xtrec: Panel Unit Root Test Based on Recursive Detrending

In xtrec: Panel Unit Root Test Based on Recursive Detrending

Panel Unit Root Test Based on Recursive Detrending

Description

Implements the t-REC and t-RREC panel unit root tests of Westerlund (2015). The t-REC assumes iid errors; the robust t-RREC accounts for serial correlation, cross-sectional dependence, and heteroskedasticity.

Usage

xtrec(data, var, panel_id, time_id, trend = 0L,
      robust = FALSE, maxlag = -1L)

Arguments

data	A data frame in long format.
var	Character. Name of the variable to test.
panel_id	Character. Name of the panel identifier variable.
time_id	Character. Name of the time variable.
trend	Integer. Polynomial trend degree: 0 (constant only), 1 (linear trend), or 2 (quadratic trend).
robust	Logical. If TRUE, compute the robust t-RREC test.
maxlag	Integer. Maximum lag for BIC selection (-1 for automatic).

Value

An object of class "xtrec" containing the test statistic, p-value, and panel summary statistics.

References

Westerlund, J. (2015). The effect of recursive detrending on panel unit root tests. Journal of Econometrics, 185(2), 453-467. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1016/j.jeconom.2014.09.013")}

Examples

dat <- grunfeld_data()
res <- xtrec(dat, var = "invest", panel_id = "firm",
             time_id = "year", trend = 0L, robust = FALSE)
print(res)

xtrec documentation built on March 29, 2026, 5:07 p.m.