pgmm {plm}R Documentation

General method of moments estimator for panel data

Description

General method of moments estimator for static or dynamic models with panel data.

Usage

pgmm(formula,data,effect="individual",model="twosteps",
instruments=NULL,inst.transformation="l",lags.endog=1,
first.period=-99,last.period=-1,...)
## S3 method for class 'pgmm':
summary(object, ...)
## S3 method for class 'summary.pgmm':
print(x,digits=5,length.line=70, ...)

Arguments

formula a symbolic description for the model to be estimated or a character string for a pure auto–regressive model,
object,x an object of class pgmm,
data the data, must be an object of class pdata.frame and is mandatory,
effect the effects introduced in the model, one of "individual" or "twoways",
model one of "onestep" or "twosteps",
instruments a one side formula containing the instruments,
inst.transformation a vector of character strings containing "l" for instruments in level and "d" for instruments in first difference,
lags.endog an integer between 0 and 2 indicating the number of lags of the dependent variable,
first.period a vector of integer containing the first period for which the instrument has to be introduced,
last.period a vector integer containing the last period for which the instrument has to be introduced,
digits digits,
length.line the maximum length of the lines in the print output,
... further arguments.

Details

pgmm estimate a model for panel data with the general method of moments estimator. A dynamic model is specified by fixing the lags.endog argument to 1 or 2. By default, the instruments used are the independent variables (and the dependent variable if lags.endog>0). The complete list of instruments can also be specified with the instruments argument. For each instruments, the first period used is specified by first.period , the last period by last.period and the way they are introduced (in level or in first difference by inst.transformation). These three arguments may be of length one, in this case, all the instruments are treated the same way. In case of a dynamic model, they may be of length two, then the first element is used for the dependent variable and the second element is used for the independent variables. They finally may be of length equal to the number of instruments to specify a specific rule for each instrument.

Value

an object of class c("pgmm","panelmodel"), which has the following elements :

coefficients the vector (or the list for fixed effects) of coefficients,
residuals the vector of residuals,
fitted.values the vector of fitted.values,
vcov the covariance matrix of the coefficients,
df.residual degrees of freedom of the residuals,
model a data.frame containing the variables used for the estimation,
omega a matrix containing the instruments (each column is an individual),
WDWm1 the inverse of the norm matrix used in the gmm estimation,
J a 3D table containing the first period, last period and number of periods for each instrument and each year,
K a list containing K the number of explanatory variables, Ky the number of lags of the dependent variable and Kt the number of time dummies,
call the call.

It has print, summary and print.summary methods.

Author(s)

Yves Croissant

References

Arellano, Manuel & Bond, Stephen (1991), Some Tests of Specification for Panel Data: Monte Carlo Evidence and an Application to Employment Equations, The Review of Economic Studies, vol. 58(2), april 1991, pp.227–297.

See Also

plm for the estimation of models with instrumental variables.

Examples

library(Ecdat)
data(Snmesp)
pdata.frame(Snmesp,"firm","year")
z <-  pgmm(n~lag(w)+lag(w,2),Snmesp,effect="twoways",model="twosteps",lags.endog=2,
          last.period=c(-2),
          inst.transformation=c("l"),instruments=~n+w)
summary(z)


[Package plm version 0.2-1 Index]