Collinearity

[nitu pun]

Hi,

Please see the attached. Stata has omitted two of my variables because of "collinearity". What can I do please?

Many thanks,


N

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and samp[e data using dataex.

When dummies are dropped for colinearity, it suggests your understanding and modelling is in error. For example, you might lose an England dummy from colinearity if all your usable data (i.e., that which has usable values for all the variables) is from England. You need to explore your data more carefully to see why it is doing this. I

[nitu pun]

Thanks Phil Bromiley

[Eric de Souza]

Consider the variable year which takes on a limited number of values, one for each year. Then i.year will create as many dummy variables as you have year values in the variable year. It will then drop one of them because otherwise you will have perfect collinearity.

[nitu pun]

Eric de Souza Hi Eric thanks for your response. I have included the i.year but it still omits my ownrent and country variable.

[Eric de Souza]

I did not say that you should introduce the variable i.year. I took it as an example since you did not provide enough information to use your variables.
Provide us with the result of the command:
sum
followed by a list of all the variables entering the poisson command