I'm a researcher in NYC looking for help with the netmeta function (I'm using v. 2.1-0 in order to be compatible with the guide listed here).

我是纽约市的一名研究人员，正在寻求有关netmeta功能的帮助(我使用v2.1-0是为了与这里列出的指南兼容)。

When I run the function netmeta on my data-set with the following arguments (comb.fixed = FALSE, comb.random = TRUE, reference.group = "PLA",) I get this error:

当我使用以下参数在我的数据集上运行函数netmeta时(com.Fixed=False，com.Random=True，Reference.group=“PLA”)，我得到这个错误：

Error: Problems in multi-arm studies!

- Studies with inconsistent treatment estimates: 'Azorin.2013', 'Landbloom.2016', 'McIntyre.2009'
- Study with negative treatment arm variance: 'Azorin.2013'
- Please check original data used as input to netmeta().
- Argument 'tol.multiarm' in netmeta() can be used to relax consistency
  assumption for multi-arm studies (if appropriate).
  In addition: Warning message:
  Matrix inversion resulted in negative variances for multi-arm study 'Azorin.2013'.
  Consider changing argument 'func.inverse', e.g., ginv() from MASS package.

First of all, here is an excerpt of my original data set (Azorin being a multi-arm study, Berwaerts being a single-arm study):

首先，这里摘录了我的原始数据集(Azorin是一项多臂研究，Berwaerts是一项单臂研究)：

Then I calculated the effect sizes using the following formula:

然后，我使用以下公式计算了效果大小：

effect_sizes_YMRS <- effect_sizes(YMRS_09_10, study=studylab, grp1m = grp1m, grp2m = grp2m, 
                                  grp1sd = grp1sd, grp2sd = grp2sd, 
                                  grp1n = grp1n, grp2n = grp2n, fun = "esc_mean_sd")

which I then extracted/transformed resulting in data-set freq_YMRS:

然后对其进行提取/转换，生成数据集freq_ymrs：

Even so when I run the main function netmeta, I still get the errors listed above. I have tried playing around with the tol.multiarm function but to no avail.

即使如此，当我运行主函数netmeta时，我仍然得到上面列出的错误。我试过使用Tol.Multiarm功能，但无济于事。

ymrs.netmeta <- netmeta(TE = es,
                     seTE = se,
                     treat1 = treat1,
                     treat2 = treat2,
                     studlab = study,
                     data = effect_sizes_YMRS,
                     sm = "SMD",
                     comb.fixed = FALSE,
                     comb.random = TRUE,
                     reference.group = "PLA",
                     details.chkmultiarm = TRUE,
                     sep.trts = " vs ",
                     )