> install.packages("metaSEM")
Installing package into ¡®C:/Users/user/Documents/R/win-library/3.5¡¯
(as ¡®lib¡¯ is unspecified)
trying URL 'https://cran.rstudio.com/bin/windows/contrib/3.5/metaSEM_1.2.0.zip'
Content type 'application/zip' length 1842447 bytes (1.8 MB)
downloaded 1.8 MB

package ¡®metaSEM¡¯ successfully unpacked and MD5 sums checked

The downloaded binary packages are in
	C:\Users\user\AppData\Local\Temp\Rtmpg94FFC\downloaded_packages
> require("metaSEM")
ÇÊ¿äÇÑ ÆÐÅ°Áö¸¦ ·ÎµùÁßÀÔ´Ï´Ù: metaSEM
ÇÊ¿äÇÑ ÆÐÅ°Áö¸¦ ·ÎµùÁßÀÔ´Ï´Ù: OpenMx
"SLSQP" is set as the default optimizer in OpenMx.
mxOption(NULL, "Gradient algorithm") is set at "central".
mxOption(NULL, "Optimality tolerance") is set at "6.3e-14".
mxOption(NULL, "Gradient iterations") is set at "2".
> library(readxl)
> dataset <- read_excel("c:/Users/user/Documents/R/paper6_3/paper6_3 data/masem_data_3_SMPL.xlsx")
> head(dataset)
# A tibble: 6 x 18
  study     N     A1a    A1b   A1c      A1f      A1g    A2a   A2b      A2e      A2f    A4a
  <chr> <dbl>   <dbl>  <dbl> <dbl>    <dbl>    <dbl>  <dbl> <dbl>    <dbl>    <dbl>  <dbl>
1 °­¸¸¿µ ~   204  NA      0.717  0.66  NA       NA      NA        NA  NA       NA      NA    
2 ±Ç¿µ°ü ~   491   0.022  0.596 NA     NA        0.076   0.504    NA  NA        0.0150 NA    
3 ±è¹ÎÈñ ~    88  -0.155 NA     NA      0.0288   0.232  NA        NA  -0.0588  -0.206  NA    
4 ±è¼­±Õ ~   254  NA      0.131 NA      0.084    0.265  NA        NA  NA       NA       0.390
5 ±èÁ¾°© ~   160  NA     NA     NA     -0.03    -0.0817 NA        NA  NA       -0.110  NA    
6 ±èÃá±Ù ~   222  NA     NA     NA     NA       NA       0.424    NA   0.337    0.441  NA    
# ... with 6 more variables: A4d <dbl>, A4e <dbl>, A5c <dbl>, A5d <dbl>, C1a <dbl>, DAT <lgl>
> ## make list of cormatrices (cordat), NA on diagonal
> nvar <- 6
> varnames <- c("RND","CEO","ABS","COM","REL","PER")
> labels <- list(varnames, varnames)
> cordat <- list()
> for (i in 1:nrow(dataset)){	
+  cordat[[i]] <- vec2symMat(as.matrix(dataset[i,3:17]),diag = FALSE)
+  dimnames(cordat[[i]]) <- labels
+  }
> # put NA on diagonal if variable is missing
> for (i in 1:length(cordat)){
+  for (j in 1:nrow(cordat[[i]])){	
+      if (sum(is.na(cordat[[i]][j,]))==nvar-1) 
+      {cordat[[i]][j,j] <- NA}
+    }}
> # put NA on diagonal for variable with least present correlations
> for (i in 1:length(cordat)){
+  for (j in 1:nrow(cordat[[i]])){
+      for (k in 1:nvar){				
+      if (is.na(cordat[[i]][j,k])==TRUE
+          &is.na(cordat[[i]][j,j])!=TRUE
+          &is.na(cordat[[i]][k,k])!=TRUE){
+      
+          if(sum(is.na(cordat[[i]])[j,])>sum(is.na(cordat[[i]])[k,]))
+          {cordat[[i]][k,k] = NA}
+          if(sum(is.na(cordat[[i]])[j,])<=sum(is.na(cordat[[i]])[k,]))
+          {cordat[[i]][j,j] = NA}	
+        }}}}
> head(cordat)
[[1]]
      RND CEO   ABS       COM REL       PER
RND    NA  NA 0.717 0.6600000  NA        NA
CEO    NA  NA    NA        NA  NA        NA
ABS 0.717  NA    NA        NA  NA        NA
COM 0.660  NA    NA        NA  NA 0.6346937
REL    NA  NA    NA        NA  NA        NA
PER    NA  NA    NA 0.6346937  NA 1.0000000

