Plot LHWR Local Inference — plot_lhwr

Plot local p-values, adjusted p-values, or local significance for a fitted LHWR model. The Poincare geometry gives a clean disk map; projection and hyperboloid modes reuse plot.lhwr().

Usage

plot_lhwr_inference(
  object,
  coefficient = NULL,
  type = c("p_value", "p_adjusted", "significance"),
  geometry = c("poincare", "projection", "hyperboloid"),
  alpha = 0.05,
  p_adjust = c("BH", "none", "holm", "bonferroni", "BY", "fdr"),
  inference_df = c("edf", "residual", "normal"),
  show_info = FALSE,
  ...
)

Arguments

object: An LHWR model object fitted with diagnostics = "full".
coefficient: Coefficient name.
type: Inference surface: "p_value", "p_adjusted", or "significance".
geometry: Plot geometry: "poincare", "projection", or "hyperboloid".
alpha: Significance level.
p_adjust: Multiplicity adjustment.
inference_df: Degrees-of-freedom rule.
show_info: Logical; draw the explanatory information box in the Poincare view.
...: Additional arguments passed to the plotting function.

Value

Invisibly returns the map object for Poincare plots or object.

Examples

H <- simulate_H2(45, r_max = 2)
x <- rnorm(45)
y <- 1 + x + rnorm(45, sd = 0.2)
fit <- lhwr(y ~ x, data.frame(y, x), Z = H$Z, bw = 18, adaptive = TRUE,
            diagnostics = "full")
plot_lhwr_inference(fit, coefficient = "x", type = "significance")