dat.bassler2004.RdResults from 10 trials reporting the physicians' judgement on the overall efficacy of ketotifen for long-term control of asthma and wheeze in children.
dat.bassler2004The data frame contains the following columns:
| study | character | study label |
| Ee | integer | number of children with treament success (ketotifen group) |
| Ne | integer | number of children (ketotifen group) |
| Ec | integer | number of children with treament success (control group) |
| Nc | integer | number of children (control group) |
| blind | character | blinding of clinicians |
Results from 10 trials reporting the physicians' judgement on the overall efficacy of Ketotifen for long-term control of asthma and wheeze in children. A prespecified subgroup analysis was conducted to evaluate whether the treatment effect is different in trials with adequate blinding compared to trials with inadequate / unclear blinding.
This data set is used as an example in Schwarzer et al. (2015).
Bassler D., Mitra A. A. D., Ducharme F. M., Forster J., & Schwarzer, G. (2004). Ketotifen alone or as additional medication for long-term control of asthma and wheeze in children. Cochrane Database of Systematic Reviews, 1, CD001384. https://doi.org/10.1002/14651858.CD001384.pub2
Schwarzer, G., Carpenter, J. R., & Rücker, G. (2015). Meta-analysis with R. Cham, Switzerland: Springer.
risk ratios, medicine, subgroup analysis
### Show full data set
dat.bassler2004
#> study Ee Ne Ec Nc blind
#> 1 Chay 1992 1 10 6 10 Adequate blinding
#> 2 Rackham 1989 31 68 38 65 Adequate blinding
#> 3 Van Asperen 1992 16 52 19 51 Adequate blinding
#> 4 Croce 1995 19 39 17 36 Method unclear
#> 5 de Benedictis 1990 7 34 35 41 Method unclear
#> 6 Longo 1986 10 18 15 18 Method unclear
#> 7 Montoya 1988 6 20 14 20 Method unclear
#> 8 Mulhern 1982 6 16 8 15 Method unclear
#> 9 Salmon 8 28 16 34 Method unclear
#> 10 Spicak 1983 9 25 20 25 Method unclear
### Load meta package
suppressPackageStartupMessages(library("meta"))
### Use DerSimonian-Laird estimator (which was the default in meta in the year 2015).
### Furthermore, print meta-analysis results with two digits.
oldset <- settings.meta(method.tau = "DL", digits = 2)
### Calculate experimental and control event rates
with(dat.bassler2004, summary(Ee / Ne))
#> Min. 1st Qu. Median Mean 3rd Qu. Max.
#> 0.1000 0.2893 0.3338 0.3433 0.4357 0.5556
with(dat.bassler2004, summary(Ec / Nc))
#> Min. 1st Qu. Median Mean 3rd Qu. Max.
#> 0.3725 0.4875 0.5923 0.6220 0.7750 0.8537
### Conduct meta-analysis using the inverse variance method
mb3 <- metabin(Ee, Ne, Ec, Nc, method = "I",
data = dat.bassler2004, studlab = study)
mb3
#> Number of studies: k = 10
#> Number of observations: o = 625 (o.e = 310, o.c = 315)
#> Number of events: e = 301
#>
#> RR 95%-CI z p-value
#> Common effect model 0.65 [0.55; 0.78] -4.81 < 0.0001
#> Random effects model 0.60 [0.46; 0.79] -3.64 0.0003
#>
#> Quantifying heterogeneity:
#> tau^2 = 0.0915 [0.0000; 0.6662]; tau = 0.3025 [0.0000; 0.8162]
#> I^2 = 52.3% [2.2%; 76.7%]; H = 1.45 [1.01; 2.07]
#>
#> Test of heterogeneity:
#> Q d.f. p-value
#> 18.87 9 0.0263
#>
#> Details on meta-analytical method:
#> - Inverse variance method
