View source: R/propensity_matching_functions.R
Given a data.table with information about which entities should be matched against, performs propensity score matching using nearest neighbors and saves out diagnostic plots. Returns a list of those entities which are significantly different from the population
1 | run_propensity_matching(dt, cols_of_interest, reg_outcome_var, match_exclude_cols, bad_entities, entity_name, plot_fp, list_save_fp, list_name, control_match_num = 3, verbose = T, sample_size = NULL, entity_sample = NULL)
|
dt: |
data.table containin all the data |
cols_of_interest: |
columns on which matching should occur |
reg_outcome_var: |
character indicating the outcome column variable |
match_exclude_cols: |
character vector of columns to exclude when performing the matching |
bad_entities: |
a character vector indicating the entities for which propensity score matching should be performed |
entity_name: |
character vector of the column in dt to be used subsetting down and identifiying 'bad_entities' |
plot_fp: |
character filepath indicating where the psm matching plots should be stored |
list_save_fp: |
character filepath indicating where the list of significant entities should be stored |
control_match_num: |
The number of properties to be matched from the global population |
verbose: |
Boolean indicating whether or not to give progress updates |
sample_size: |
numeric indicating the sample size of the entity of interest to be taken for matching |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.