Analyses Selection Effects
Selection Model
Hormonal Contraception
Simple Model
Model
Summary
## Family: bernoulli
## Links: mu = probit
## Formula: contraception_hormonal ~ age + net_income + relationship_duration_factor
## Data: data (Number of observations: 1179)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-90% CI u-90% CI Rhat Bulk_ESS
## Intercept 1.00 0.23 0.63 1.37 1.00 5799
## age -0.06 0.01 -0.08 -0.05 1.00 4109
## net_incomeeuro_500_1000 -0.12 0.10 -0.28 0.03 1.00 4105
## net_incomeeuro_1000_2000 0.14 0.13 -0.07 0.36 1.00 3463
## net_incomeeuro_2000_3000 0.12 0.20 -0.20 0.45 1.00 4109
## net_incomeeuro_gt_3000 0.41 0.35 -0.14 1.00 1.00 5466
## net_incomedont_tell -0.00 0.25 -0.42 0.40 1.00 5421
## relationship_duration_factorPartnered_upto12months 0.39 0.11 0.21 0.57 1.00 4734
## relationship_duration_factorPartnered_upto28months 0.56 0.11 0.38 0.75 1.00 4483
## relationship_duration_factorPartnered_upto52months 0.57 0.11 0.38 0.76 1.00 4365
## relationship_duration_factorPartnered_morethan52months 0.74 0.12 0.54 0.94 1.00 4671
## Tail_ESS
## Intercept 2987
## age 3228
## net_incomeeuro_500_1000 3075
## net_incomeeuro_1000_2000 3352
## net_incomeeuro_2000_3000 3459
## net_incomeeuro_gt_3000 3171
## net_incomedont_tell 2810
## relationship_duration_factorPartnered_upto12months 3407
## relationship_duration_factorPartnered_upto28months 3208
## relationship_duration_factorPartnered_upto52months 3327
## relationship_duration_factorPartnered_morethan52months 3341
##
## 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).
Forest Plot for Effect Sizes
m_selection_hc_simple %>%
spread_draws(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto12months,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months) %>%
pivot_longer(cols = c(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto12months,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months),
names_to = "condition",
values_to = "r_condition") %>%
mutate(condition_mean = r_condition,
group = ifelse(condition %contains% "b_relationship_duration_factor",
"Relationship Duration",
ifelse(condition %contains% "b_net_income",
"Income",
NA)),
condition = ifelse(condition == "b_age", "Age",
ifelse(condition == "b_net_incomeeuro_500_1000", "500-1000 Euro",
ifelse(condition == "b_net_incomeeuro_1000_2000", "1000-2000 Euro",
ifelse(condition == "b_net_incomeeuro_2000_3000", "2000-3000 Euro",
ifelse(condition == "b_net_incomeeuro_gt_3000", ">3000 Euro",
ifelse(condition == "b_net_incomedont_tell", "do not tell",
ifelse(condition == "b_relationship_duration_factorPartnered_upto12months",
"0-12 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto28months",
"13-28 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto52months",
"29-52 months",
ifelse(condition == "b_relationship_duration_factorPartnered_morethan52months",
">52 months",
condition)))))))))),
group = ifelse(is.na(group), condition, group),
condition = factor(condition, levels = rev(c("Age",
"500-1000 Euro", "1000-2000 Euro",
"2000-3000 Euro", ">3000 Euro", "do not tell",
"0-12 months", "13-28 months", "29-52 months",
">52 months")))) %>%
ggplot(aes(y = condition, x = condition_mean, color = group)) +
stat_halfeye() +
geom_vline(xintercept = 0, linetype = "dotted", size = 1) +
apatheme +
theme(legend.title = element_blank()) +
labs(x = "Effect Size Estimates", y = "Predictors")
Complex Model
Model
Summary
