Take the 2-minute tour ×
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

In my logistic regression model, I have one independent variable that has a B value of 0, p = 0.006 and exp(B) = 1. Goodness-of-fit measures indicate that the model is acceptably "good".

Intuitively, I would imagine a significant variable to have a non-zero coefficient and some effect. Statistically though, I am not sure.

So, I am not sure if the outcome on this variable is an acceptable outcome. If yes, what is the explanation? If this type of outcome [B=0, p=0.006, exp(B)=1] is not acceptable, what could it be symptomatic of -- what is the problem?

share|improve this question
3  
p-value for what? Which null hypothesis? –  onestop Jul 13 '11 at 9:12

1 Answer 1

Are you sure the B has not been rounded too much? If the predictor is measured in, say, $, you may need 5 or 6 decimal places on B and its odds ratio in order to see the effect.

share|improve this answer
    
Yep, it seems a problem with the scale of the variable. Try to use antoher scale (divide by 1000, use log etc.) –  Manoel Galdino Jul 13 '11 at 12:32
    
Hahaha, unbelievable! you are right - about the decimal places. Thanks! –  bjkdy Jul 14 '11 at 3:24

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

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