[[2]]
         RND       CEO        ABS COM REL        PER
RND 1.000000 0.0220000 0.59571198  NA  NA 0.07600000
CEO 0.022000 1.0000000 0.50400068  NA  NA 0.01500000
ABS 0.595712 0.5040007 1.00000000  NA  NA 0.02553593
COM       NA        NA         NA  NA  NA         NA
REL       NA        NA         NA  NA  NA         NA
PER 0.076000 0.0150000 0.02553593  NA  NA 1.00000000

[[3]]
            RND         CEO ABS COM         REL        PER
RND  1.00000000 -0.15535388  NA  NA  0.02878428  0.2320000
CEO -0.15535388  1.00000000  NA  NA -0.05880413 -0.2060000
ABS          NA          NA  NA  NA          NA         NA
COM          NA          NA  NA  NA          NA         NA
REL  0.02878428 -0.05880413  NA  NA  1.00000000  0.3485515
PER  0.23200000 -0.20600000  NA  NA  0.34855150  1.0000000

[[4]]
      RND CEO       ABS       COM       REL       PER
RND    NA  NA 0.1310000        NA 0.0840000 0.2650000
CEO    NA  NA        NA        NA        NA        NA
ABS 0.131  NA        NA 0.3900557 0.3840000        NA
COM    NA  NA 0.3900557 1.0000000 0.3445486 0.4955869
REL 0.084  NA 0.3840000 0.3445486 1.0000000 0.2850000
PER 0.265  NA        NA 0.4955869 0.2850000 1.0000000

[[5]]
            RND        CEO       ABS        COM          REL          PER
RND          NA         NA        NA         NA -0.030000000 -0.081667985
CEO          NA         NA        NA         NA           NA -0.110341938
ABS          NA         NA        NA         NA           NA  0.173111535
COM          NA         NA        NA         NA           NA  0.037432028
REL -0.03000000         NA        NA         NA           NA -0.004333652
PER -0.08166799 -0.1103419 0.1731115 0.03743203 -0.004333652  1.000000000

[[6]]
    RND   CEO   ABS   COM   REL   PER
RND  NA    NA    NA    NA    NA    NA
CEO  NA    NA 0.424    NA 0.337 0.441
ABS  NA 0.424    NA    NA 0.470 0.548
COM  NA    NA    NA 1.000 0.445 0.446
REL  NA 0.337 0.470 0.445 1.000 0.534
PER  NA 0.441 0.548 0.446 0.534 1.000

> dataset$N
 [1]  204  491   88  254  160  222 2200  105   72  151  157  143  242  253  133  346  309  140
[19]  242  150  305  238  111   23  183  144  118  567  111  228  421  120  426  919  100  288
[37]  215  104   89  114  127  149  102  103  173
> #### stage 1 
> stage1random <- tssem1(Cov=cordat, n=dataset$N, method="REM", RE.type="Diag")
> summary(stage1random)

Call:
meta(y = ES, v = acovR, RE.constraints = Diag(paste0(RE.startvalues, 
    "*Tau2_", 1:no.es, "_", 1:no.es)), RE.lbound = RE.lbound, 
    I2 = I2, model.name = model.name, suppressWarnings = TRUE, 
    silent = silent, run = run)