## Family: bernoulli
## Links: mu = probit
## Formula: contraception_hormonal ~ age + net_income + relationship_duration_factor + education_years + bfi_extra + bfi_neuro + bfi_agree + bfi_consc + bfi_open + religiosity
## Data: data (Number of observations: 1179)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-90% CI u-90% CI Rhat Bulk_ESS
## Intercept 0.20 0.55 -0.71 1.10 1.00 5305
## age -0.06 0.01 -0.08 -0.04 1.00 3417
## net_incomeeuro_500_1000 -0.13 0.10 -0.29 0.03 1.00 3819
## net_incomeeuro_1000_2000 0.13 0.13 -0.09 0.35 1.00 3198
## net_incomeeuro_2000_3000 0.07 0.20 -0.27 0.40 1.00 3459
## net_incomeeuro_gt_3000 0.40 0.34 -0.16 0.96 1.00 4356
## net_incomedont_tell -0.01 0.24 -0.40 0.39 1.00 5075
## relationship_duration_factorPartnered_upto12months 0.38 0.11 0.20 0.57 1.00 4658
## relationship_duration_factorPartnered_upto28months 0.54 0.11 0.36 0.72 1.00 4441
## relationship_duration_factorPartnered_upto52months 0.52 0.11 0.34 0.71 1.00 3901
## relationship_duration_factorPartnered_morethan52months 0.70 0.12 0.51 0.90 1.00 4237
## education_years 0.01 0.01 -0.00 0.03 1.00 6464
## bfi_extra 0.06 0.06 -0.03 0.15 1.00 5838
## bfi_neuro 0.07 0.06 -0.02 0.17 1.00 4854
## bfi_agree 0.07 0.07 -0.05 0.18 1.00 5349
## bfi_consc 0.20 0.06 0.10 0.30 1.00 7477
## bfi_open -0.18 0.06 -0.28 -0.07 1.00 7614
## religiosity -0.04 0.03 -0.09 0.01 1.00 6300
## Tail_ESS
## Intercept 3393
## age 3249
## net_incomeeuro_500_1000 3001
## net_incomeeuro_1000_2000 3363
## net_incomeeuro_2000_3000 3322
## net_incomeeuro_gt_3000 2965
## net_incomedont_tell 3361
## relationship_duration_factorPartnered_upto12months 3385
## relationship_duration_factorPartnered_upto28months 3471
## relationship_duration_factorPartnered_upto52months 3427
## relationship_duration_factorPartnered_morethan52months 3142
## education_years 2953
## bfi_extra 3351
## bfi_neuro 3486
## bfi_agree 3472
## bfi_consc 3112
## bfi_open 3173
## religiosity 3310
##
## 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).
Forest Plot for Effect Sizes
m_selection_hc_complex %>%
spread_draws(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto12months,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months,
b_education_years,
b_bfi_extra, b_bfi_neuro, b_bfi_agree, b_bfi_consc, b_bfi_open,
b_religiosity) %>%
pivot_longer(cols = c(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto12months,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months,
b_education_years,
b_bfi_extra, b_bfi_neuro, b_bfi_agree, b_bfi_consc, b_bfi_open,
b_religiosity),
names_to = "condition",
values_to = "r_condition") %>%
mutate(condition_mean = r_condition,
group = ifelse(condition %contains% "b_relationship_duration_factor",
"Relationship Duration",
ifelse(condition %contains% "b_net_income",
"Income",
NA)),
condition = ifelse(condition == "b_age", "Age",
ifelse(condition == "b_net_incomeeuro_500_1000", "500-1000 Euro",
ifelse(condition == "b_net_incomeeuro_1000_2000", "1000-2000 Euro",
ifelse(condition == "b_net_incomeeuro_2000_3000", "2000-3000 Euro",
ifelse(condition == "b_net_incomeeuro_gt_3000", ">3000 Euro",
ifelse(condition == "b_net_incomedont_tell", "do not tell",
ifelse(condition == "b_relationship_duration_factorPartnered_upto12months",
"0-12 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto28months",
"13-28 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto52months",
"29-52 months",
ifelse(condition == "b_relationship_duration_factorPartnered_morethan52months",
">52 months",
ifelse(condition == "b_education_years", "Years of Education",
ifelse(condition == "b_bfi_extra", "Extraversion",
ifelse(condition == "b_bfi_neuro", "Neuroticism",
ifelse(condition == "b_bfi_agree", "Agreeableness",
ifelse(condition == "b_bfi_consc", "Conscientiousness",
ifelse(condition == "b_bfi_open", "Openness",
ifelse(condition == "b_religiosity", "Religiosity",
condition))))))))))))))))),
group = ifelse(is.na(group), condition, group),
condition = factor(condition, levels = rev(c("Age",
"500-1000 Euro", "1000-2000 Euro",
"2000-3000 Euro", ">3000 Euro", "do not tell",
"0-12 months", "13-28 months", "29-52 months",
">52 months",
"Years of Education",
"Extraversion", "Neuroticism", "Agreeableness",
"Conscientiousness","Openness","Religiosity"))),
