## EXAMPLE 1:
## A cross sectional study investigating the relationship between dry cat
## food (DCF) and feline urologic syndrome (FUS) was conducted (Willeberg
## 1977). Counts of individuals in each group were as follows:
## DCF-exposed cats (cases, non-cases) 13, 2163
## Non DCF-exposed cats (cases, non-cases) 5, 3349
## Outcome variable (FUS) as columns:
dat <- matrix(c(13,2163,5,3349), nrow = 2, byrow = TRUE)
rownames(dat) <- c("DF+", "DF-"); colnames(dat) <- c("FUS+", "FUS-"); dat
epi.2by2(dat = as.table(dat), method = "cross.sectional",
conf.level = 0.95, units = 100, homogeneity = "breslow.day",
outcome = "as.columns")
## Outcome variable (FUS) as rows:
dat <- matrix(c(13,5,2163,3349), nrow = 2, byrow = TRUE)
rownames(dat) <- c("FUS+", "FUS-"); colnames(dat) <- c("DF+", "DF-"); dat
epi.2by2(dat = as.table(dat), method = "cross.sectional",
conf.level = 0.95, units = 100, homogeneity = "breslow.day",
outcome = "as.rows")
## Prevalence ratio:
## The prevalence of FUS in DCF exposed cats is 4.01 times (95\% CI 1.43 to
## 11.23) greater than the prevalence of FUS in non-DCF exposed cats.
## Attributable fraction:
## In DCF exposed cats, 75\% of FUS is attributable to DCF (95\% CI 30\% to
## 91\%).
## Population attributable fraction:
## Fifty-four percent of FUS cases in the cat population are attributable
## to DCF (95\% CI 4\% to 78\%).
## EXAMPLE 2:
## This example shows how the table function can be used to pass data to
## epi.2by2. Here we use the birthwgt data from the MASS package.
library(MASS)
dat1 <- birthwt; head(dat1)
## Generate a table of cell frequencies. First set the levels of the outcome
## and the exposure so the frequencies in the 2 by 2 table come out in the
## conventional format:
dat1$low <- factor(dat1$low, levels = c(1,0))
dat1$smoke <- factor(dat1$smoke, levels = c(1,0))
dat1$race <- factor(dat1$race, levels = c(1,2,3))
## Generate the 2 by 2 table. Exposure (rows) = smoke. Outcome (columns) = low.
tab1 <- table(dat1$smoke, dat1$low, dnn = c("Smoke", "Low BW"))
print(tab1)
## Compute the odds ratio and other measures of association:
epi.2by2(dat = tab1, method = "cohort.count",
conf.level = 0.95, units = 100, homogeneity = "breslow.day",
outcome = "as.columns")
## Stratify by race:
tab2 <- table(dat1$smoke, dat1$low, dat1$race,
dnn = c("Smoke", "Low BW", "Race"))
print(tab2)
## Compute the crude and Mantel-Haenszel adjusted odds ratio and other
## measures of association:
epi.2by2(dat = tab2, method = "cohort.count",
conf.level = 0.95, units = 100, homogeneity = "breslow.day",
outcome = "as.columns")
## Now turn tab2 into a data frame. Often your data will be presented to
## you in this summary format:
dat2 <- data.frame(tab2)
print(dat2)
## Re-format dat2 (a summary count data frame) into tabular format using the
## xtabs function:
tab3 <- xtabs(Freq ~ Smoke + Low.BW + Race, data = dat2)
print(tab3)
# tab3 can now be passed to epi.2by2:
rval <- epi.2by2(dat = tab3, method = "cohort.count",
conf.level = 0.95, units = 100, homogeneity = "breslow.day",
outcome = "as.columns")
print(rval)
## Crude odds ratio:
## 2.01 (95\% CI 1.03 to 3.96)
## Mantel-Haenszel adjusted odds ratio:
## 3.09 (95\% CI 1.49 to 6.39)
## Plot the individual strata-level odds ratios and compare them with the
## Mantel-Haenszel adjusted odds ratio.
library(ggplot2); library(scales)
nstrata <- 1:dim(tab3)[3]
strata.lab <- paste("Strata ", nstrata, sep = "")
y.at <- c(nstrata, max(nstrata) + 1)
y.lab <- c("M-H", strata.lab)
x.at <- c(0.25, 0.5, 1, 2, 4, 8, 16, 32)
or.l <- c(rval$res$OR.mh$lower, rval$res$OR.strata$lower)
or.u <- c(rval$res$OR.mh$upper, rval$res$OR.strata$upper)
or.p <- c(rval$res$OR.mh$est, rval$res$OR.strata$est)
dat <- data.frame(y.at, y.lab, or.p, or.l, or.u)
p <- ggplot(dat, aes(or.p, y.at))
windows(); p + geom_point() +
geom_errorbarh(aes(xmax = or.l, xmin = or.u, height = 0.2)) +
labs(x = "Odds ratio", y = "Strata") +
scale_x_continuous(trans = log2_trans(), breaks = x.at,
limits = c(0.25,32)) + scale_y_continuous(breaks = y.at, labels = y.lab) +
geom_vline(xintercept = 1, lwd = 1) + coord_fixed(ratio = 0.75 / 1) +
theme(axis.title.y = element_text(vjust = 0))
## EXAMPLE 3:
## A study was conducted by Feychting et al (1998) comparing cancer occurrence
## among the blind with occurrence among those who were not blind but had
## severe visual impairment. From these data we calculate a cancer rate of
## 136/22050 person-years among the blind compared with 1709/127650 person-
## years among those who were visually impaired but not blind.
dat <- as.table(matrix(c(136,22050,1709,127650), nrow = 2, byrow = TRUE))
rval <- epi.2by2(dat = dat, method = "cohort.time", conf.level = 0.90,
units = 1000, homogeneity = "breslow.day", outcome = "as.columns")
summary(rval)$AR
## The incidence rate of cancer was 7.22 cases per 1000 person-years less in the
## blind, compared with those who were not blind but had severe visual impairment
## (90\% CI 6.20 to 8.24 cases per 1000 person-years).
round(summary(rval)$IRR, digits = 2)
## The incidence rate of cancer in the blind group was less than half that of the
## comparison group (incidence rate ratio 0.46, 90\% CI 0.40 to 0.53).Run the code above in your browser using DataLab