quick search yields similar claims made by Svartberg and Jorde (2006) in the International Journal of Andrology, though they discuss cigarette smoking more generally.

Note that cigar smoking, either its general usage (e.g., "ever smoked" versus "never smoked") or the amount of cigars smoked per unit time (e.g., 6 cigars per day/year), is the independent variable in a multiple linear regression equation predicting total or free testosterone levels in men. The authors of the study more than likely adjusted for (controlled for) other variables (e.g., age, medical history, waist circumference, etc.) which might confound this relationship. By adjusting for these factors, the authors then make claims of the independent effect of smoking on testosterone. In statistical applications, the authors are merely stating that this effect is independent of these other confounding variables.

To put this in the context of the aforementioned study, the authors claim the effect of smoking is a positive and independent predictor of testosterone. In other words, smoking is a positive predictor because the linear increase in the number of cigarettes smoked per day/year is associated with an "increase" in testosterone. Put simply, if smoking increases, then testosterone increases. And smoking is also an independent predictor because the effect is now "independent of" or "apart from" the influence of the other factors. Put another way, think of it as the effect of smoking on testosterone after eliminating its correlation with the other variables in the model.

It is worth noting that the "postive" effect of smoking on testosterone is probably short-lived, especially given the plethora of evidence suggesting smoking's long-term, negative effects on overall health.

If the term "statistical control" is new to you, then peruse the answers from here or here.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.