group = factor(group, levels = c("Age", "Income", "Relationship Duration",
"Years of Education",
"Extraversion", "Neuroticism", "Agreeableness",
"Conscientiousness","Openness","Religiosity"))) %>%
ggplot(aes(y = condition, x = condition_mean, color = group)) +
stat_halfeye() +
geom_vline(xintercept = 0, linetype = "dotted", size = 1) +
apatheme +
theme(legend.title = element_blank()) +
labs(x = "Effect Size Estimates", y = "Predictors")
Comparison
LooIC first model: 1530.01
LooIC second model: 1523.11
Model Comparisons: The difference between models is -3.45 compared to a standard error of 4.71
## Output of model 'm_selection_hc_simple':
##
## Computed from 4000 by 1179 log-likelihood matrix
##
## Estimate SE
## elpd_loo -765.0 11.2
## p_loo 11.7 0.6
## looic 1530.0 22.5
## ------
## Monte Carlo SE of elpd_loo is 0.0.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Output of model 'm_selection_hc_complex':
##
## Computed from 4000 by 1179 log-likelihood matrix
##
## Estimate SE
## elpd_loo -761.6 12.1
## p_loo 18.9 0.7
## looic 1523.1 24.3
## ------
## Monte Carlo SE of elpd_loo is 0.1.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Model comparisons:
## elpd_diff se_diff
## m_selection_hc_complex 0.0 0.0
## m_selection_hc_simple -3.5 4.7(In)congruent use of hormonal contraceptives
Simple Model
Model
Summary
## Family: bernoulli
## Links: mu = probit
## Formula: congruent_contraception ~ age + net_income + relationship_duration_factor
## Data: data (Number of observations: 774)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-90% CI u-90% CI Rhat Bulk_ESS
## Intercept 0.32 0.29 -0.16 0.79 1.00 4641
## age 0.03 0.01 0.01 0.05 1.00 3638
## net_incomeeuro_500_1000 -0.09 0.12 -0.29 0.11 1.00 3077
## net_incomeeuro_1000_2000 -0.06 0.16 -0.32 0.21 1.00 2805
## net_incomeeuro_2000_3000 -0.49 0.23 -0.86 -0.12 1.00 3333
## net_incomeeuro_gt_3000 -0.54 0.39 -1.18 0.10 1.00 4548
## net_incomedont_tell -0.30 0.30 -0.80 0.21 1.00 4430
## relationship_duration_factorPartnered_upto28months -0.41 0.14 -0.65 -0.17 1.00 3200
## relationship_duration_factorPartnered_upto52months -0.97 0.14 -1.20 -0.73 1.00 2908
## relationship_duration_factorPartnered_morethan52months -1.00 0.15 -1.24 -0.76 1.00 2883
## Tail_ESS
## Intercept 2666
## age 3154
## net_incomeeuro_500_1000 3198
## net_incomeeuro_1000_2000 3175
## net_incomeeuro_2000_3000 3141
## net_incomeeuro_gt_3000 3044
## net_incomedont_tell 3134
## relationship_duration_factorPartnered_upto28months 3480
## relationship_duration_factorPartnered_upto52months 3357
## relationship_duration_factorPartnered_morethan52months 3272
##
## 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).
Forest Plot for Effect Sizes
m_selection_congruent_simple %>%
spread_draws(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months) %>%
pivot_longer(cols = c(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months),
names_to = "condition",
values_to = "r_condition") %>%
mutate(condition_mean = r_condition,
group = ifelse(condition %contains% "b_relationship_duration_factor",
"Relationship Duration",
ifelse(condition %contains% "b_net_income",
"Income",
NA)),
condition = ifelse(condition == "b_age", "Age",
ifelse(condition == "b_net_incomeeuro_500_1000", "500-1000 Euro",
ifelse(condition == "b_net_incomeeuro_1000_2000", "1000-2000 Euro",
ifelse(condition == "b_net_incomeeuro_2000_3000", "2000-3000 Euro",
ifelse(condition == "b_net_incomeeuro_gt_3000", ">3000 Euro",
ifelse(condition == "b_net_incomedont_tell", "do not tell",
ifelse(condition == "b_relationship_duration_factorPartnered_upto12months",
"0-12 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto28months",
"13-28 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto52months",
"29-52 months",
ifelse(condition == "b_relationship_duration_factorPartnered_morethan52months",
">52 months",
condition)))))))))),
