plot_diagnostics: Individual demand diagnostics

In PBCAR/PThelper: Systematic Cleaning, Processing, and Summarizing of Behavioral Economic Purchase Task Data

Individual demand diagnostics

Description

This function diagnoses individual demand, by visualizing empirical consumption or fitted demand curves (linear or exponentiated). This function can be used to assess fitted demand curves of those with poor R^2 values (default is < 0.5) or those that are greater than a set number of standard deviations away from the mean (default is |3|). Alternatively, this function can be used to visualize all empirical demand or individual demand curves. See details for further information.

Usage

plot_diagnostics(
  pt,
  id_var,
  type = NULL,
  diagnostics = "all",
  threshold = NULL,
  zero_val = 0.001,
  n_rc = c(4, 5)
)

Arguments

pt	A data frame consisting of the 'id_var', purchase task variables, alpha or eta (depending on the type of demand curve to diagnose), Q0 and k-value if 'type' is "curve", as well as and R^2 values is 'diagnostics' argument is "r2".
id_var	The name of the unique identifier as identified in the data frame.
type	The type of demand to be visualized. One of c("empirical","linear","curve").
diagnostics	The diagnostic used to identify potentially poor-quality demand curves when 'type' is "linear" or "curve". One of c("r2","zscore","all"). The default is "all".
threshold	The threshold of R^2 or z-score, depending on the 'diagnostics' selected. For 'diagnostics' "r2", the default is 0.5, thus plotting those with R^2 scores lower than 0.5. For 'diagnostics' "zscore", the default is 3, plotting those with a demand value (alpha or eta) value that is greater than 3 standard deviations away from the mean (z-score > |3|).
zero_val	For 'type' "linear", the value to substitute zero values in the price and consumption data (default is 0.001).
n_rc	The number of rows and columns used to display individual curves. The default is c(4,5).

Details

To diagnose empirical consumption before or after quality control has been implemented, this function provides users the ability to plot individual responses on the purchase task, similar to the consumption visualization produced using the 'plot_summary()' function. To diagnose fitted linear or exponentiated demand curves, this function will produce individual demand curves similar to those produced for overall demand in the 'pt_linear' or 'pt_curve()' function, respectively.

Value

A ggplot2 graphical object

Examples

### --- Load Data
data("cpt_data")

### --- Prep Data
pt <- price_prep(cpt_data, id_var = "ID", vars = c(paste0("cpt",1:15)),
prices = c("0","0.05","0.10","0.20","0.30","0.40","0.50", "0.75","1","2","3","4","5","7.5","10"))

pt2 <- pt_prep(pt, id_var = "ID", type = "partial", remove0 = TRUE, max_val = 99)
pt3 <- pt_qc(pt2, id_var = "ID", type = "partial")
pt4 <- pt_curve(pt3$data, id_var = "ID", type = "individual")

### --- Function Example
plot_diagnostics(pt4, id_var = "ID", type = "curve", diagnostics = "r2", threshold = 0.7)

PBCAR/PThelper documentation built on May 13, 2024, 3:45 p.m.