Regression Model with aggregated target data

Question

I would like to fit a regression-like model where I have all the predictor-variables on the individual level, but my target value only on some aggregate-level. So for many groups of individuals, I have the summed up target-value but not the individual target.

I could imagine to change OLS a bit and use a function like this:

But I I wanted to ask, if there are better approaches or if there are libraries (preferably in python) for this kind of OLS.

Thank you in advance!

Ps: I asked a similar question and earned a tumbleweed-badge. So I wasn't sure, whether to post this as a new question or edit the old one...

You guessed correctly: the preferred approach is to edit the original, so that there is no need to post duplicate answers. — whuber, Jul 25 '17 at 13:15

score 0 · Accepted Answer · answered Jul 25 '17 at 11:13

0

Okay, I found out that what I was looking for is called a hierarchical linear models (see wikipedia). Just dropping that here, in case someone else encounters a similar problem.

answered Jul 25 '17 at 11:13

Bobipuegi

753
5
12

Regression Model with aggregated target data

1 Answers1

Linked