X hits on this document

103 views

0 shares

0 downloads

0 comments

10 / 31

indexes time. This model has a full set of time effects, t, a full set of group effects, g, group/time period covariates, xgt (these are the policy variables), individual-specific covariates, zigt, unobserved group/time effects, vgt, and individual-specific errors, uigt. We are interested in estimating . As in cluster sample cases, can write

yigt gt zigtgt uigt, i 1, . . . , Mgt,

which shows a model at the individual level where both the intercepts and slopes are allowed to differ across all g, tpairs. Then, we think of gt as

  • gt t g xgtvgt.

We can think of (7) as a regression model at the group/time period level.

10

(6 )

(7)

Document info
Document views103
Page views103
Page last viewedSat Dec 10 15:02:35 UTC 2016
Pages31
Paragraphs261
Words3934

Comments