Performs the unrelated mean effects model of Dias et al. (2013) that has been refined (Spineli, 2021) and extended to address aggregate binary and continuous missing participant outcome data via the pattern-mixture model (Spineli et al. 2021; Spineli, 2019). This model offers a global evaluation of the plausibility of the consistency assumption in the network.
Arguments
- full
- n_iter
Positive integer specifying the number of Markov chains for the MCMC sampling; an argument of the
jags
function of the R-package R2jags. The default argument is 10000.- n_burnin
Positive integer specifying the number of iterations to discard at the beginning of the MCMC sampling; an argument of the
jags
function of the R-package R2jags. The default argument is 1000.- n_chains
Positive integer specifying the number of chains for the MCMC sampling; an argument of the
jags
function of the R-package R2jags. The default argument is 2.- n_thin
Positive integer specifying the thinning rate for the MCMC sampling; an argument of the
jags
function of the R-package R2jags. The default argument is 1.- inits
A list with the initial values for the parameters; an argument of the
jags
function of the R-package R2jags. The default argument isNULL
, and JAGS generates the initial values.
Value
An R2jags output on the summaries of the posterior distribution, and the Gelman-Rubin convergence diagnostic (Gelman et al., 1992) of the following monitored parameters:
- EM
The summary effect estimate (according to the argument
measure
defined inrun_model
) for each pairwise comparison observed in the network.- dev_o
The deviance contribution of each trial-arm based on the observed outcome.
- hat_par
The fitted outcome at each trial-arm.
- tau
The between-trial standard deviation (assumed common across the observed pairwise comparisons) for the whole network, when a random-effects model has been specified.
- m_tau
The between-trial standard deviation (assumed common across the observed pairwise comparisons) for the subset of multi-arm trials, when a random-effects model has been specified.
The output also includes the following elements:
- leverage_o
The leverage for the observed outcome at each trial-arm.
- sign_dev_o
The sign of the difference between observed and fitted outcome at each trial-arm.
- model_assessment
A data-frame on the measures of model assessment: deviance information criterion, number of effective parameters, and total residual deviance.
- jagsfit
An object of S3 class
jags
with the posterior results on all monitored parameters to be used in themcmc_diagnostics
function.
Furthermore, run_ume
returns a character vector with the pairwise
comparisons observed in the network, obs_comp
, and a character
vector with comparisons between the non-baseline interventions observed in
multi-arm trials only, frail_comp
. Both vectors are used in
ume_plot
function.
Details
run_ume
inherits the arguments data
,
measure
, model
, assumption
, heter_prior
,
mean_misspar
, var_misspar
, and ref
from
run_model
.
This prevents specifying a different Bayesian model from that considered in
run_model
.Therefore, the user needs first to apply
run_model
, and then use run_ume
(see 'Examples').
The run_ume
function also returns the arguments data
,
model
, measure
, assumption
, n_chains
,
n_iter
, n_burnin
, and n_thin
as specified by the user
to be inherited by other relevant functions of the package.
Initially, run_ume
calls the improved_ume
function to
identify the frail comparisons, that is, comparisons between
non-baseline interventions in multi-arm trials not investigated in any
two-arm or multi-arm trial of the network (Spineli, 2021). The 'original'
model of Dias et al. (2013) omits the frail comparisons from the estimation
process. Consequently, the number of estimated summary effects is less
than those obtained by performing separate pairwise meta-analyses
(see run_series_meta
).
For a binary outcome, when measure
is "RR" (relative risk) or "RD"
(risk difference) in run_model
, run_ume
currently
considers the odds ratio as effect measure for being the base-case
effect measure in run_model
for a binary outcome
(see also 'Details' in run_model
).
run_ume
calls the prepare_ume
function which contains
the WinBUGS code as written by Dias et al. (2013) for binomial and normal
likelihood to analyse binary and continuous outcome data, respectively.
prepare_ume
has been extended to incorporate the
pattern-mixture model with informative missingness parameters for binary
and continuous outcome data (see 'Details' in run_model
).
prepare_ume
has also been refined to account for the
multi-arm trials by assigning conditional univariate normal distributions
on the underlying trial-specific effect size of comparisons with the
baseline arm of the multi-arm trial (Spineli, 2021).
run_ume
runs Bayesian unrelated mean effects model in JAGS
.
