Skip to contents

Odds ratio for a 2x2 table [[a, b], [c, d]]

Source: R/effect_sizes.R
odds_ratio.Rd

Odds ratio for a 2x2 table [[a, b], [c, d]]

Usage

odds_ratio(a, b, c, d, confidence = 0.95)

Arguments

a, b, c, d

Cell counts of the 2x2 table: a = exposed with outcome, b = exposed without, c = unexposed with outcome, d = unexposed without.

confidence

Confidence level. Default 0.95.

Value

A morie_effect_size.

Examples

# Cohort: 20/100 exposed and 10/100 unexposed develop the outcome.
res <- odds_ratio(20, 80, 10, 90)
res                          # rich print: estimate + CI
#> $measure
#> [1] "Odds ratio"
#> 
#> $estimate
#> [1] 2.25
#> 
#> $ci_lower
#> [1] 0.9942949
#> 
#> $ci_upper
#> [1] 5.091548
#> 
#> $se
#> [1] 0.4166667
#> 
#> $n
#> [1] 200
#> 
#> $extra
#> $extra$log_or
#> [1] 0.8109302
#> 
#> 
#> attr(,"class")
#> [1] "morie_effect_size" "list"             
res$estimate                 # (a*d)/(b*c) = 2.25
#> [1] 2.25
c(lower = res$ci_lower, upper = res$ci_upper)
#>     lower     upper 
#> 0.9942949 5.0915478 

# OR = 1 means no association; a CI excluding 1 is "significant".
odds_ratio(50, 50, 50, 50)$estimate      # 1
#> [1] 1

# `confidence` widens/narrows the interval.
odds_ratio(20, 80, 10, 90, confidence = 0.99)$ci_upper
#> [1] 6.581038