group = ifelse(is.na(group), condition, group),
condition = factor(condition, levels = rev(c("Age",
"500-1000 Euro", "1000-2000 Euro",
"2000-3000 Euro", ">3000 Euro", "do not tell",
"13-28 months", "29-52 months",
">52 months")))) %>%
ggplot(aes(y = condition, x = condition_mean, color = group)) +
stat_halfeye() +
geom_vline(xintercept = 0, linetype = "dotted", size = 1) +
apatheme +
theme(legend.title = element_blank()) +
labs(x = "Effect Size Estimates", y = "Predictors")
Complex Model
Model
Summary
## Family: bernoulli
## Links: mu = probit
## Formula: congruent_contraception ~ age + net_income + relationship_duration_factor + education_years + bfi_extra + bfi_neuro + bfi_agree + bfi_consc + bfi_open + religiosity
## Data: data (Number of observations: 774)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error l-90% CI u-90% CI Rhat Bulk_ESS
## Intercept -0.07 0.70 -1.23 1.09 1.00 4393
## age 0.03 0.01 0.01 0.05 1.00 3691
## net_incomeeuro_500_1000 -0.09 0.12 -0.29 0.11 1.00 3177
## net_incomeeuro_1000_2000 -0.07 0.16 -0.33 0.21 1.00 2871
## net_incomeeuro_2000_3000 -0.52 0.22 -0.89 -0.15 1.00 3250
## net_incomeeuro_gt_3000 -0.52 0.37 -1.14 0.10 1.00 3902
## net_incomedont_tell -0.30 0.31 -0.81 0.21 1.00 4380
## relationship_duration_factorPartnered_upto28months -0.43 0.14 -0.66 -0.20 1.00 3234
## relationship_duration_factorPartnered_upto52months -1.01 0.14 -1.25 -0.78 1.00 3126
## relationship_duration_factorPartnered_morethan52months -1.03 0.15 -1.27 -0.78 1.00 3059
## education_years 0.01 0.01 -0.01 0.03 1.00 6073
## bfi_extra 0.02 0.07 -0.09 0.13 1.00 4778
## bfi_neuro 0.08 0.07 -0.04 0.20 1.00 3730
## bfi_agree -0.04 0.09 -0.19 0.10 1.00 4347
## bfi_consc 0.13 0.08 0.00 0.25 1.00 5472
## bfi_open -0.07 0.08 -0.20 0.06 1.00 5426
## religiosity -0.03 0.04 -0.09 0.03 1.00 5400
## Tail_ESS
## Intercept 2895
## age 2883
## net_incomeeuro_500_1000 2953
## net_incomeeuro_1000_2000 3018
## net_incomeeuro_2000_3000 3041
## net_incomeeuro_gt_3000 3104
## net_incomedont_tell 2638
## relationship_duration_factorPartnered_upto28months 3143
## relationship_duration_factorPartnered_upto52months 3161
## relationship_duration_factorPartnered_morethan52months 3084
## education_years 3208
## bfi_extra 3542
## bfi_neuro 2624
## bfi_agree 3080
## bfi_consc 3270
## bfi_open 3681
## religiosity 3126
##
## 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).
Forest Plot for Effect Sizes
m_selection_congruent_complex %>%
spread_draws(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months,
b_education_years,
b_bfi_extra, b_bfi_neuro, b_bfi_agree, b_bfi_consc, b_bfi_open,
b_religiosity) %>%
pivot_longer(cols = c(b_age,
b_net_incomeeuro_500_1000, b_net_incomeeuro_1000_2000,
b_net_incomeeuro_2000_3000, b_net_incomeeuro_gt_3000, b_net_incomedont_tell,
b_relationship_duration_factorPartnered_upto28months,
b_relationship_duration_factorPartnered_upto52months,
b_relationship_duration_factorPartnered_morethan52months,
b_education_years,
b_bfi_extra, b_bfi_neuro, b_bfi_agree, b_bfi_consc, b_bfi_open,
b_religiosity),
names_to = "condition",
values_to = "r_condition") %>%
mutate(condition_mean = r_condition,
group = ifelse(condition %contains% "b_relationship_duration_factor",
"Relationship Duration",
ifelse(condition %contains% "b_net_income",
"Income",
NA)),
condition = ifelse(condition == "b_age", "Age",
ifelse(condition == "b_net_incomeeuro_500_1000", "500-1000 Euro",
ifelse(condition == "b_net_incomeeuro_1000_2000", "1000-2000 Euro",
ifelse(condition == "b_net_incomeeuro_2000_3000", "2000-3000 Euro",
ifelse(condition == "b_net_incomeeuro_gt_3000", ">3000 Euro",
ifelse(condition == "b_net_incomedont_tell", "do not tell",
ifelse(condition == "b_relationship_duration_factorPartnered_upto12months",
"0-12 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto28months",
"13-28 months",
