dat.hackshaw1998.RdResults from 37 studies on the risk of lung cancer in women exposed to environmental tobacco smoke (ETS) from their smoking spouse.
dat.hackshaw1998The data frame contains the following columns:
| study | numeric | study number |
| author | character | first author of study |
| year | numeric | publication year |
| country | character | country where study was conducted |
| design | character | study design (either cohort or case-control) |
| cases | numeric | number of lung cancer cases |
| or | numeric | odds ratio |
| or.lb | numeric | lower bound of 95% CI for the odds ratio |
| or.ub | numeric | upper bound of 95% CI for the odds ratio |
| yi | numeric | log odds ratio |
| vi | numeric | corresponding sampling variance |
The dataset includes the results from 37 studies (4 cohort, 33 case-control) examining if women (who are lifelong nonsmokers) have an elevated risk for lung cancer due to exposure to environmental tobacco smoke (ETS) from their smoking spouse. Values of the log odds ratio greater than 0 indicate an increased risk of cancer in exposed women compared to women not exposed to ETS from their spouse.
Note that the log odds ratios and corresponding sampling variances were back-calculated from the reported odds ratios and confidence interval (CI) bounds (see ‘Examples’). Since the reported values were rounded to some extent, this introduces some minor inaccuracies into the back-calculations. The overall estimate reported in Hackshaw et al. (1997) and Hackshaw (1998) can be fully reproduced though.
Hackshaw, A. K., Law, M. R., & Wald, N. J. (1997). The accumulated evidence on lung cancer and environmental tobacco smoke. British Medical Journal, 315(7114), 980–988. https://doi.org/10.1136/bmj.315.7114.980
Hackshaw, A. K. (1998). Lung cancer and passive smoking. Statistical Methods in Medical Research, 7(2), 119–136. https://doi.org/10.1177/096228029800700203
medicine, oncology, epidemiology, smoking, odds ratios
### copy data into 'dat' and examine data
dat <- dat.hackshaw1998
head(dat, 10)
#>
#> study author year country design cases or or.lb or.ub yi vi
#> 1 1 Garfinkel 1981 USA cohort 153 1.18 0.90 1.54 0.1655 0.0188
#> 2 2 Hirayama 1984 Japan cohort 200 1.45 1.02 2.08 0.3716 0.0330
#> 3 3 Butler 1988 USA cohort 8 2.02 0.48 8.56 0.7031 0.5402
#> 4 4 Cardenas 1997 USA cohort 150 1.20 0.80 1.60 0.1823 0.0313
#> 5 5 Chan 1982 Hong Kong case-control 84 0.75 0.43 1.30 -0.2877 0.0797
#> 6 6 Correa 1983 USA case-control 22 2.07 0.81 5.25 0.7275 0.2273
#> 7 7 Trichopolous 1983 Greece case-control 62 2.13 1.19 3.83 0.7561 0.0889
#> 8 8 Buffler 1984 USA case-control 41 0.80 0.34 1.90 -0.2231 0.1927
#> 9 9 Kabat 1984 USA case-control 24 0.79 0.25 2.45 -0.2357 0.3390
#> 10 10 Lam 1985 Hong Kong case-control 60 2.01 1.09 3.72 0.6981 0.0981
#>
### load metafor package
library(metafor)
### random-effects model using the log odds ratios
res <- rma(yi, vi, data=dat, method="DL")
res
#>
#> Random-Effects Model (k = 37; tau^2 estimator: DL)
#>
#> tau^2 (estimated amount of total heterogeneity): 0.0170 (SE = 0.0171)
#> tau (square root of estimated tau^2 value): 0.1305
#> I^2 (total heterogeneity / total variability): 24.21%
#> H^2 (total variability / sampling variability): 1.32
#>
#> Test for Heterogeneity:
#> Q(df = 36) = 47.4979, p-val = 0.0952
#>
#> Model Results:
#>
#> estimate se zval pval ci.lb ci.ub
#> 0.2139 0.0471 4.5390 <.0001 0.1215 0.3062 ***
#>
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#>
### estimated average odds ratio with CI (and prediction interval)
predict(res, transf=exp, digits=2)
#>
#> pred ci.lb ci.ub pi.lb pi.ub
#> 1.24 1.13 1.36 0.94 1.63
#>
### illustrate how the log odds ratios and corresponding sampling variances
### can be back-calculated based on the reported odds ratios and CI bounds
dat$yi <- NULL
dat$vi <- NULL
dat <- data.frame(dat)
head(dat, 10)
#> study author year country design cases or or.lb or.ub
#> 1 1 Garfinkel 1981 USA cohort 153 1.18 0.90 1.54
#> 2 2 Hirayama 1984 Japan cohort 200 1.45 1.02 2.08
#> 3 3 Butler 1988 USA cohort 8 2.02 0.48 8.56
#> 4 4 Cardenas 1997 USA cohort 150 1.20 0.80 1.60
#> 5 5 Chan 1982 Hong Kong case-control 84 0.75 0.43 1.30
#> 6 6 Correa 1983 USA case-control 22 2.07 0.81 5.25
#> 7 7 Trichopolous 1983 Greece case-control 62 2.13 1.19 3.83
#> 8 8 Buffler 1984 USA case-control 41 0.80 0.34 1.90
#> 9 9 Kabat 1984 USA case-control 24 0.79 0.25 2.45
#> 10 10 Lam 1985 Hong Kong case-control 60 2.01 1.09 3.72
dat <- conv.wald(out=or, ci.lb=or.lb, ci.ub=or.ub, data=dat, transf=log)
head(dat, 10)
#>
#> study author year country design cases or or.lb or.ub yi vi
#> 1 1 Garfinkel 1981 USA cohort 153 1.18 0.90 1.54 0.1655 0.0188
#> 2 2 Hirayama 1984 Japan cohort 200 1.45 1.02 2.08 0.3716 0.0330
#> 3 3 Butler 1988 USA cohort 8 2.02 0.48 8.56 0.7031 0.5402
#> 4 4 Cardenas 1997 USA cohort 150 1.20 0.80 1.60 0.1823 0.0313
#> 5 5 Chan 1982 Hong Kong case-control 84 0.75 0.43 1.30 -0.2877 0.0797
#> 6 6 Correa 1983 USA case-control 22 2.07 0.81 5.25 0.7275 0.2273
#> 7 7 Trichopolous 1983 Greece case-control 62 2.13 1.19 3.83 0.7561 0.0889
#> 8 8 Buffler 1984 USA case-control 41 0.80 0.34 1.90 -0.2231 0.1927
#> 9 9 Kabat 1984 USA case-control 24 0.79 0.25 2.45 -0.2357 0.3390
#> 10 10 Lam 1985 Hong Kong case-control 60 2.01 1.09 3.72 0.6981 0.0981
#>