Chapter 2 epiR
2.1 epi.2by2
- Summary measures for count data presented in a 2 by 2 table
library(epiR)
epi.2by2(dat,
method = c("cohort.count", "cohort.time", "case.control", "cross.sectional"),
conf.level = 0.95,
units = 100,
outcome = c("as.columns","as.rows"))
dat
: an object of classtable
containing the individual cell frequencies.method
: a character string indicating the study design on which the tabular data has been based.- Based on the study design specified by the user, appropriate measures of association, measures of effect in the exposed and measures of effect in the population are returned by the function.
cohort.count | case.control | |
---|---|---|
Measures of association | ||
RR | \(\checkmark\) | |
OR | \(\checkmark\) | \(\checkmark\) |
Measures of effect in the exposed | ||
ARisk | \(\checkmark\) | \(\checkmark\) |
AFRisk | \(\checkmark\) | AFest |
Measures of effect in the population | ||
PARisk | \(\checkmark\) | \(\checkmark\) |
PAFRisk | \(\checkmark\) | PAFest |
chi-squared test | ||
chisq.strata | \(\checkmark\) | \(\checkmark\) |
chisq.crude | \(\checkmark\) | \(\checkmark\) |
chisq.mh | \(\checkmark\) | \(\checkmark\) |
Mantel-Haenszel (Woolf) test of homogeneity | ||
RR.homog | \(\checkmark\) | |
OR.homog | \(\checkmark\) | \(\checkmark\) |
conf.level
: magnitude of the returned confidence intervals. The default value is 0.95.units
: multiplier for prevalence and incidence (risk or rate) estimates. Default value is 100.unit=1
Outcomes per population unitunit=100
Outcomes per 100 population unitThe multiplier is applied to Attributable risk, Attributable risk in population, etc.
outcome
: how the outcome variable is represented in the contingency table.