Ordinales Modell

Modellübersicht

##  Family: cumulative 
##   Links: mu = probit; disc = log 
## Formula: demun ~ 1 + (1 | nuts2) 
##          disc ~ 1 + (1 | nuts2)
##    Data: cee12 (Number of observations: 6851) 
##   Draws: 3 chains, each with iter = 66000; warmup = 6000; thin = 6;
##          total post-warmup draws = 30000
## 
## Group-Level Effects: 
## ~nuts2 (Number of levels: 26) 
##                    Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept)          0.46      0.15     0.23     0.82 1.00    13936    19980
## sd(disc_Intercept)     0.17      0.03     0.12     0.24 1.00    23100    27361
## 
## Population-Level Effects: 
##                Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept[1]      -5.04      1.43    -8.33    -2.73 1.00    13240    20484
## Intercept[2]      -4.77      1.35    -7.83    -2.59 1.00    13305    20135
## Intercept[3]      -4.16      1.17    -6.83    -2.26 1.00    13271    20368
## Intercept[4]      -3.58      1.01    -5.88    -1.95 1.00    13307    20539
## Intercept[5]      -2.95      0.83    -4.82    -1.60 1.00    13333    20537
## Intercept[6]      -2.27      0.64    -3.72    -1.23 1.00    13419    20465
## Intercept[7]      -1.64      0.46    -2.69    -0.89 1.00    13533    20392
## Intercept[8]      -1.05      0.30    -1.74    -0.56 1.00    13777    20282
## Intercept[9]      -0.34      0.13    -0.64    -0.13 1.00    14806    21036
## Intercept[10]      0.65      0.22     0.31     1.15 1.00    12599    20689
## disc_Intercept    -0.19      0.28    -0.73     0.39 1.00    13176    20167
## 
## Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).

Trace-Plots

Trace-Plot

Autokorrelation-Plots

Autokorrelation-Plot

Posterior-Verteilung

Posterior-Plot

Ordinales Nullmodell

Modellübersicht

## Warning: There were 1 divergent transitions after warmup. Increasing adapt_delta
## above 0.99 may help. See http://mc-stan.org/misc/warnings.html#divergent-
## transitions-after-warmup

##  Family: cumulative 
##   Links: mu = probit; disc = log 
## Formula: demun ~ 1 
##          disc ~ 1
##    Data: cee12 (Number of observations: 6851) 
##   Draws: 3 chains, each with iter = 66000; warmup = 6000; thin = 6;
##          total post-warmup draws = 30000
## 
## Population-Level Effects: 
##                Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept[1]      -4.61      1.34    -7.67    -2.45 1.00    18053    21834
## Intercept[2]      -4.35      1.26    -7.18    -2.31 1.00    18009    21813
## Intercept[3]      -3.79      1.09    -6.25    -2.01 1.00    18014    21149
## Intercept[4]      -3.28      0.94    -5.42    -1.75 1.00    17981    20661
## Intercept[5]      -2.72      0.78    -4.48    -1.45 1.00    18014    21734
## Intercept[6]      -2.12      0.61    -3.49    -1.13 1.00    18026    20811
## Intercept[7]      -1.54      0.44    -2.54    -0.82 1.00    18029    21057
## Intercept[8]      -0.98      0.28    -1.62    -0.52 1.00    18051    21442
## Intercept[9]      -0.30      0.09    -0.50    -0.16 1.00    18391    22025
## Intercept[10]      0.67      0.19     0.35     1.10 1.00    18102    21339
## disc_Intercept    -0.22      0.29    -0.76     0.37 1.00    18033    21329
## 
## Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).

Trace-Plots

Trace-Plot

Autokorrelation-Plots

Autokorrelation-Plot

Posterior-Verteilung

Posterior-Plot

Metrisches Modell

Modellübersicht

##  Family: student 
##   Links: mu = identity; sigma = log; nu = identity 
## Formula: demun ~ 1 + (1 | nuts2) 
##          sigma ~ 1 + (1 | nuts2)
##    Data: cee12 (Number of observations: 6851) 
##   Draws: 3 chains, each with iter = 51000; warmup = 3000; thin = 3;
##          total post-warmup draws = 48000
## 
## Group-Level Effects: 
## ~nuts2 (Number of levels: 26) 
##                     Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## sd(Intercept)           0.47      0.07     0.35     0.64 1.00    17141    27772
## sd(sigma_Intercept)     0.23      0.04     0.17     0.31 1.00    17982    27153
## 
## Population-Level Effects: 
##                 Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept           8.69      0.10     8.50     8.88 1.00    11667    19594
## sigma_Intercept     0.16      0.05     0.07     0.26 1.00    13751    23349
## 
## Family Specific Parameters: 
##    Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## nu     8.07      0.79     6.72     9.80 1.00    46968    46241
## 
## Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).

Trace-Plots

Trace-Plot

Autokorrelation-Plots

Autokorrelation-Plot

Posterior-Verteilung

Posterior-Plot

Metrisches Nullmodell

Modellübersicht

##  Family: student 
##   Links: mu = identity; sigma = log; nu = identity 
## Formula: demun ~ 1 
##          sigma ~ 1
##    Data: cee12 (Number of observations: 6851) 
##   Draws: 3 chains, each with iter = 51000; warmup = 3000; thin = 3;
##          total post-warmup draws = 48000
## 
## Population-Level Effects: 
##                 Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## Intercept           8.65      0.02     8.61     8.69 1.00    35290    41414
## sigma_Intercept     0.26      0.02     0.23     0.29 1.00    32819    39280
## 
## Family Specific Parameters: 
##    Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
## nu     7.37      0.67     6.22     8.82 1.00    31515    37590
## 
## Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
## and Tail_ESS are effective sample size measures, and Rhat is the potential
## scale reduction factor on split chains (at convergence, Rhat = 1).

Trace-Plots

Trace-Plot

Autokorrelation-Plots

Autokorrelation-Plot

Posterior-Verteilung

Posterior-Plot

Copyright:
Benedikt Philipp Kleer, 2022 (Online-Appendix zur Promotion, eingereicht am 14. September 2022, Fachbereich 03, Justus-Liebig-Universität Gießen).