Regression diagnostics

morie_breusch_pagan tests for heteroskedasticity (Koenker's studentised form, as lmtest::bptest); morie_durbin_watson gives the first-order autocorrelation statistic, roughly 2(1 - rho); morie_vif gives variance inflation factors 1/(1 - R_j^2), where a value above about 10 means that coefficient's variance is inflated an order of magnitude by collinearity.

Usage

morie_breusch_pagan(fit)

morie_durbin_watson(fit)

morie_vif(X, add_intercept = TRUE)

Arguments

fit

a morie_ols fit

X

Argument X; see Usage.

add_intercept

Argument add_intercept; see Usage.

Value

a list of the statistic and, where exact, its p-value

Examples

if (requireNamespace("sandwich", quietly = TRUE)) {
  N <- 40
  X1 <- sapply(0:(N - 1), function(i) ((i * 7)%%13) + 0.5 * ((i *
      3)%%5))
  X2 <- sapply(0:(N - 1), function(i) ((i * 5)%%11) - 0.25 * ((i *
      2)%%7))
  E <- sapply(0:(N - 1), function(i) ((i * 13)%%17)/17 - 0.5)
  Y <- 3 + 1.5 * X1 - 0.8 * X2 + E * (1 + 0.05 * X1)
  X <- cbind(X1, X2)
  FIT <- morie_ols(Y, X)
  morie_breusch_pagan(FIT)
}
#> $statistic
#> [1] 0.7927511
#> 
#> $df
#> [1] 2
#> 
#> $p_value
#> [1] 0.672754
#> 
#> $studentised
#> [1] TRUE
#>