inf_2D_image {sim2Dpredictr}

Display Inference Results for 2D Predictors

Description

Provide graphics for spatial extent of predictor parameters, rejections and/or the truth/falsity of the rejections.

Usage

inf_2D_image(
  rejections = NULL,
  B = NULL,
  im.res,
  test.statistic = NULL,
  reject.threshold = NULL,
  binarize.B = TRUE,
  grid.color = "grey",
  n.colors = length(unique(B)),
  B.incl.B0 = TRUE,
  plot.title = TRUE,
  manual.title = NULL,
  title.size = 1
)

Arguments

rejections

A binary vector; rejection[i] = 1 means the null hypothesis is rejected for parameter B[i], whereas rejection[i] = 0 means that the null hypothesis was not rejected for parameter B[i].

B

A vector of "true" parameter values. For inference purposes, this can be a vector of actual parameter values, or a binary vector indicating non-zero status.

im.res

A vector defining the dimension of spatial data. The first entry is the number of rows and the second entry is the number of columns.

test.statistic

A vector of test statistics; e.g., t-statistics or p-values that are used to determine whether or not to reject the null hypothesis.

reject.threshold

A list whose first element is the rejection criteria, e.g., the minimum t-statistic or maximum p-value for which to reject the null hypothesis. The second element is one of c("greater", "less", "2-tailed"), which tell the function to reject when the values in test.statistic are greater than or less than the threshold, the test is a 2-tailed, respectively. In the latter case the function internally calculates the upper or lower threshold needed for the 2-tailed test.

binarize.B

Either TRUE (default) or FALSE. When binarize.B = TRUE the parameter vector is converted to a binary vector where 1 indicates non-zero parameter and 0 indicates zero-valued parameter.

grid.color

Specify the color for the grid lines.

n.colors

Determines the number of colors in the printed image. Default is length(unique(B)), but it is recommended to use trial and error to determine the ideal setting for specific situations.

B.incl.B0

If B.incl.B0 = TRUE then the first entry should be the intercept, B0. B.incl.B0 = FALSE indicates that the first entry of B is not an intercept.

plot.title

When plot.title = TRUE a title accompanies the output graph, and plot.title = FALSE suppresses the title.

manual.title

When plot.title = TRUE, use manual.title to specify a title manually.

title.size

Specifies the size of the title text. This is based on cex.main within the image() function. Default is 1.

Value

An image depicting the spatial extent of some image characteristic.

Note

If both rejections and B are specified then the function provides an image with separate color each for:

• No rejection and B[i] = 0 (i.e. True Negative).

• No rejection and B[i] != 0 (i.e. False Negative).

• Rejection and B[i] = 0 (i.e. False Positive).

• Rejection and B[i] != 0 (i.e. True Positive).

Examples

## parameter vector
Bex <- beta_builder(row.index = c(rep(5, 3), rep(6, 3), rep(7, 3)),
                    col.index = rep(c(5, 6, 7), 3),
                    im.res = c(10, 10), index.type = "manual",
                    B0 = 0, B.values = 1:9,
                    output.indices = FALSE)

## co-opt beta builder to get rejections
rejex <- beta_builder(row.index = c(rep(4, 3), rep(5, 3), rep(6, 3)),
                      col.index = rep(c(4, 5, 6), 3),
                      im.res = c(10, 10), index.type = "manual",
                      B0 = 0, B.values = rep(1, 9),
                      output.indices = FALSE)[-1]

rejex.sm2 <- beta_builder(row.index = 5:6, col.index = 5:6,
                          im.res = c(10, 10),
                          B0 = 0, B.values = 1,
                          output.indices = FALSE)[-1]

## just B
inf_2D_image(B = Bex, im.res = c(10, 10))
## just rejections
inf_2D_image(rejections = rejex, im.res = c(10, 10))

## both B and rejections
inf_2D_image(rejections = rejex, B = Bex, im.res = c(10, 10))
inf_2D_image(rejections = rejex.sm2, B = Bex, im.res = c(10, 10))

## larger dimension example
Bex2 <- beta_builder(row.index = 5:15, col.index = 16:20,
                     im.res = c(50, 50), B0 = 0,
                     B.values = 1:(length(5:15) * length(16:20)),
                     index.type = "rectangle",
                     output.indices = FALSE)
rejex2 <- beta_builder(row.index = 13:21, col.index = 30:41,
                       im.res = c(50, 50), B0 = 0,
                       B.values = rep(1, (length(13:21) * length(30:41))),
                       index.type = "rectangle",
                       output.indices = FALSE)[-1]
rejex3 <- beta_builder(row.index = 5:20, col.index = 16:30,
                       im.res = c(50, 50), B0 = 0,
                       B.values = rep(1, (length(5:20) * length(16:30))),
                       index.type = "rectangle",
                       output.indices = FALSE)[-1]
rejex4 <- beta_builder(row.index = 5:10, col.index = 16:17,
                       im.res = c(50, 50), B0 = 0,
                       B.values = rep(1, (length(5:10) * length(16:17))),
                       index.type = "rectangle",
                       output.indices = FALSE)[-1]
## images
inf_2D_image(B = Bex2, im.res = c(50, 50))
inf_2D_image(B = Bex2, im.res = c(50, 50), binarize.B = FALSE)
inf_2D_image(rejections = rejex2, im.res = c(50, 50))

## No TP
inf_2D_image(rejections = rejex2, B = Bex2, im.res = c(50, 50))
## ALL TP
inf_2D_image(rejections = Bex2[-1], B = Bex2, im.res = c(50, 50))
## No FN
inf_2D_image(rejections = rejex3, B = Bex2, im.res = c(50, 50))
## No FP, but FN
inf_2D_image(rejections = rejex4, im.res = c(50, 50))
inf_2D_image(B = Bex2, im.res = c(50, 50))
inf_2D_image(rejections = rejex4, B = Bex2, im.res = c(50, 50))