95% confidence intervals: z statistic approximation
Coefficients:
               Estimate   Std.Error      lbound      ubound z value  Pr(>|z|)    
Intercept1   1.2396e-01  8.4374e-02 -4.1407e-02  2.8933e-01  1.4692 0.1417770    
Intercept2   5.1578e-01  1.2539e-01  2.7001e-01  7.6155e-01  4.1133 3.901e-05 ***
Intercept3   3.7318e-01  9.0127e-02  1.9653e-01  5.4983e-01  4.1406 3.464e-05 ***
Intercept4   3.1033e-01  6.4448e-02  1.8401e-01  4.3664e-01  4.8152 1.471e-06 ***
Intercept5   3.4502e-01  5.7028e-02  2.3325e-01  4.5679e-01  6.0500 1.449e-09 ***
Intercept6   5.2213e-01  2.9261e-02  4.6478e-01  5.7948e-01 17.8440 < 2.2e-16 ***
Intercept7   3.7959e-01  8.2425e-02  2.1804e-01  5.4114e-01  4.6052 4.120e-06 ***
Intercept8   3.6483e-01  7.7441e-02  2.1305e-01  5.1661e-01  4.7110 2.465e-06 ***
Intercept9   3.2921e-01  9.4050e-02  1.4487e-01  5.1354e-01  3.5003 0.0004647 ***
Intercept10  4.5393e-01  6.0485e-02  3.3538e-01  5.7247e-01  7.5048 6.151e-14 ***
Intercept11  3.9949e-01  3.7611e-02  3.2577e-01  4.7321e-01 10.6216 < 2.2e-16 ***
Intercept12  3.8744e-01  5.0495e-02  2.8847e-01  4.8641e-01  7.6727 1.688e-14 ***
Intercept13  4.9346e-01  4.7210e-02  4.0093e-01  5.8599e-01 10.4526 < 2.2e-16 ***
Intercept14  4.1131e-01  4.7085e-02  3.1903e-01  5.0360e-01  8.7356 < 2.2e-16 ***
Intercept15  4.5677e-01  3.2941e-02  3.9221e-01  5.2134e-01 13.8663 < 2.2e-16 ***
Tau2_1_1     2.3785e-02  2.1301e-02 -1.7965e-02  6.5535e-02  1.1166 0.2641691    
Tau2_2_2     5.7058e-02  4.4676e-02 -3.0506e-02  1.4462e-01  1.2771 0.2015536    
Tau2_3_3     2.7349e-02  2.1812e-02 -1.5403e-02  7.0101e-02  1.2538 0.2099045    
Tau2_4_4     1.3236e-02  1.3020e-02 -1.2282e-02  3.8754e-02  1.0166 0.3093386    
Tau2_5_5     2.3413e-02  1.2984e-02 -2.0356e-03  4.8861e-02  1.8032 0.0713583 .  
Tau2_6_6     3.1973e-08          NA          NA          NA      NA        NA    
Tau2_7_7     1.7326e-02  1.6324e-02 -1.4668e-02  4.9320e-02  1.0614 0.2885035    
Tau2_8_8     2.8081e-02  2.1734e-02 -1.4518e-02  7.0680e-02  1.2920 0.1963544    
Tau2_9_9     7.4326e-02  3.7930e-02 -1.5643e-05  1.4867e-01  1.9596 0.0500482 .  
Tau2_10_10   9.5991e-03  1.0689e-02 -1.1351e-02  3.0549e-02  0.8980 0.3691755    
Tau2_11_11   1.2368e-08          NA          NA          NA      NA        NA    
Tau2_12_12   1.9685e-02  1.0304e-02 -5.1128e-04  3.9881e-02  1.9103 0.0560886 .  
Tau2_13_13   1.2640e-02  9.0057e-03 -5.0108e-03  3.0291e-02  1.4036 0.1604491    
Tau2_14_14   3.2430e-02  1.2160e-02  8.5976e-03  5.6263e-02  2.6670 0.0076527 ** 
Tau2_15_15   1.8115e-02  6.6153e-03  5.1494e-03  3.1081e-02  2.7384 0.0061744 ** 
---
Signif. codes:  0 ¡®***¡¯ 0.001 ¡®**¡¯ 0.01 ¡®*¡¯ 0.05 ¡®.¡¯ 0.1 ¡® ¡¯ 1

Q statistic on the homogeneity of effect sizes: 968.5929
Degrees of freedom of the Q statistic: 97
P value of the Q statistic: 0

Heterogeneity indices (based on the estimated Tau2):
                              Estimate
Intercept1: I2 (Q statistic)    0.8551
Intercept2: I2 (Q statistic)    0.9364
Intercept3: I2 (Q statistic)    0.8744
Intercept4: I2 (Q statistic)    0.7675
Intercept5: I2 (Q statistic)    0.8585
Intercept6: I2 (Q statistic)    0.0000
Intercept7: I2 (Q statistic)    0.8115
Intercept8: I2 (Q statistic)    0.8747
Intercept9: I2 (Q statistic)    0.9501
Intercept10: I2 (Q statistic)   0.7139
Intercept11: I2 (Q statistic)   0.0000
Intercept12: I2 (Q statistic)   0.8378
Intercept13: I2 (Q statistic)   0.7612
Intercept14: I2 (Q statistic)   0.9055
Intercept15: I2 (Q statistic)   0.8312

Number of studies (or clusters): 45
Number of observed statistics: 112
Number of estimated parameters: 30
Degrees of freedom: 82
-2 log likelihood: -92.24089 
OpenMx status1: 6 ("0" or "1": The optimization is considered fine.
Other values may indicate problems.)
Warning message:
In print.summary.meta(x) :
  OpenMx status1 is neither 0 or 1. You are advised to 'rerun' it again.

> # returns models via maTryHard()
> random1_rerun <- rerun(stage1random)
                                                                               
Retry limit reached; solution not found.  Best fit=-92.240917 (started at -92.240886)  (11 attempt(s): 11 valid, 0 errors)

>