ifelse(condition == "b_relationship_duration_factorPartnered_upto52months",
"29-52 months",
ifelse(condition == "b_relationship_duration_factorPartnered_morethan52months",
">52 months",
ifelse(condition == "b_education_years", "Years of Education",
ifelse(condition == "b_bfi_extra", "Extraversion",
ifelse(condition == "b_bfi_neuro", "Neuroticism",
ifelse(condition == "b_bfi_agree", "Agreeableness",
ifelse(condition == "b_bfi_consc", "Conscientiousness",
ifelse(condition == "b_bfi_open", "Openness",
ifelse(condition == "b_religiosity", "Religiosity",
condition))))))))))))))))),
group = ifelse(is.na(group), condition, group),
condition = factor(condition, levels = rev(c("Age",
"500-1000 Euro", "1000-2000 Euro",
"2000-3000 Euro", ">3000 Euro", "do not tell",
"13-28 months", "29-52 months",
">52 months",
"Years of Education",
"Extraversion", "Neuroticism", "Agreeableness",
"Conscientiousness","Openness","Religiosity"))),
group = factor(group, levels = c("Age", "Income", "Relationship Duration",
"Years of Education",
"Extraversion", "Neuroticism", "Agreeableness",
"Conscientiousness","Openness","Religiosity"))) %>%
ggplot(aes(y = condition, x = condition_mean, color = group)) +
stat_halfeye() +
geom_vline(xintercept = 0, linetype = "dotted", size = 1) +
apatheme +
theme(legend.title = element_blank()) +
labs(x = "Effect Size Estimates", y = "Predictors")
Comparison
LooIC first model: 963.57
LooIC second model: 971.32
Model Comparisons: The difference between models is -3.87 compared to a standard error of 2.65
## Output of model 'm_selection_congruent_simple':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -481.8 10.6
## p_loo 10.4 0.6
## looic 963.6 21.2
## ------
## Monte Carlo SE of elpd_loo is 0.0.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Output of model 'm_selection_congruent_complex':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -485.7 11.1
## p_loo 17.4 0.7
## looic 971.3 22.2
## ------
## Monte Carlo SE of elpd_loo is 0.1.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Model comparisons:
## elpd_diff se_diff
## m_selection_congruent_simple 0.0 0.0
## m_selection_congruent_complex -3.9 2.6(In)congruent use of hormonal contraceptives including current contraceptive method
Simple Model
Model
Summary
## Family: bernoulli
## Links: mu = probit
## Formula: congruent_contraception ~ (age + net_income + relationship_duration_factor) * as.factor(contraception_meeting_partner)
## Data: data (Number of observations: 774)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate
## Intercept -1.92
## age 0.12
## net_incomeeuro_500_1000 0.11
## net_incomeeuro_1000_2000 -0.05
## net_incomeeuro_2000_3000 -0.70
## net_incomeeuro_gt_3000 -0.76
## net_incomedont_tell -0.40
## relationship_duration_factorPartnered_upto28months -0.38
## relationship_duration_factorPartnered_upto52months -0.98
## relationship_duration_factorPartnered_morethan52months -1.19
## as.factorcontraception_meeting_partneryes 4.16
## age:as.factorcontraception_meeting_partneryes -0.16
## net_incomeeuro_500_1000:as.factorcontraception_meeting_partneryes -0.42
## net_incomeeuro_1000_2000:as.factorcontraception_meeting_partneryes -0.12
## net_incomeeuro_2000_3000:as.factorcontraception_meeting_partneryes 0.33
## net_incomeeuro_gt_3000:as.factorcontraception_meeting_partneryes 0.69
## net_incomedont_tell:as.factorcontraception_meeting_partneryes 0.11
## relationship_duration_factorPartnered_upto28months:as.factorcontraception_meeting_partneryes -0.09
## relationship_duration_factorPartnered_upto52months:as.factorcontraception_meeting_partneryes 0.02
## relationship_duration_factorPartnered_morethan52months:as.factorcontraception_meeting_partneryes 0.43
## Est.Error
## Intercept 0.47
## age 0.02
## net_incomeeuro_500_1000 0.18
## net_incomeeuro_1000_2000 0.26
## net_incomeeuro_2000_3000 0.36
