Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.

good day, I have a question related to the time fixed effects when using Swamy Random coefficient model, as you may know in the fixed and random effect context, we use a set of time dummies to estimate the time fixed effects, and i would like if we can use the same approch whith swamy???

Any hint would be highly appreciated.

Ama

share|improve this question

1 Answer

I think you use Stata, given your other post about Panel data and selection models issue. Did you look at the following paper, From the help desk: Swamy’s random-coefficients model from the Stata Journal (2003 3(3))? It seems that the command xtrchh2 (available through findit xtrchh in Stata command line) includes an option about time, but I'm afraid it only allow to estimate the panel-specific coefficients. Looking around, I only found this article, Estimation and testing of fixed-effect panel-data systems (SJ 2005 5(2)), but it doesn't seem to address your question. So maybe it is better to use the xtreg command directly. If you have more than one random coefficient, then it may be better to gllamm.

Otherwise, I would suggest trying the plm R package (it has a lot of dependencies, but it mainly relies on the nlme and survival packages). The effect parameter that is passed to plm() seems to return individual, time or both (for balanced design) kind of effects; there's also a function names plstest(). I'm not a specialist of econometrics, I only used it for clinical trials in the past, but quoting the online help, it seems you will be able to get fixed effects for your time covariate (expressed as deviations from the overall mean or as deviations from the first value of the index):

library(plm)
data("Grunfeld", package = "plm")
gi <- plm(inv ~ value + capital, data = Grunfeld,
          model = "within", effect = "twoways")
summary(gi)
fixef(gi,effect = "time")

where the data looks like (or see the plot below to get a rough idea):

    firm year   inv  value capital
  1    1 1935 317.6 3078.5     2.8
  2    1 1936 391.8 4661.7    52.6
  3    1 1937 410.6 5387.1   156.9
...
198   10 1952  6.00  74.42    9.93
199   10 1953  6.53  63.51   11.68
200   10 1954  5.12  58.12   14.33

For more information, check the accompagnying vignette or this paper, Panel Data Econometrics in R: The plm Package, published in the JSS (2008 27(2)).

Grunfeld

share|improve this answer
Thank you very much Chl :) – Ama Sep 14 '10 at 18:24

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.