Control variable netincome

[Annelotte van Nouhuijs]

Dear all,

In my thesis I am researching whether people who are recently divorced have a smaller chance of owning luxury assets (second house, boat, car). A control variable I want to include is netincome (historgram below). I am wondering if I should create categories within net income?

Many thanks in advance!
Annelotte

[Carlo Lazzaro]

Annelotte:
in general, categorizing a continuous predictor is not advisable (see: http://citeseerx.ist.psu.edu/viewdoc...=rep1&type=pdf).
However, it is also wise to skim through the literature in your research field and see what others did in the past when presented with the same research goal.

[Marcos Almeida]

This seems to me a typical histogram of income, I mean, with positive skewness.

Categorizing is an option (usually, not the best one) but, depending on the statistical model, GLM for example, this pattern of distribution shall not be a problem.

P.S.: crossed with Carlo's wise advice.

.