find_cp_linreg: Find the change point in count data using linear regression...

In aarmiller/delaySim: Package to run delayed diagnosis simulations

Find the change point in count data using linear regression models

Description

Find the change point in count data using linear regression models

Usage

find_cp_linreg(
  data,
  var_name = "n_miss_visits",
  method = "lm",
  eval_criteria = "AIC",
  return_miss_only = FALSE,
  specify_cp = NULL,
  week_period = FALSE
)

Arguments

data	A dataset of visit counts
var_name	The name of the count variable to find the change-point for
method	The method used to fit curves before and after the changepoint. Options include "lm", "lm_quad", "lm_cube", "quad", "cube", "exp", "spline"
eval_criteria	The evaluation criteria used to find change points
return_miss_only	Logical argument to only return the tibbles of miss visit counts
specify_cp	Set a specific change point you want to use instead of searching for optimal change point. Enter a postive integer value repersenting the days before the index on which you you want to specify the change point. (e.g. 100 would be 100 days before the index)
week_period	Logical to incorporate a "day of the week" effect into the linear model. Note this is only sensible for one-day period aggregation.

Examples

cp_result_original <- final_time_map %>%
prep_cp_data(event_name = "any_ssd", start_day = 1, by_days = 1) %>%
find_cp_linreg(var_name="n_miss_visits", method="lm_cube")

aarmiller/delaySim documentation built on Jan. 2, 2023, 11:23 p.m.