epi.iv {epiR}R Documentation

Fixed-effect meta-analysis of binary outcomes using the inverse variance method

Description

Computes odds ratios (or risk ratios) and confidence intervals for binary outcome data. Computes the pooled odds ratio (or risk ratios) using the inverse variance method. Performs a test of heterogeneity among trials. Performs a test for the overall difference between groups (that is, after pooling the studies, do treated groups differ significantly from controls?).

Usage

epi.iv(ev.trt, n.trt, ev.ctrl, n.ctrl, names, method = "odds.ratio", 
   conf.level = 0.95)

Arguments

ev.trt observed number of events in the treatment group.
n.trt number in the treatment group.
ev.ctrl observed number of events in the control group.
n.ctrl number in the control group.
names character string identifying each trial.
method a character string indicating the method to be used. Options are odds.ratio or risk.ratio.
conf.level magnitude of the returned confidence interval. Must be a single number between 0 and 1.

Details

Using this method, the inverse variance weights are used to compute the pooled odds ratios and risk ratios. The inverse variance weights should be used to indicate the weight each trial contributes to the meta-analysis.

Value

A list containing:

odds.ratio the names of the trials specified, the odds ratios for each trial, the lower and upper bounds of the confidence interval of the odds ratio for each trial and the pooled odds ratio and the lower and upper bounds of the confidence interval of the pooled odds ratio.
risk.ratio the names of the trials specified, the risk ratio for each trial, the lower and upper bounds of the confidence interval of the risk ratio for each trial and the pooled risk ratio and the lower and upper bounds of the confidence interval of the pooled risk ratio.
weights the raw and inverse variance weights assigned to each trial.
heterogeneity a vector containing Q the heterogeneity test statistic, df the degrees of freedom and its associated P-value.
Hsq the relative excess of the heterogeneity test statistic Q over the degrees of freedom df.
Isq the percentage of total variation in study estimates that is due to heterogeneity rather than chance.
effect a vector containing z the test statistic for overall treatment effect and its associated P-value.

Note

The inverse variance method performs poorly when data are sparse, both in terms of event rates being low and trials being small. The Mantel-Haenszel method (epi.mh) is more robust when data are sparse.

Using this method, the inverse variance weights are used to compute the pooled odds ratios and risk ratios.

References

Deeks JJ, Altman DG, Bradburn MJ (2001). Statistical methods for examining heterogeneity and combining results from several studies in meta-analysis. In: Egger M, Davey Smith G, Altman D (eds). Systematic Review in Health Care Meta-Analysis in Context. British Medical Journal, London, 2001, pp. 291 - 299.

Higgins JP, Thompson SG (2002). Quantifying heterogeneity in a meta-analysis. Statistics in Medicine 21: 1539 - 1558.

See Also

epi.dsl, epi.mh, epi.smd

Examples

data(epi.epidural)
epi.iv(ev.trt = epi.epidural$ev.trt, n.trt = epi.epidural$n.trt, 
   ev.ctrl = epi.epidural$ev.ctrl, n.ctrl = epi.epidural$n.ctrl, 
   names = as.character(epi.epidural$trial), method = "odds.ratio", 
   conf.level = 0.95)

[Package epiR version 0.9-15 Index]