Binning data in Stata 9.1

[ks1012]

Hi,
Could anyone tell me how to bin data in Stata 9? I want to construct a table for Fisher's exact test and can't seem to get the coding right.
Thanks!

[bukharin]

If you want to test associations why would you bin rather than using a test that uses all of your data?

[ks1012]

Wanting to test if I see a higher exposure to a pathogen at higher environmental levels of exposure. Binning seemed like a good way to do that.(?)

[bukharin]

Not really because you are throwing away the granularity of your data. How have you measured the exposures?

If both variables are continuous you could use some kind of correlation analysis (Pearson's or Spearman's depending on the shape of the relationship), or a regression model if you wanted to adjust for other factors. If one of the variables is categorical and the other one is continuous then there are various methods depending on which one is which, and whether the data are (more or less) normally distributed.