The progress of the simulation appears on the R console. The model is
updated until convergence using the autojags
function of the R-package
R2jags with 2 updates and
number of iterations and thinning equal to n_iter
and n_thin
,
respectively.
The output of run_ume
is not end-user-ready. The
ume_plot
function uses the output of run_ume
as an S3
object and processes it further to provide an end-user-ready output.
run_ume
can be used only for a network of interventions. In the case
of two interventions, the execution of the function will be stopped and an
error message will be printed on the R console.
References
Dias S, Welton NJ, Sutton AJ, Caldwell DM, Lu G, Ades AE. Evidence synthesis for decision making 4: inconsistency in networks of evidence based on randomized controlled trials. Med Decis Making 2013;33(5):641–56. doi: 10.1177/0272989X12455847
Gelman A, Rubin DB. Inference from iterative simulation using multiple sequences. Stat Sci 1992;7(4):457–72. doi: 10.1214/ss/1177011136
Spineli LM. A Revised Framework to Evaluate the Consistency Assumption Globally in a Network of Interventions. Med Decis Making 2021. doi: 10.1177/0272989X211068005
Spineli LM, Kalyvas C, Papadimitropoulou K. Continuous(ly) missing outcome data in network meta-analysis: a one-stage pattern-mixture model approach. Stat Methods Med Res 2021;30(4):958–75. doi: 10.1177/0962280220983544
Spineli LM. An empirical comparison of Bayesian modelling strategies for missing binary outcome data in network meta-analysis. BMC Med Res Methodol 2019;19(1):86. doi: 10.1186/s12874-019-0731-y
Examples
data("nma.liu2013")
# Read results from 'run_model' (using the default arguments)
res <- readRDS(system.file('extdata/res_liu.rds', package = 'rnmamod'))
# \donttest{
# Run random-effects unrelated mean effects model
# Note: Ideally, set 'n_iter' to 10000 and 'n_burnin' to 1000
run_ume(full = res,
n_chains = 3,
n_iter = 1000,
n_burnin = 100,
n_thin = 1)
#> JAGS generates initial values for the parameters.
#> Running the model ...
#> Compiling model graph
#> Resolving undeclared variables
#> Allocating nodes
#> Graph information:
#> Observed stochastic nodes: 59
#> Unobserved stochastic nodes: 80
#> Total graph size: 1291
#>
#> Initializing model
#>
#> ... Updating the model until convergence
#> $EM
#> mean sd 2.5% 25% 50% 75%
#> EM[2,1] 0.5947222 0.8430483 -1.2005171 0.1575535 0.6004243 1.05460962
#> EM[3,1] 0.1591737 0.6939274 -1.2870231 -0.2418464 0.1722985 0.61293914
#> EM[4,1] 0.7434191 0.5222778 -0.3670261 0.4626603 0.7599240 1.05245281
#> EM[5,1] 1.8308135 0.7776631 0.4469792 1.3403337 1.7779057 2.25997082
#> EM[4,2] -0.4524609 0.9170062 -2.3390133 -0.9695892 -0.4729023 0.09366015
#> EM[6,2] -1.4627077 1.1348636 -3.6967621 -2.1593898 -1.4037489 -0.76798556
