match_on_index: Function for performing matching of controls to cases using...
In rEHR: Manipulating and Analysing Electronic Health Record Data

Description Usage Arguments Value

Controls are matched on an arbitrary number of categrorical variables and on continuous variables via the extra_conditions argument. Also the date at index_var is matched to the eventdate in the consultation files, providing a dummy index date for controls of a consultaton within +/- index_diff_limit days of the index date.

Note that the consultaton files must be in flat-file format (i.e. not as part of the database, but as text (or other filetype, e.g stata dta) files). Set the import_fn argument to use different file formats (e.g. foreign::read.dta or readstata13::read.dta13)

The extra_conditions argument can add extra condtions to the matching criteria on top of the matching vars for example you could add "year > 1990". You can wrap calls to expressions in dotted brackets to automatically expand them. This is particularly useful when you want to find the value for each individual case. Each case is denoted by CASE e.g. "start_date < .(CASE$start_date)" will ensure the start date for controls is prior to the start date for the matched case.

1
2
3

match_on_index(cases, control_pool, index_var, match_vars,
  extra_conditions = "", index_diff_limit = 90, consult_path,
  n_controls = 5, cores = 1, import_fn = read.delim, ...)

`cases`	A dataframe of cases to which to match controls
`control_pool`	A dataframe of possible contols to match to cases
`index_var`	character string of the name of the variable containing index dates
`match_vars`	character vector detailing the common variables in `cases` and `control_pool` to match on
`extra_conditions`	character string detailing other matching constraints (see details)
`index_diff_limit`	integer number of days before or after the case index date that dummy index dates can be picked from the consultation files
`consult_path`	path to directory containing consultation files
`n_controls`	integer the number of controls to attempt to match to each case
`cores`	integer the number of processor cores to be used in processing
`import_fn`	function name stipulating the function used to read the consultation files
`...`	extra arguments to be passed to import_fn