epi.cp: Extract unique covariate patterns from a data set

In epiR: Tools for the Analysis of Epidemiological Data

Extract unique covariate patterns from a data set

Description

Extract the set of unique patterns from a set of covariates (explanatory variables).

Usage

epi.cp(dat)

Arguments

dat	an i row by j column data frame where the i rows represent individual observations and the m columns represent a set of m covariates. The function allows for one or more covariates for each observation.

Details

This function extracts the k unique covariate patterns in a data set comprised of i observations, labelling them from 1 to k. The frequency of occurrence of each covariate pattern is listed. A vector of length i is also returned, listing the 1:k covariate pattern identifier for each observation.

Value

A list containing the following:

cov.pattern	a data frame with columns: id the unique covariate pattern identifier (labelled 1 to k), n the number of occasions each of the listed covariate pattern appears in the data, and the unique covariate combinations.
id	a vector of length i listing the 1:k covariate pattern identifier for each observation.

Author(s)

Thanks to Johann Popp and Mathew Jay for providing code and suggestions to enhance the utility of this function.

References

Dohoo I, Martin W, Stryhn H (2003). Veterinary Epidemiologic Research. AVC Inc, Charlottetown, Prince Edward Island, Canada.

Examples

## EXAMPLE 1:

## Generate a set of covariates:
set.seed(seed = 1234)
obs <- round(runif(n = 100, min = 0, max = 1), digits = 0)
v1 <- round(runif(n = 100, min = 0, max = 4), digits = 0)
v2 <- round(runif(n = 100, min = 0, max = 4), digits = 0)
dat.df01 <- data.frame(obs, v1, v2)

dat.glm01 <- glm(obs ~ v1 + v2, family = binomial, data = dat.df01)
dat.mf01 <- model.frame(dat.glm01)

## Covariate pattern. Drop the first column of dat.mf01 (since column 1 is the
## outcome variable:
epi.cp(dat.mf01[,2:3])

## There are 25 covariate patterns in this data set. Subject 100 has
## covariate pattern 21. 

epiR documentation built on Nov. 20, 2023, 9:06 a.m.