#> EM[4,3] 1.1116045 0.9349771 -0.9611786 0.5989397 1.1876997 1.63650496
#> EM[5,4] -1.0862288 1.4764196 -3.8890788 -2.0634799 -1.0827566 -0.16439937
#> 97.5% Rhat n.eff
#> EM[2,1] 2.3449609 1.025794 3000
#> EM[3,1] 1.5272344 1.018473 660
#> EM[4,1] 1.7357237 1.037343 290
#> EM[5,1] 3.5211586 1.028526 100
#> EM[4,2] 1.4544861 1.019178 700
#> EM[6,2] 0.7292316 1.006155 860
#> EM[4,3] 2.9574815 1.003563 880
#> EM[5,4] 1.8527278 1.032855 680
#>
#> $dev_o
#> mean sd 2.5% 25% 50%
#> dev.o[1,1] 0.985983787 1.40490586 0.0010046933 0.11020435 0.4673353
#> dev.o[2,1] 0.919791470 1.26141256 0.0011401185 0.09635134 0.4458006
#> dev.o[3,1] 1.243734559 1.71873099 0.0012670737 0.11642395 0.5507678
#> dev.o[4,1] 0.902589174 1.25667548 0.0011319355 0.08760769 0.4048065
#> dev.o[5,1] 1.006698811 1.44346175 0.0008604505 0.10938977 0.4621310
#> dev.o[6,1] 1.070421380 1.44093882 0.0011437083 0.10125210 0.4994910
#> dev.o[7,1] 0.921456282 1.16639970 0.0011177070 0.11742322 0.4725905
#> dev.o[8,1] 0.005482831 0.07736295 0.0000000000 0.00000000 0.0000000
#> dev.o[9,1] 0.822162593 1.15774276 0.0011721758 0.07967904 0.3703845
#> dev.o[10,1] 0.995261000 1.29888238 0.0013469038 0.11526749 0.4967196
#> dev.o[11,1] 0.820181867 1.19515108 0.0005195380 0.07581729 0.3518669
#> dev.o[1,2] 0.971189005 1.36998635 0.0010034590 0.09472016 0.4497191
#> dev.o[2,2] 1.177886105 1.60599406 0.0009268151 0.11555453 0.5408863
#> dev.o[3,2] 1.004605032 1.45101083 0.0010593475 0.09977836 0.4502062
#> dev.o[4,2] 0.980890916 1.39242521 0.0009036894 0.09561195 0.4340786
#> dev.o[5,2] 1.090904310 1.47893409 0.0013522680 0.10934646 0.4971036
#> dev.o[6,2] 1.163874002 1.44612473 0.0011913232 0.12765310 0.5996290
#> dev.o[7,2] 0.735312682 1.03914465 0.0006481353 0.07482311 0.3313387
#> dev.o[8,2] 0.010169872 0.12656844 0.0000000000 0.00000000 0.0000000
#> dev.o[9,2] 1.012799013 1.39004952 0.0016683229 0.11845876 0.4733460
#> dev.o[10,2] 1.446373021 1.73177053 0.0026215358 0.19383249 0.7968175
#> dev.o[11,2] 1.244043607 1.59050585 0.0015822987 0.15195041 0.6509902
#> dev.o[9,3] 1.249472738 1.59887141 0.0015970499 0.14759694 0.6381660
#> dev.o[10,3] 0.879844676 1.25155523 0.0009062425 0.08849844 0.4069015
#> dev.o[11,3] 1.014732848 1.50559039 0.0008608670 0.09901235 0.4282766
#> 75% 97.5% Rhat n.eff
#> dev.o[1,1] 1.285832e+00 4.98045379 1.003114 1100
#> dev.o[2,1] 1.214172e+00 4.59699544 1.001551 1900
#> dev.o[3,1] 1.684661e+00 6.12757302 1.004924 450
#> dev.o[4,1] 1.224398e+00 4.48964382 1.000894 3000
#> dev.o[5,1] 1.365406e+00 4.74224106 1.003645 3000
#> dev.o[6,1] 1.478914e+00 5.05822200 1.004120 550
#> dev.o[7,1] 1.259554e+00 4.34814218 1.003017 800
#> dev.o[8,1] 4.263256e-14 0.01407587 1.076300 3000
#> dev.o[9,1] 1.125181e+00 4.37895483 1.000747 3000
