# Thread: Large odds ratio in binary logistic regression/big scale difference of variables

1. ## Large odds ratio in binary logistic regression/big scale difference of variables

I'd like to ask for some help with a binary logistic regression. In SPSS I am building a binary logistic regression with 4 independent continuous variables(Sample size - 85). However, with one of the variables (Bicaudatus_index) I get a huge odds radio:

I think that I know where the problem is: the scale of this variable is very different than other variables:

As this variable is a ratio of two measurements, I try to multiply the variable 100 times and get a new variable, which odds ratio in the same regression seem to be within normal range.

However I don't know if it is appropriate to do that. If I multiply the variable not 100, but e.g. 150 times, I get odds ratios that are different from the ones that I get with 100.

Therefore, I want to ask what should I do in this case, is this method appropriate or do I need to interpret the results differently because of multiplication, or do I need a whole new approach. Help would be greatly appreciated

2. ## Re: Large odds ratio in binary logistic regression/big scale difference of variables

hi,
this is quite natural and you are on the good track. The odds ratio tells us how the odds change if we change the X by one unit. Imagine we look at odds of heart attack vs. weight -the odds will definitely be greater if we measure the weight in 50 kg units as when we measure in grams (i.e the odds of a heart attack by a weight increase of 50kg vs. a weight increase of 1 g)
Regards

3. ## The Following User Says Thank You to rogojel For This Useful Post:

gianmarco (10-02-2016)

4. ## Re: Large odds ratio in binary logistic regression/big scale difference of variables

Originally Posted by rogojel
hi,
this is quite natural and you are on the good track. The odds ratio tells us how the odds change if we change the X by one unit. Imagine we look at odds of heart attack vs. weight -the odds will definitely be greater if we measure the weight in 50 kg units as when we measure in grams (i.e the odds of a heart attack by a weight increase of 50kg vs. a weight increase of 1 g)
Regards
Thank you for your answer . So as I understand, it is appropriate to multiply the varible e.i. 100 times to get a valid odds ratio, this way one just has to interpret it differently?

5. ## Re: Large odds ratio in binary logistic regression/big scale difference of variables

I would phrase it differently - it is ok to re-scale the variable so that the change of 1 unit is of practical interest. E.g. neither a weight gain of 1 gram nor of 50kg is practically interesting, but maybe the effect of a change ofb500g or 1 kg would be.

regards

6. ## The Following User Says Thank You to rogojel For This Useful Post:

gianmarco (10-02-2016)

 Tweet