Skip to contents

Durbin-Watson test for temporal autocorrelation

Source: R/diagnostics_sim.R
durbin_watson.Rd

Tests first-order autocorrelation in temporally-ordered residuals.

Usage

durbin_watson(
  object,
  alternative = c("two.sided", "greater", "less"),
  time = NULL,
  resid_type = "pearson"
)

Arguments

object

A fitted model, or a numeric vector of temporally-ordered residuals. A fit's residuals are in its data's row order, so pass time unless the rows already are in time order.

alternative

"two.sided", "greater" (positive autocorr), or "less"

time

Optional time index, one per residual; the residuals are put in increasing time order before the statistic is formed. NULL (default) takes them in the order given.

resid_type

Residual type if extracting from a model (default "pearson"), as for moran_i().

Value

An htest object with DW statistic, lag-1 r, and p-value

Examples

set.seed(1)
e <- as.numeric(arima.sim(list(ar = 0.6), n = 100))
durbin_watson(e)
# Residuals recorded out of time order:
tt <- sample(100)
durbin_watson(e[tt], time = tt)