| meta.score {rmeta} | R Documentation |
Computes individual relative risks, a summary relative risk, and confidence intervals. The confidence intervals are based on inverting the score test (similar to the so-called "Cornfield" method for odd ratios).
meta.score(ntrt, nctrl, ptrt, pctrl, conf.level = 0.95, names = NULL, data = NULL, subset = NULL, na.action = na.fail, statistic = "RR", control = 1.5) ## S3 method for class 'meta.score': summary(object,...)
ntrt |
Number of subjects in treated/exposed group |
nctrl |
Number of subjects in control group |
ptrt |
Number of events in treated/exposed group |
pctrl |
Number of events in control group |
names |
names or labels for studies |
data |
data frame to interpret variables |
subset |
subset of studies to include |
na.action |
a function which indicates what should happen when
the data contain NAs. Defaults to na.fail. |
statistic |
"RR" for relative risk is currently the only option |
control |
used to set search limits in finding interval endpoints |
conf.level |
Confidence level for intervals |
object |
meta.score object |
... |
For future expansion |
An object of class meta.MH with print,
and summary methods.
The correction for skewness described in the reference is not yet implemented.
Gart JJ, Nam J. (1988) "Approximate Interval Estimation of the Ratio of Binomial Parameters: A review and corrections for skewness". Biometrics 44(2) 323–338
## From Gart and Nam
mice<-data.frame(n1=c(16, 16, 18, 15),
n0 = c(79, 87, 90, 82),
x1 = c(4, 2, 4, 1),
x0 = c(5, 3, 10, 3)
)
summary(meta.score(ntrt=n1,nctrl=n0,ptrt=x1,pctrl=x0,data=mice))