#> dev.o[10,1] 1.333162e+00 4.80449417 1.016040 180
#> dev.o[11,1] 1.053907e+00 4.37750960 1.009376 230
#> dev.o[1,2] 1.279290e+00 4.82290628 1.002172 1200
#> dev.o[2,2] 1.639259e+00 5.90247930 1.000714 3000
#> dev.o[3,2] 1.282902e+00 5.10187280 1.005282 440
#> dev.o[4,2] 1.308308e+00 5.05717334 1.006832 480
#> dev.o[5,2] 1.508699e+00 5.37195910 1.005915 1000
#> dev.o[6,2] 1.703769e+00 5.14886605 1.003091 770
#> dev.o[7,2] 9.735489e-01 3.78266333 1.000971 3000
#> dev.o[8,2] 1.365574e-13 0.03017531 1.084359 3000
#> dev.o[9,2] 1.357082e+00 5.12471205 1.002709 910
#> dev.o[10,2] 2.144792e+00 6.15383554 1.009327 240
#> dev.o[11,2] 1.720726e+00 5.66070651 1.009214 290
#> dev.o[9,3] 1.733396e+00 5.70532388 1.015835 160
#> dev.o[10,3] 1.148878e+00 4.34282061 1.003916 590
#> dev.o[11,3] 1.289410e+00 5.29948842 1.001818 3000
#>
#> $hat_par
#> mean sd 2.5% 25% 50% 75%
#> hat.par[1,1] 27.084147 4.55952549 18.5294994 23.846531 26.923828 30.170731
#> hat.par[2,1] 2.881072 1.32939458 0.7791472 1.912607 2.713528 3.649450
#> hat.par[3,1] 10.157241 1.23850288 7.1039028 9.499212 10.395638 11.116004
#> hat.par[4,1] 22.965355 2.36809611 17.9821955 21.437424 23.073463 24.637432
#> hat.par[5,1] 8.228573 2.08322009 4.5143358 6.716998 8.168844 9.625220
#> hat.par[6,1] 3.268687 0.96380353 1.4078866 2.558003 3.325323 3.960825
#> hat.par[7,1] 2.545305 1.22578640 0.7568332 1.622818 2.330505 3.292534
#> hat.par[8,1] 11.997320 0.03724392 11.9929641 12.000000 12.000000 12.000000
#> hat.par[9,1] 15.579530 2.49663250 10.8964371 13.862498 15.540176 17.299153
#> hat.par[10,1] 3.295808 1.22988979 1.2781704 2.409504 3.169625 4.039878
#> hat.par[11,1] 4.664264 1.50088021 1.9333652 3.663153 4.583564 5.604451
#> hat.par[1,2] 38.074015 5.03276389 28.6408994 34.564537 38.003453 41.411313
#> hat.par[2,2] 4.168838 1.63817871 1.4829176 2.923775 3.975995 5.212129
#> hat.par[3,2] 7.851603 1.41159676 4.7555186 6.936488 7.972689 8.905724
#> hat.par[4,2] 16.088300 2.45719348 11.0565474 14.491114 16.195306 17.847879
#> hat.par[5,2] 2.837039 1.48162642 0.6385541 1.715516 2.602804 3.738770
#> hat.par[6,2] 3.753185 0.91279125 1.8180245 3.125764 3.819324 4.468994
#> hat.par[7,2] 2.452636 1.14937047 0.6386105 1.587643 2.304123 3.149827
#> hat.par[8,2] 14.995045 0.06024151 14.9849199 15.000000 15.000000 15.000000
#> hat.par[9,2] 16.899899 2.74053658 11.5128012 14.965564 16.981483 18.814750
#> hat.par[10,2] 3.282876 1.31510854 1.0042255 2.319033 3.199081 4.212683
#> hat.par[11,2] 6.821531 1.56366274 3.8836049 5.740580 6.789153 7.888193
#> hat.par[9,3] 21.304858 2.24564732 16.7556198 19.830633 21.406683 22.853312
#> hat.par[10,3] 8.397038 1.35561028 5.4860084 7.530189 8.497482 9.372634
#> hat.par[11,3] 11.442663 1.63033725 7.9861655 10.404622 11.569351 12.587880
#> 97.5% Rhat n.eff
