For illustrative purposes, consider the example given on p. 473 of Jann (2008). However, instead of the difference and coefficients noted, let's assume the difference and coefficients were the following:

Difference: 0.20


  • educ: 0.15
  • exp_ten: 0.15
  • isco: -0.15
  • Total: 0.15

How would you properly describe these results? It seems odd to say that educ and exp_ten each individually accounted for 100% of the explained part of the outcome differential, but that would seem to be consistent with Jann's interpretation when no considerable negative coefficient was present:

Differences in education and combined differences in experience and tenure each account for about half the explained part of the outcome differential, whereas occupational segregation based on the nine major groups of the International Standard Classification of Occupations (ISCO-88) does not seem to matter much.

Here's the screenshot of the Stata output from Jann's example on p. 473: Jann 2008 Stata output (p. 473)


Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.