Hello all

I'm doing a difference-in-difference regression with 3 time points (1 pre, and 2 post). My outcome variable is 'performance', which I regress over 'time##treat' (where 'treat' indicates whether the observation is in the treatment or control group). Two variables (ind and prac) have fixed effects over all the time periods.

I'd like to look at the treatment effect separately, in the first and second year of the intervention.

My regression command is

[CODE]
reg performance i.time##i.treat i.ind i.prac
[CODE]

This is my output:

[CODE]
perf | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
Year |
2017 | -1.063955 .6237676 -1.71 0.088 -2.286557 .1586483
2018 | -1.243376 .6294985 -1.98 0.048 -2.477212 -.0095408
|
1.treat | 22.55029 .6320399 35.68 0.000 21.31147 23.78911
|
Year#treat |
2017 1 | -4.784684 .647142 -7.39 0.000 -6.053101 -3.516267
2018 1 | -12.53964 .6528977 -19.21 0.000 -13.81934 -11.25994
|

etc.
etc.
[CODE]


To look at the margins, I do:
[CODE]
margins treat, dydx(time)
[CODE]

My output is:
[CODE]
Expression : Linear prediction, predict()
dy/dx w.r.t. : 2017.Year 2018.Year

------------------------------------------------------------------------------
| Delta-method
| dy/dx Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
2016.Year | (base outcome)
-------------+----------------------------------------------------------------
2017.time |
treat |
0 | . (not estimable)
1 | . (not estimable)
-------------+----------------------------------------------------------------
2018.time |
treat |
0 | . (not estimable)
1 | . (not estimable)
------------------------------------------------------------------------------
Note: dy/dx for factor levels is the discrete change from the base level.
[CODE]

I can't work out why it isn't estimable?

Many thanks for any advice/help.