#> hat.par[1,1] 36.347957 1.000973 3000
#> hat.par[2,1] 5.991596 1.016786 170
#> hat.par[3,1] 11.774320 1.007522 1000
#> hat.par[4,1] 27.196344 1.001338 2400
#> hat.par[5,1] 12.338856 1.000509 3000
#> hat.par[6,1] 5.027113 1.010496 210
#> hat.par[7,1] 5.337914 1.011301 190
#> hat.par[8,1] 12.000000 1.076300 3000
#> hat.par[9,1] 20.567990 1.007296 330
#> hat.par[10,1] 6.050334 1.024371 86
#> hat.par[11,1] 7.912445 1.015552 750
#> hat.par[1,2] 48.226456 1.002233 1200
#> hat.par[2,2] 7.823680 1.002778 1000
#> hat.par[3,2] 10.196624 1.005455 2300
#> hat.par[4,2] 20.519165 1.003512 670
#> hat.par[5,2] 6.290378 1.009785 320
#> hat.par[6,2] 5.272194 1.011627 230
#> hat.par[7,2] 5.103067 1.012555 230
#> hat.par[8,2] 15.000000 1.084359 3000
#> hat.par[9,2] 22.167800 1.004334 520
#> hat.par[10,2] 5.989117 1.037229 73
#> hat.par[11,2] 9.901348 1.020325 110
#> hat.par[9,3] 25.462852 1.024125 97
#> hat.par[10,3] 10.733275 1.001403 2200
#> hat.par[11,3] 14.311746 1.015586 150
#>
#> $leverage_o
#> [1] 0.985655246 0.575542703 1.228236532 0.902403918 0.995473428
#> [6] 0.701714463 0.830219835 -0.006215128 0.781263695 0.788079501
#> [11] 0.682552727 0.970981289 0.982845000 0.994710699 0.979692783
#> [16] 1.079835640 0.773237438 0.626952701 0.006214386 0.917458542
#> [21] 0.660572562 0.810647453 0.763715079 0.730488506 0.955714700
#>
#> $sign_dev_o
#> [1] -1 -1 -1 1 -1 1 1 -1 -1 1 -1 -1 1 1 -1 1 -1 -1 -1 -1 -1 1 1 1 -1
#>
#> $tau
#> mean sd 2.5% 25% 50% 75%
#> 0.63923086 0.42951255 0.06153243 0.28004386 0.59011883 0.89141283
#> 97.5% Rhat n.eff
#> 1.64156031 1.18046201 16.00000000
#>
#> $m_tau
#> mean sd 2.5% 25% 50% 75%
#> 6.823073e-01 5.101420e-01 5.061281e-04 2.753894e-01 6.061996e-01 9.971981e-01
#> 97.5% Rhat n.eff
#> 1.881547e+00 1.310647e+00 1.800000e+01
#>
#> $model_assessment
#> DIC pD dev
#> 1 43.39386 19.71799 23.67586
#>
#> $obs_comp
#> [1] "2vs1" "3vs1" "4vs1" "5vs1" "4vs2" "6vs2" "4vs3" "5vs4"
#>
#> $jagsfit
#> Inference for Bugs model at "14", fit using jags,
#> 3 chains, each with 1000 iterations (first 0 discarded)
#> n.sims = 3000 iterations saved
#> mu.vect sd.vect 2.5% 25% 50% 75% 97.5% Rhat n.eff
#> EM[2,1] 0.595 0.843 -1.201 0.158 0.600 1.055 2.345 1.026 3000
#> EM[3,1] 0.159 0.694 -1.287 -0.242 0.172 0.613 1.527 1.018 660
#> EM[4,1] 0.743 0.522 -0.367 0.463 0.760 1.052 1.736 1.037 290
#> EM[5,1] 1.831 0.778 0.447 1.340 1.778 2.260 3.521 1.029 100
#> EM[4,2] -0.452 0.917 -2.339 -0.970 -0.473 0.094 1.454 1.019 700
#> EM[6,2] -1.463 1.135 -3.697 -2.159 -1.404 -0.768 0.729 1.006 860
#> EM[4,3] 1.112 0.935 -0.961 0.599 1.188 1.637 2.957 1.004 880
#> EM[5,4] -1.086 1.476 -3.889 -2.063 -1.083 -0.164 1.853 1.033 680
#> dev.o[1,1] 0.986 1.405 0.001 0.110 0.467 1.286 4.980 1.003 1100
