admin管理员组

文章数量:1024016

I would like to compute a meta-analysis in R using the metagen function from the dmetar package, but would like to apply a Freeman-Tukey doublearcsine transformation. When applying the Freeman-Tukey transformation using the argument sm=PFT within the metagen function, I have the following problem:

The confidence intervals of each indivdual study are being reported, as well as a value for tau^2, I^2 and Q, but I receive "NA" as result for the pooled effect size and confidence interval (in my case being a prevalence rate).

This is the code:


SE_proportion <- sqrt(1/(data$sample_size+0.5))
m.phys_ab <- metagen(TE = data$proportion,
                 seTE = SE_proportion,
                 studlab = data$author,
                 data = data,
                 sm = "PFT",
                 fixed = FALSE,
                 random = TRUE,
                 method.tau = "REML",
                 method.random.ci = "HK",
                 title = "Physical abuse")

**This is the result: **

                   ` proportion           95%-CI %W(random)
Study1               0.5146 [0.3569; 0.6709]        3.0
Study2              0.5445 [0.4178; 0.6684]        3.1
....and so on

number of studies: k = 34

                          proportion 95%-CI     t  p-value
Random effects model (HK)         NA        15.42 < 0.0001  #this is the problem

Quantifying heterogeneity:
 tau^2 = 0.0422 [0.0251; 0.0782]; tau = 0.2054 [0.1584; 0.2796]
 I^2 = 93.8% [92.3%; 95.1%]; H = 4.03 [3.60; 4.50]

Test of heterogeneity:
      Q d.f.  p-value
 534.87   33 < 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
- Hartung-Knapp adjustment for random effects model (df = 33)
- Freeman-Tukey double arcsine transformation`

What can I do to receive a result using PFT in metagen?

session info: `

R version 4.4.1 (2024-06-14 ucrt)
Platform: x86_64-w64-mingw32/x64
Running under: Windows 10 x64 (build 19045)

Matrix products: default 

time zone: Europe/Berlin
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] metafor_4.6-0       numDeriv_2016.8-1.1 Matrix_1.7-0        meta_7.0-0         
 [5] metadat_1.2-0       lubridate_1.9.3     forcats_1.0.0       stringr_1.5.1      
 [9] dplyr_1.1.4         purrr_1.0.2         readr_2.1.5         tidyr_1.3.1        
[13] tibble_3.2.1        ggplot2_3.5.1       tidyverse_2.0.0     openxlsx_4.2.7.1   
[17] dmetar_0.1.0        devtools_2.4.5      usethis_3.0.0      `

I would like to compute a meta-analysis in R using the metagen function from the dmetar package, but would like to apply a Freeman-Tukey doublearcsine transformation. When applying the Freeman-Tukey transformation using the argument sm=PFT within the metagen function, I have the following problem:

The confidence intervals of each indivdual study are being reported, as well as a value for tau^2, I^2 and Q, but I receive "NA" as result for the pooled effect size and confidence interval (in my case being a prevalence rate).

This is the code:


SE_proportion <- sqrt(1/(data$sample_size+0.5))
m.phys_ab <- metagen(TE = data$proportion,
                 seTE = SE_proportion,
                 studlab = data$author,
                 data = data,
                 sm = "PFT",
                 fixed = FALSE,
                 random = TRUE,
                 method.tau = "REML",
                 method.random.ci = "HK",
                 title = "Physical abuse")

**This is the result: **

                   ` proportion           95%-CI %W(random)
Study1               0.5146 [0.3569; 0.6709]        3.0
Study2              0.5445 [0.4178; 0.6684]        3.1
....and so on

number of studies: k = 34

                          proportion 95%-CI     t  p-value
Random effects model (HK)         NA        15.42 < 0.0001  #this is the problem

Quantifying heterogeneity:
 tau^2 = 0.0422 [0.0251; 0.0782]; tau = 0.2054 [0.1584; 0.2796]
 I^2 = 93.8% [92.3%; 95.1%]; H = 4.03 [3.60; 4.50]

Test of heterogeneity:
      Q d.f.  p-value
 534.87   33 < 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
- Hartung-Knapp adjustment for random effects model (df = 33)
- Freeman-Tukey double arcsine transformation`

What can I do to receive a result using PFT in metagen?

session info: `

R version 4.4.1 (2024-06-14 ucrt)
Platform: x86_64-w64-mingw32/x64
Running under: Windows 10 x64 (build 19045)

Matrix products: default 

time zone: Europe/Berlin
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] metafor_4.6-0       numDeriv_2016.8-1.1 Matrix_1.7-0        meta_7.0-0         
 [5] metadat_1.2-0       lubridate_1.9.3     forcats_1.0.0       stringr_1.5.1      
 [9] dplyr_1.1.4         purrr_1.0.2         readr_2.1.5         tidyr_1.3.1        
[13] tibble_3.2.1        ggplot2_3.5.1       tidyverse_2.0.0     openxlsx_4.2.7.1   
[17] dmetar_0.1.0        devtools_2.4.5      usethis_3.0.0      `

本文标签： Using FreemanTukey transformation (PFT) in metagen function from dmetar in RStack Overflow

版权声明：本文标题：Using Freeman-Tukey transformation (PFT) in metagen function from dmetar in [R] - Stack Overflow 内容由热心网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：http://it.en369.cn/questions/1745607181a2158793.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。