1

I am estimating a variable coefficient model with time effect via function pvcm from package plm. I am using a within estimator. Unfortunately, I have difficulties with using the summary command. It does not provide me usual output with standard errors, t-statistics, and p-values. Instead of the usual output, I see the information about quantile values of a particular variable. Could you help me with that? I would appreciate all the hints and suggestions.

summary(model1.pvcm)

Oneway (time) effect No-pooling model

Call:
pvcm(formula = dependent_variable ~ var1 + var2 + ......,
     data = estimation_balanced, 
     effect = c("time"), model = "within", index = c("BID", "YEAR"))

Balanced Panel: n = 693, T = 4, N = 2772

Residuals:
       Min.     1st Qu.      Median     3rd Qu.        Max. 
-2.14103956 -0.01104022  0.00000000  0.01279167  2.75017609 

Coefficients:
  (Intercept)          var1
Min.   :0.000000   Min.   :-0.027970
1st Qu.:0.009435   1st Qu.:-0.019728 
Median :0.037489   Median :-0.011825
Mean   :0.046593   Mean   :-0.012905
Helix123
  • 3,502
  • 2
  • 16
  • 36
Olena
  • 11
  • 2

1 Answers1

0

From the help page of function pvcm you can see that model = "within" estimates a pooling model per individual:

Coefficients are assumed to be fixed if model = "within" and random if model = "random". In the first case, a different model is estimated for each individual (or time period). In the second case, the Swamy (1970) model is estimated. It is a generalized least squares model which uses the results of the previous model.

In your case with model = "within" you estimate a lot of models, each with estimates for coefficients. Thus, summary gives only summary statistics of the coefficients as it could be a lot of models/coefficients for the same variable. To see the coefficients, use coef(<your_model>). Below I extend the example from the help page a little:

library("plm")
data("Produc", package = "plm")
zw <- pvcm(log(gsp) ~ log(pcap) + log(pc) + log(emp) + unemp, data = Produc, model = "within")
summary(zw) # gives summary information on estimated coefficients
coef(zw) # gives coefficients of all estimated models
## (Intercept)    log(pcap)      log(pc)    log(emp)         unemp
## ALABAMA          8.4960384 -1.442643991  0.279501016  1.83524980  0.0073545006
## ARIZONA          4.6652825 -0.162708442 -0.005220745  1.07582801 -0.0036579767
## ARKANSAS         3.2456536 -0.505650280  0.321247275  1.23401732  0.0014922130
## CALIFORNIA       0.2793476  0.263937746  0.248403298  0.69913460 -0.0107451010
## COLORADO         0.5143180  0.731379856 -0.209834096  0.74826795 -0.0039961705
## CONNECTICUT      5.0302333 -0.431134765  0.453161751  0.73256902 -0.0053864641
## DELAWARE        -1.1751222  0.622117695 -0.318462279  1.41693168 -0.0038134886
## FLORIDA          1.5253424  0.552803128 -0.250663389  0.87120938 -0.0014626098
## [...]
Helix123
  • 3,502
  • 2
  • 16
  • 36