R version 2.10.1 (2009-12-14)
Copyright (C) 2009 The R Foundation for Statistical Computing
ISBN 3-900051-07-0

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> ## ----------------------------------------------------------------------------
> ## Bera, Sosa-Escudero and Yoon (2001)
> ##
> ## data
> ## availability: none
> ## firms: General Motors, Chrysler, General Electric, Westinghouse, US Steel
> ##        (taken from Greene, 4e, 2000)
> ## errors: as in Greene (1993/2000/2003)
> ##
> ## analysis
> ## result: exact at precision given (except for tiny deviation for RSO_mu*)
> ## ----------------------------------------------------------------------------
> 
> ## preliminaries
> source("start.R")
Loading required package: kinship
Loading required package: survival
Loading required package: splines
Loading required package: nlme
Loading required package: lattice
[1] "kinship is loaded"
Loading required package: Formula
Loading required package: MASS
Loading required package: sandwich
Loading required package: zoo
Loading required package: Matrix
Loading required package: car
Loading required package: lmtest
> 
> ## data pre-processing
> gr <- subset(Grunfeld, firm %in% c("General Motors", "Chrysler", "General Electric",
+   "Westinghouse", "US Steel"))
> gr$firm <- factor(gr$firm)
> gr$invest[c(66, 78)] <- c(261.6, 645.2)
> gr$capital[72] <- 232.6
> pgr <- plm.data(gr, c("firm", "year"))
> 
> 
> ## model fitting
> fm_pool <- plm(invest ~ value + capital, data = pgr, model = "pooling")
> 
> ## preliminary computations for Table 1
> rr <- residuals(fm_pool)
> u <- rr[-((0:4) * 20 + 1)]
> u1 <- rr[-((1:5) * 20)]
> A <- 1 - crossprod(rr, kronecker(diag(5), matrix(1, nrow = 20, ncol = 20)) %*% rr) / sum(rr^2)
> B <- crossprod(u, u1) / sum(u^2)
> 
> ## Table 1 (p. 13) gives the following statistics:
> plmtest(invest ~ value + capital, data = pgr, type = "bp")     ## RS_mu

	Lagrange Multiplier Test - (Breusch-Pagan)

data:  invest ~ value + capital 
chisq = 453.8221, df = 1, p-value < 2.2e-16
alternative hypothesis: significant effects 

> 5 * 20 * (A + 2*B)^2 / 2 / (20 - 1) / (1 - 2/20)               ## RS_mu*
         [,1]
[1,] 384.1832
> 5 * 20^2 * B^2 / (20 - 1)                                      ## RS_rho
         [,1]
[1,] 73.35132
> pbsytest(invest ~ value + capital, data = pgr)                 ## RS_rho*

	Bera, Sosa-Escudero and Yoon locally robust test

data:  formula 
chisq = 3.7125, df = 1, p-value = 0.05401
alternative hypothesis: AR(1) errors sub random effects 

> pbsytest(invest ~ value + capital, data = pgr, test = "J")     ## RS_mu,rho

	Baltagi and Li AR-RE joint test

data:  formula 
chisq = 457.5346, df = 2, p-value < 2.2e-16
alternative hypothesis: AR(1) errors or random effects 

> plmtest(invest ~ value + capital, data = pgr, type = "honda")  ## RSO_mu

	Lagrange Multiplier Test - (Honda)

data:  invest ~ value + capital 
normal = 21.3031, p-value < 2.2e-16
alternative hypothesis: significant effects 

> pbsytest(invest ~ value + capital, data = pgr, test = "RE")    ## RSO_mu*

	Bera, Sosa-Escudero and Yoon locally robust test

data:  formula 
z = 19.6006, p-value < 2.2e-16
alternative hypothesis: random effects sub AR(1) errors 

> ## small deviation for RSO_mu* = 19.60059 instead of 19.605
>