vcmeta (version 1.5.0)

replicate.oddsratio: Compares and combines odds ratios in original and follow-up studies

Description

This function computes confidence intervals for an odds ratio from an original study and a follow-up study. Confidence intervals for the ratio of odds ratios and geometric average odds ratio are also computed. The confidence level for the ratio of ratios is 1 – 2*alpha, which is recommended for equivalence testing.

Usage

replicate.oddsratio(alpha, est1, se1, est2, se2)

Value

A 4-row matrix. The rows are:

• Row 1 summarizes the original study

• Row 2 summarizes the follow-up study

• Row 3 estimates the ratio of odds ratios

• Row 4 estimates the geometric average odds ratio

The columns are:

• Estimate - odds ratio estimate (single study, ratio, average)

• SE - standard error

• z - z-value

• p - p-value

• LL - exponentiated lower limit of the confidence interval

• UL - exponentiated upper limit of the confidence interval

Arguments

alpha

alpha level for 1-alpha confidence

est1

estimate of log odds ratio in original study

se1

standard error of log odds ratio in original study

est2

estimate of log odds ratio in follow-up study

se2

standard error of log odds ratio in follow-up study

References

Bonett2021vcmeta

Examples

replicate.oddsratio(.05, 1.39, .302, 1.48, .206)

# Should return:
#                          Estimate        SE          z            p
# Original:              1.39000000 0.3020000  4.6026490 4.171509e-06
# Follow-up:             1.48000000 0.2060000  7.1844660 6.747936e-13
# Original/Follow-up:   -0.06273834 0.3655681 -0.1716188 8.637372e-01
# Average:               0.36067292 0.1827840  1.9732190 4.847061e-02
#                         exp(LL)  exp(UL)
# Original:             2.2212961 7.256583
# Follow-up:            2.9336501 6.578144
# Original/Fllow-up:    0.5147653 1.713551
# Average:              1.0024257 2.052222