When other significant variables were added in final model, one of the variables turned out non significant in logistic regression. Should I do any additional analysis for this or should I do separate logistic regression by splitting the data (according to the site)?
Hello Sri,
The most likely answer is that the information carried by the variable is redundant with information carried by other variables in the full logistic model (e.g., collinearity).
In such cases, a candidate IV can show relationship with the DV when evaluated by itself, but not when included with other IVs in a more complete model.
Good luck with your work.
Did you create a pairs plot first?
Plot the data on the upper/lower side of the diagonal and plot the correlations on the other half. Here you may simply see what David Morse just said.
An example for R is found e.g. here: https://statisticsglobe.com/r-pairs-plot-example/ (see the fifth pairs plot, that can also be created using native R code without ggplot)
This can be plotted in most other languages pretty easy as well.
The natural function in R is pairs (x, y).
Jan
assess how much the significance levels differences in chi square and logistic regression. you can try with splitting the data to prove it is not significant. looking to the practical situation of the relationship of the variables you can interpret as it is.
- Badges
- Science topic
- Similar topics
- Citations