如何使用metafor包的escalc和rma函数进行单均值荟萃分析？

Question

我知道如何使用meta包的metamean函数执行单一均值荟萃分析，但是，我想使用metafor包的escalc和rma函数来执行此操作。不幸的是，我不知道该怎么做（也不能使用 ChatGPT！）。

请在下面找到一个最小的工作示例：

study <- c("Study 1", "Study 2", "Study 3", "Study 4", "Study 5")
mean <- c(1.2, 1.6, 1.4, 1.5, 1.7)
sd <- c(0.1, 0.2, 0.15, 0.17, 0.18)
n <- c(100, 120, 110, 105, 115)
data <- data.frame(study, mean, sd, n)

data
    study mean   sd   n
1 Study 1  1.2 0.10 100
2 Study 2  1.6 0.20 120
3 Study 3  1.4 0.15 110
4 Study 4  1.5 0.17 105
5 Study 5  1.7 0.18 115

library (meta)

mm <- metamean (n = n,
                  mean = mean,
                  sd = sd,
                  studlab = study, 
                  data = data)

Number of studies: k = 5
Number of observations: o = 550

                       mean           95%-CI
Common effect model  1.4011 [1.3887; 1.4135]
Random effects model 1.4797 [1.3108; 1.6485]

Quantifying heterogeneity:
 tau^2 = 0.0369 [0.0131; 0.3053]; tau = 0.1920 [0.1144; 0.5526]
 I^2 = 99.5% [99.4%; 99.7%]; H = 14.80 [12.93; 16.93]

Test of heterogeneity:
      Q d.f.  p-value
 875.75    4 < 0.0001

Details on meta-analytical method:
- Inverse variance method
- Restricted maximum-likelihood estimator for tau^2
- Q-Profile method for confidence interval of tau^2 and tau
- Untransformed (raw) means

library (metafor)

esc <- escalc (measure = "SMD", 
                m1i = mean, 
                sd1i = sd, 
                n1i = n, 
                slab =  study, 
                data = data)

escalc 中的错误（measure = "SMD", m1i =mean,sd1i = sd,n1i = n,slab = Study,： 无法计算结果。检查是否指定了所有必需的信息 通过适当的参数（即 m1i、m2i、sd1i、sd2i、n1i、n2i（和 di、ti、pi））。

有什么想法吗？

提前感谢您的帮助？

Answer 1

当您只有单组均值时，不要尝试计算标准化均值差 (SMD)。您想使用：

dat <- escalc(measure="MN", mi=mean, sdi=sd, ni=n, slab=study, data=data)
rma(yi, vi, data=dat)