smoking: Smoking example

Description Format Details Source See Also Examples

Description

Meta-analyses on the effect of smoking on mortality risk.

Format

A data frame with the following columns:

study study label
participants total number of participants
d.smokers number of deaths in smokers' group
py.smokers person years at risk in smokers' group
d.nonsmokers number of deaths in non-smokers' group
py.nonsmokers person years at risk in non-smokers' group

Details

Data have been reconstructed based on the famous Smoking and Health Report to the Surgeon General (Bayne-Jones S et al., 1964). Data sets can be used to evaluate the risk of smoking on overall mortality (dataset smoking) and lung-cancer deaths (dataset lungcancer), respectively.

The person time is attributed such that the rate ratios are equal to the reported mortality ratios implicitly assuming that the data have arisen from a homogeneous age group; more detailed information by age is not available from the report. Note, the group of "non-smokers" actually consists of all participants except those who are smokers of cigarettes only. Information on real non-smokers is not available from the published Smoking and Health Report.

Source

Bayne-Jones S et al. (1964): Smoking and Health: Report of the Advisory Committee to the Surgeon General of the United States. U-23 Department of Health, Education, and Welfare. Public Health Service Publication No. 1103.

See Also

metainc

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
data(smoking)

m1 <- metainc(d.smokers, py.smokers,
              d.nonsmokers, py.nonsmokers,
              data = smoking, studlab = study)
print(m1, digits = 2)

data(lungcancer)

m2 <- metainc(d.smokers, py.smokers,
              d.nonsmokers, py.nonsmokers,
              data = lungcancer, studlab = study)
print(m2, digits = 2)

Example output

Loading 'meta' package (version 4.9-5).
Type 'help(meta)' for a brief overview.
                         IRR       95%-CI %W(fixed) %W(random)
British Doctors         1.44 [1.35; 1.53]       8.1       14.6
Men in 9 States         1.70 [1.63; 1.76]      17.1       16.5
U.S. Veterans           1.79 [1.74; 1.84]      32.1       17.2
California Occupational 1.78 [1.56; 2.03]       1.9        8.5
California Legion       1.58 [1.42; 1.76]       2.8       10.3
Canadian Veterans       1.65 [1.59; 1.72]      16.1       16.3
Men in 25 States        1.63 [1.57; 1.69]      21.9       16.6

Number of studies combined: k = 7

                      IRR       95%-CI     z  p-value
Fixed effect model   1.68 [1.65; 1.71] 62.11        0
Random effects model 1.65 [1.56; 1.74] 18.43 < 0.0001

Quantifying heterogeneity:
tau^2 = 0.0041; H = 2.92 [2.14; 3.97]; I^2 = 88.2% [78.2%; 93.7%]

Test of heterogeneity:
     Q d.f.  p-value
 51.04    6 < 0.0001

Details on meta-analytical method:
- Mantel-Haenszel method
- DerSimonian-Laird estimator for tau^2
                          IRR         95%-CI %W(fixed) %W(random)
British Doctors         19.86 [11.81; 33.39]       4.3       10.0
Men in 9 States          9.95 [ 7.76; 12.76]      17.1       19.9
U.S. Veterans           12.33 [10.40; 14.60]      31.8       23.6
California Occupational 14.50 [ 4.62; 45.51]       2.1        2.9
California Legion        4.90 [ 2.63;  9.15]       6.6        7.8
Canadian Veterans       11.65 [ 8.79; 15.44]      17.2       18.3
Men in 25 States         9.54 [ 7.07; 12.86]      20.8       17.6

Number of studies combined: k = 7

                       IRR        95%-CI     z  p-value
Fixed effect model   11.10 [9.90; 12.45] 41.26        0
Random effects model 10.96 [8.93; 13.45] 22.94 < 0.0001

Quantifying heterogeneity:
tau^2 = 0.0387; H = 1.58 [1.04; 2.39]; I^2 = 59.8% [7.7%; 82.5%]

Test of heterogeneity:
     Q d.f. p-value
 14.93    6  0.0208

Details on meta-analytical method:
- Mantel-Haenszel method
- DerSimonian-Laird estimator for tau^2

meta documentation built on Sept. 14, 2021, 5:14 p.m.