3

Is it correct to find that an explanatory variable was found to be statistically significant with the chi-square test but insignificant with the logistic regression analysis model?

kjetil b halvorsen
  • 63,378
  • 26
  • 142
  • 467
Etta
  • 31
  • 1
  • 3
    Does your logistic regression model only have one explanatory variable in it? –  Nov 19 '15 at 19:04
  • 1
    No it has several explanatory variables,about 10 of them. – Etta Nov 19 '15 at 19:19
  • 1
    It sounds as if you are running the risk of double dipping. You can't use associations with $Y$ to decide which variables to test for associations with $Y$. Besides that, adjusted and unadjusted (for covariates) analyses naturally differ. – Frank Harrell Nov 19 '15 at 19:27
  • Does this mean that the results might be faulty or the approach wrong? – Etta Nov 19 '15 at 19:45
  • 2
    Correct. Look at some of the rules of thumb for the required sample size as a function of the number of _candidate_ predictors, and pre-specify a full model and use it as the basis for your conclusions. – Frank Harrell Nov 19 '15 at 21:23

1 Answers1

1

Cleared up and partially answered in comments:

This logistic regression model has several explanatory variables, about 10 of them. – Etta

It sounds as if you are running the risk of double dipping. You can't use associations with Y to decide which variables to test for associations with Y. Besides that, adjusted and unadjusted (for covariates) analyses naturally differ. – Frank Harrell

Does this mean that the results might be faulty or the approach wrong? – Etta

Correct. Look at some of the rules of thumb for the required sample size as a function of the number of candidate predictors, and pre-specify a full model and use it as the basis for your conclusions. – Frank Harrell

See also Variable selection for predictive modeling really needed in 2016?

kjetil b halvorsen
  • 63,378
  • 26
  • 142
  • 467