pact (version 0.5.0)

overall.analysis: Overall statistics and inference

Description

Produces some statistics for the overall (non-predictive) comparison of the E and C for the same dataset for which the predictive model pact.fit was developed.

Usage

overall.analysis(p)

Arguments

p

An object of class pact

Value

An list with the following components. As a side effect, these are also printed on screen

family

The response variable type used

nobs

The sample size

n.E

Number of subjects getting the new treatment

n.C

Number of subjects getting the control treatment

LR

The log-rank statistic for the overal difference in survival between E and C groups (for family="cox")

LR.pval

The p-value for LR based on the log-rank test (for family="cox")

RR.E

The response rate for group treated with E (new treatment) (for family="binomial")

RR.C

The response rate for group treated with C (Control) (for family="binomial")

RRdiff.pval

The chi-square test based pvalue for the difference in response rates (for family="binomial")

Details

Statistics for the overall comparison of the E and C is produced for the the data from a randomized clinical trial. The input is an object of class pact.

Examples

data(prostateCancer)
Y <- prostateCancer[,3:4]
Xf <- prostateCancer[,7:8]
Xv <- prostateCancer[,c(5:6,9)]
Treatment <- as.factor(prostateCancer[,2])
p <- pact.fit(Y=Y, Xf=Xf, Xv=Xv, Treatment=Treatment, family="cox", varSelect="none")
overall.analysis(p)

### Binary response
data(EORTC10994)
Y <- as.factor(EORTC10994[,4])
Xv <- EORTC10994[,c(2,5:7)]
Treatment <- as.factor(EORTC10994[,3])
p <- pact.fit(Y=Y,Xv=Xv,Treatment=Treatment,family="binomial",varSelect="none")
overall.analysis(p)