#> - DerSimonian-Laird estimator for tau^2
#> - Jackson method for confidence interval of tau^2 and tau
### Conduct subgroup analysis comparing trials with adequate blinding
### to trials with inadequate or unclear blinding
mb3s <- update(mb3, subgroup = blind, print.subgroup.name = FALSE)
mb3s
#> Number of studies: k = 10
#> Number of observations: o = 625 (o.e = 310, o.c = 315)
#> Number of events: e = 301
#>
#> RR 95%-CI z p-value
#> Common effect model 0.65 [0.55; 0.78] -4.81 < 0.0001
#> Random effects model 0.60 [0.46; 0.79] -3.64 0.0003
#>
#> Quantifying heterogeneity:
#> tau^2 = 0.0915 [0.0000; 0.6662]; tau = 0.3025 [0.0000; 0.8162]
#> I^2 = 52.3% [2.2%; 76.7%]; H = 1.45 [1.01; 2.07]
#>
#> Test of heterogeneity:
#> Q d.f. p-value
#> 18.87 9 0.0263
#>
#> Results for subgroups (common effect model):
#> k RR 95%-CI Q I^2
#> Adequate blinding 3 0.77 [0.58; 1.01] 2.49 19.7%
#> Method unclear 7 0.59 [0.47; 0.74] 14.29 58.0%
#>
#> Test for subgroup differences (common effect model):
#> Q d.f. p-value
#> Between groups 2.09 1 0.1483
#> Within groups 16.79 8 0.0324
#>
#> Results for subgroups (random effects model):
#> k RR 95%-CI tau^2 tau
#> Adequate blinding 3 0.75 [0.53; 1.08] 0.0237 0.1541
#> Method unclear 7 0.56 [0.39; 0.79] 0.1282 0.3580
#>
#> Test for subgroup differences (random effects model):
#> Q d.f. p-value
#> Between groups 1.40 1 0.2367
#>
#> Details on meta-analytical method:
#> - Inverse variance method
#> - DerSimonian-Laird estimator for tau^2
#> - Jackson method for confidence interval of tau^2 and tau
### Conduct subgroup analysis assuming common between-study variance in subgroups
mb3s.c <- update(mb3s, tau.common = TRUE)
mb3s.c
#> Number of studies: k = 10
#> Number of observations: o = 625 (o.e = 310, o.c = 315)
#> Number of events: e = 301
#>
#> RR 95%-CI z p-value
#> Common effect model 0.65 [0.55; 0.78] -4.81 < 0.0001
#> Random effects model 0.60 [0.46; 0.79] -3.64 0.0003
#>
#> Quantifying heterogeneity:
#> tau^2 = 0.0915 [0.0000; 0.6662]; tau = 0.3025 [0.0000; 0.8162]
#> I^2 = 52.3% [2.2%; 76.7%]; H = 1.45 [1.01; 2.07]
#>
#> Quantifying residual heterogeneity:
#> tau^2 = 0.1028; tau = 0.3207; I^2 = 52.3% [0.0%; 77.6%]; H = 1.45 [1.00; 2.11]
#>
#> Test of heterogeneity:
#> Q d.f. p-value
#> 18.87 9 0.0263
#>
#> Results for subgroups (common effect model):
#> k RR 95%-CI Q I^2
#> Adequate blinding 3 0.77 [0.58; 1.01] 2.49 19.7%
#> Method unclear 7 0.59 [0.47; 0.74] 14.29 58.0%
#>
#> Test for subgroup differences (common effect model):
#> Q d.f. p-value
#> Between groups 2.09 1 0.1483
#> Within groups 16.79 8 0.0324
#>
#> Results for subgroups (random effects model):
#> k RR 95%-CI tau^2 tau
#> Adequate blinding 3 0.72 [0.43; 1.21] 0.1028 0.3207
#> Method unclear 7 0.56 [0.40; 0.78] 0.1028 0.3207
#>
#> Test for subgroup differences (random effects model):
#> Q d.f. p-value
#> Between groups 0.64 1 0.4245
#> Within groups 16.79 8 0.0324
#>
#> Details on meta-analytical method:
#> - Inverse variance method
#> - DerSimonian-Laird estimator for tau^2
#> (assuming common tau^2 in subgroups)
#> - Jackson method for confidence interval of tau^2 and tau
### Use previous settings
settings.meta(oldset)