oddsratio {vcd}R Documentation

(Log) Odds Ratios

Description

Computes (log) odds ratios and their asymptotic standard errors for (possibly) stratified data.

Usage

oddsratio(x, stratum = NULL, log = TRUE)
## S3 method for class 'oddsratio':
plot(x, conf_level = 0.95, type = "o",
  xlab = NULL, ylab = NULL, xlim = NULL, ylim = NULL, whiskers = 0.1,
  baseline = TRUE, transpose = FALSE, ...)

Arguments

x a 2 by 2 by ... table.
stratum vector of strata dimensions.
log if FALSE, ordinary odds ratios are computed.
conf_level if not NULL or FALSE, conf_level-% confidence intervals are plotted for each data point.
type plot type.
xlab label for the x-axis. Defaults to "Strata" if transpose is FALSE.
ylab label for the y-axis. Defaults to "Strata" if transpose is TRUE.
xlim x-axis limits. Ignored if transpose is FALSE.
ylim y-axis limits. Ignored if transpose is TRUE.
baseline if TRUE, a red dashed line is plotted at a value of 1 (in case of odds) or 0 (in case of log-odds).
transpose if TRUE, the plot is transposed.
whiskers width of the confidence interval whiskers.
... other graphics parameters (see par).

Value

An object of class "logoddsratio", which is simply a vector of (log) odds ratios with dimensionality depending on stratum, along with the following attributes:

ASE a numeric vector with the asymptotic standard errors.
log logical indicating whether log odds ratios or common odds ratios are computed.

Note

In case of zero entries, 0.5 will be added to the table.

The summary method prints the standard errors and—for log odds ratios—also computes and prints asymptotic z tests (standardized log odds ratios) and the corresponding p values.

There is a confint method for computing confidence intervals for the (log) odds ratios.

The plot method plots (log) odds ratios, computed by oddsratio for 2 x 2 x k tables, along with confidence intervals.

Author(s)

David Meyer David.Meyer@R-project.org

References

M. Friendly (2000), Visualizing Categorical Data. SAS Institute, Cary, NC.

See Also

confint

Examples

## load Coal Miners data
data("CoalMiners")

## compute log odds ratios
lor <- oddsratio(CoalMiners)
lor

## summary with z tests
summary(lor)

## confidence intervals
confint(lor)

## visualization
plot(lor,
     xlab = "Age Group",
     main = "Breathelessness and Wheeze in Coal Miners")

## add quadratic model
g <- seq(25, 60, by = 5)
m <- lm(lor ~ g + I(g^2))
lines(fitted(m), col = "red")

[Package vcd version 1.2-4 Index]