#> dev.o[2,1] 0.920 1.261 0.001 0.096 0.446 1.214 4.597 1.002 1900
#> dev.o[3,1] 1.244 1.719 0.001 0.116 0.551 1.685 6.128 1.005 450
#> dev.o[4,1] 0.903 1.257 0.001 0.088 0.405 1.224 4.490 1.001 3000
#> dev.o[5,1] 1.007 1.443 0.001 0.109 0.462 1.365 4.742 1.004 3000
#> dev.o[6,1] 1.070 1.441 0.001 0.101 0.499 1.479 5.058 1.004 550
#> dev.o[7,1] 0.921 1.166 0.001 0.117 0.473 1.260 4.348 1.003 800
#> dev.o[8,1] 0.005 0.077 0.000 0.000 0.000 0.000 0.014 1.076 3000
#> dev.o[9,1] 0.822 1.158 0.001 0.080 0.370 1.125 4.379 1.001 3000
#> dev.o[10,1] 0.995 1.299 0.001 0.115 0.497 1.333 4.804 1.016 180
#> dev.o[11,1] 0.820 1.195 0.001 0.076 0.352 1.054 4.378 1.009 230
#> dev.o[1,2] 0.971 1.370 0.001 0.095 0.450 1.279 4.823 1.002 1200
#> dev.o[2,2] 1.178 1.606 0.001 0.116 0.541 1.639 5.902 1.001 3000
#> dev.o[3,2] 1.005 1.451 0.001 0.100 0.450 1.283 5.102 1.005 440
#> dev.o[4,2] 0.981 1.392 0.001 0.096 0.434 1.308 5.057 1.007 480
#> dev.o[5,2] 1.091 1.479 0.001 0.109 0.497 1.509 5.372 1.006 1000
#> dev.o[6,2] 1.164 1.446 0.001 0.128 0.600 1.704 5.149 1.003 770
#> dev.o[7,2] 0.735 1.039 0.001 0.075 0.331 0.974 3.783 1.001 3000
#> dev.o[8,2] 0.010 0.127 0.000 0.000 0.000 0.000 0.030 1.084 3000
#> dev.o[9,2] 1.013 1.390 0.002 0.118 0.473 1.357 5.125 1.003 910
#> dev.o[10,2] 1.446 1.732 0.003 0.194 0.797 2.145 6.154 1.009 240
#> dev.o[11,2] 1.244 1.591 0.002 0.152 0.651 1.721 5.661 1.009 290
#> dev.o[9,3] 1.249 1.599 0.002 0.148 0.638 1.733 5.705 1.016 160
#> dev.o[10,3] 0.880 1.252 0.001 0.088 0.407 1.149 4.343 1.004 590
#> dev.o[11,3] 1.015 1.506 0.001 0.099 0.428 1.289 5.299 1.002 3000
#> hat.par[1,1] 27.084 4.560 18.529 23.847 26.924 30.171 36.348 1.001 3000
#> hat.par[2,1] 2.881 1.329 0.779 1.913 2.714 3.649 5.992 1.017 170
#> hat.par[3,1] 10.157 1.239 7.104 9.499 10.396 11.116 11.774 1.008 1000
#> hat.par[4,1] 22.965 2.368 17.982 21.437 23.073 24.637 27.196 1.001 2400
#> hat.par[5,1] 8.229 2.083 4.514 6.717 8.169 9.625 12.339 1.001 3000
#> hat.par[6,1] 3.269 0.964 1.408 2.558 3.325 3.961 5.027 1.010 210
#> hat.par[7,1] 2.545 1.226 0.757 1.623 2.331 3.293 5.338 1.011 190
#> hat.par[8,1] 11.997 0.037 11.993 12.000 12.000 12.000 12.000 1.076 3000
#> hat.par[9,1] 15.580 2.497 10.896 13.862 15.540 17.299 20.568 1.007 330
#> hat.par[10,1] 3.296 1.230 1.278 2.410 3.170 4.040 6.050 1.024 86
#> hat.par[11,1] 4.664 1.501 1.933 3.663 4.584 5.604 7.912 1.016 750
#> hat.par[1,2] 38.074 5.033 28.641 34.565 38.003 41.411 48.226 1.002 1200
#> hat.par[2,2] 4.169 1.638 1.483 2.924 3.976 5.212 7.824 1.003 1000
#> hat.par[3,2] 7.852 1.412 4.756 6.936 7.973 8.906 10.197 1.005 2300
#> hat.par[4,2] 16.088 2.457 11.057 14.491 16.195 17.848 20.519 1.004 670
#> hat.par[5,2] 2.837 1.482 0.639 1.716 2.603 3.739 6.290 1.010 320
#> hat.par[6,2] 3.753 0.913 1.818 3.126 3.819 4.469 5.272 1.012 230
