Baltagi and Li Serial Dependence Test For Random Effects Models

Baltagi and Li (1995) 's Lagrange multiplier test for AR(1) or MA(1) idiosyncratic errors in panel models with random effects.

pbltest(x, ...)

# S3 method for class 'formula'
pbltest(x, data, alternative = c("twosided", "onesided"), index = NULL, ...)

# S3 method for class 'plm'
pbltest(x, alternative = c("twosided", "onesided"), ...)

Arguments

x

a model formula or an estimated random–effects model of class plm ,

...

further arguments.

data

for the formula interface only: a data.frame,

alternative

one of "twosided", "onesided". Selects either \(H_A: \rho \neq 0\) or \(H_A: \rho = 0\) (i.e., the Normal or the Chi-squared version of the test),

index

the index of the data.frame,

Value

An object of class "htest".

Details

This is a Lagrange multiplier test for the null of no serial correlation, against the alternative of either an AR(1) or a MA(1) process, in the idiosyncratic component of the error term in a random effects panel model (as the analytical expression of the test turns out to be the same under both alternatives, (see Baltagi and Li 1995 and Baltagi and Li 1997) . The alternative argument, defaulting to twosided, allows testing for positive serial correlation only, if set to onesided.

References

Baltagi B, Li Q (1995). “Testing AR(1) Against MA(1) Disturbances in an Error Component Model.” Journal of Econometrics, 68, 133–151.

Baltagi B, Li Q (1997). “Monte Carlo Results on Pure and Pretest Estimators of an Error Components Model With Autocorrelated Disturbances.” Annales d'Economie et de Statistique, 48, 69–82.

See also

pdwtest(), pbnftest(), pbgtest(), pbsytest(), pwartest() and pwfdtest() for other serial correlation tests for panel models.

Author

Giovanni Millo

Examples

data("Grunfeld", package = "plm")

# formula interface
pbltest(inv ~ value + capital, data = Grunfeld)
#> 
#> 	Baltagi and Li two-sided LM test
#> 
#> data:  inv ~ value + capital
#> chisq = 69.532, df = 1, p-value < 2.2e-16
#> alternative hypothesis: AR(1)/MA(1) errors in RE panel model
#> 

# plm interface
re_mod <- plm(inv ~ value + capital, data = Grunfeld, model = "random")
pbltest(re_mod)
#> 
#> 	Baltagi and Li two-sided LM test
#> 
#> data:  formula(x$formula)
#> chisq = 69.532, df = 1, p-value < 2.2e-16
#> alternative hypothesis: AR(1)/MA(1) errors in RE panel model
#> 
pbltest(re_mod, alternative = "onesided")
#> 
#> 	Baltagi and Li one-sided LM test
#> 
#> data:  formula(x$formula)
#> z = 8.3386, p-value < 2.2e-16
#> alternative hypothesis: AR(1)/MA(1) errors in RE panel model
#>