#> hat.par[7,2] 2.453 1.149 0.639 1.588 2.304 3.150 5.103 1.013 230
#> hat.par[8,2] 14.995 0.060 14.985 15.000 15.000 15.000 15.000 1.084 3000
#> hat.par[9,2] 16.900 2.741 11.513 14.966 16.981 18.815 22.168 1.004 520
#> hat.par[10,2] 3.283 1.315 1.004 2.319 3.199 4.213 5.989 1.037 73
#> hat.par[11,2] 6.822 1.564 3.884 5.741 6.789 7.888 9.901 1.020 110
#> hat.par[9,3] 21.305 2.246 16.756 19.831 21.407 22.853 25.463 1.024 97
#> hat.par[10,3] 8.397 1.356 5.486 7.530 8.497 9.373 10.733 1.001 2200
#> hat.par[11,3] 11.443 1.630 7.986 10.405 11.569 12.588 14.312 1.016 150
#> m.tau 0.682 0.510 0.001 0.275 0.606 0.997 1.882 1.311 18
#> resdev.o[1] 1.957 1.965 0.051 0.560 1.348 2.715 7.185 1.005 1100
#> resdev.o[2] 2.098 1.967 0.056 0.687 1.540 2.901 7.251 1.008 730
#> resdev.o[3] 2.248 2.250 0.049 0.615 1.578 3.128 8.212 1.013 160
#> resdev.o[4] 1.883 1.888 0.041 0.557 1.322 2.579 7.080 1.003 870
#> resdev.o[5] 2.098 2.073 0.056 0.588 1.461 2.960 7.671 1.002 2700
#> resdev.o[6] 2.234 1.814 0.098 0.970 1.852 2.959 6.884 1.024 140
#> resdev.o[7] 1.657 1.543 0.054 0.550 1.191 2.271 5.788 1.015 250
#> resdev.o[8] 0.016 0.183 0.000 0.000 0.000 0.000 0.053 1.073 3000
#> resdev.o[9] 3.084 2.359 0.254 1.334 2.515 4.249 9.106 1.017 160
#> resdev.o[10] 3.321 2.424 0.303 1.537 2.809 4.522 9.289 1.010 230
#> resdev.o[11] 3.079 2.402 0.259 1.331 2.527 4.150 9.265 1.001 3000
#> tau 0.639 0.430 0.062 0.280 0.590 0.891 1.642 1.180 16
#> totresdev.o 23.676 6.780 12.521 18.859 22.936 27.671 38.969 1.002 1000
#>
#> For each parameter, n.eff is a crude measure of effective sample size,
#> and Rhat is the potential scale reduction factor (at convergence, Rhat=1).
#>
#> $data
#> study t1 t2 t3 r1 r2 r3 m1 m2 m3 n1 n2 n3
#> 356 Richard, 2012 1 3 4 15 16 23 6 8 4 39 42 34
#> 357 Barone, 2010 1 2 NA 27 38 NA 19 20 NA 152 144 NA
#> 358 Weinbtraub, 2010 1 3 NA 2 5 NA 6 6 NA 27 28 NA
#> 359 Menza, 2009 1 4 5 4 2 9 6 7 5 17 18 17
#> 360 Devos, 2008 1 4 5 4 8 11 0 2 1 16 15 17
#> 361 Antonini, 2006 4 5 NA 10 8 NA 4 4 NA 16 15 NA
#> 362 Barone, 2006 2 4 NA 23 16 NA 1 7 NA 33 34 NA
#> 363 Rektorova, 2003 2 6 NA 8 3 NA 3 2 NA 22 19 NA
#> 364 Leentjens, 2003 1 4 NA 4 3 NA 0 0 NA 6 6 NA
#> 365 Wermuth, 1998 1 4 NA 3 2 NA 2 5 NA 19 18 NA
#> 366 Rabey, 1996 4 5 NA 12 15 NA 8 12 NA 20 27 NA
#>
#> $model
#> [1] "RE"
#>
#> $measure
#> [1] "OR"
#>
#> $assumption
#> [1] "IDE-ARM"
#>
#> $phi
#> NULL
#>
#> $n_chains
#> [1] 3
#>
#> $n_iter
#> [1] 1000
#>
#> $n_burnin
#> [1] 100
#>
#> $n_thin
#> [1] 1
#>
#> $m_tau
#> mean sd 2.5% 25% 50% 75%
#> 6.823073e-01 5.101420e-01 5.061281e-04 2.753894e-01 6.061996e-01 9.971981e-01
#> 97.5% Rhat n.eff
#> 1.881547e+00 1.310647e+00 1.800000e+01
#>
#> $frail_comp
#> [1] "4vs3"
#>
#> attr(,"class")
#> [1] "run_ume"
# }