## net_incomeeuro_gt_3000 0.52
## net_incomedont_tell 0.44
## relationship_duration_factorPartnered_upto28months 0.19
## relationship_duration_factorPartnered_upto52months 0.19
## relationship_duration_factorPartnered_morethan52months 0.21
## as.factorcontraception_meeting_partneryes 0.63
## age:as.factorcontraception_meeting_partneryes 0.03
## net_incomeeuro_500_1000:as.factorcontraception_meeting_partneryes 0.26
## net_incomeeuro_1000_2000:as.factorcontraception_meeting_partneryes 0.34
## net_incomeeuro_2000_3000:as.factorcontraception_meeting_partneryes 0.48
## net_incomeeuro_gt_3000:as.factorcontraception_meeting_partneryes 0.75
## net_incomedont_tell:as.factorcontraception_meeting_partneryes 0.65
## relationship_duration_factorPartnered_upto28months:as.factorcontraception_meeting_partneryes 0.29
## relationship_duration_factorPartnered_upto52months:as.factorcontraception_meeting_partneryes 0.28
## relationship_duration_factorPartnered_morethan52months:as.factorcontraception_meeting_partneryes 0.30
## l-90% CI
## Intercept -2.70
## age 0.09
## net_incomeeuro_500_1000 -0.19
## net_incomeeuro_1000_2000 -0.47
## net_incomeeuro_2000_3000 -1.28
## net_incomeeuro_gt_3000 -1.60
## net_incomedont_tell -1.12
## relationship_duration_factorPartnered_upto28months -0.70
## relationship_duration_factorPartnered_upto52months -1.28
## relationship_duration_factorPartnered_morethan52months -1.54
## as.factorcontraception_meeting_partneryes 3.17
## age:as.factorcontraception_meeting_partneryes -0.20
## net_incomeeuro_500_1000:as.factorcontraception_meeting_partneryes -0.85
## net_incomeeuro_1000_2000:as.factorcontraception_meeting_partneryes -0.66
## net_incomeeuro_2000_3000:as.factorcontraception_meeting_partneryes -0.45
## net_incomeeuro_gt_3000:as.factorcontraception_meeting_partneryes -0.54
## net_incomedont_tell:as.factorcontraception_meeting_partneryes -0.94
## relationship_duration_factorPartnered_upto28months:as.factorcontraception_meeting_partneryes -0.57
## relationship_duration_factorPartnered_upto52months:as.factorcontraception_meeting_partneryes -0.46
## relationship_duration_factorPartnered_morethan52months:as.factorcontraception_meeting_partneryes -0.08
## u-90% CI
## Intercept -1.15
## age 0.15
## net_incomeeuro_500_1000 0.42
## net_incomeeuro_1000_2000 0.39
## net_incomeeuro_2000_3000 -0.11
## net_incomeeuro_gt_3000 0.12
## net_incomedont_tell 0.33
## relationship_duration_factorPartnered_upto28months -0.08
## relationship_duration_factorPartnered_upto52months -0.67
## relationship_duration_factorPartnered_morethan52months -0.86
## as.factorcontraception_meeting_partneryes 5.20
## age:as.factorcontraception_meeting_partneryes -0.12
## net_incomeeuro_500_1000:as.factorcontraception_meeting_partneryes -0.00
## net_incomeeuro_1000_2000:as.factorcontraception_meeting_partneryes 0.45
## net_incomeeuro_2000_3000:as.factorcontraception_meeting_partneryes 1.13
## net_incomeeuro_gt_3000:as.factorcontraception_meeting_partneryes 1.92
## net_incomedont_tell:as.factorcontraception_meeting_partneryes 1.17
## relationship_duration_factorPartnered_upto28months:as.factorcontraception_meeting_partneryes 0.38
## relationship_duration_factorPartnered_upto52months:as.factorcontraception_meeting_partneryes 0.48
## relationship_duration_factorPartnered_morethan52months:as.factorcontraception_meeting_partneryes 0.92
## Rhat
## Intercept 1.00
## age 1.00
## net_incomeeuro_500_1000 1.00
## net_incomeeuro_1000_2000 1.00
## net_incomeeuro_2000_3000 1.00
## net_incomeeuro_gt_3000 1.00
## net_incomedont_tell 1.00
## relationship_duration_factorPartnered_upto28months 1.00
## relationship_duration_factorPartnered_upto52months 1.00
## relationship_duration_factorPartnered_morethan52months 1.00
## as.factorcontraception_meeting_partneryes 1.00
## age:as.factorcontraception_meeting_partneryes 1.00
## net_incomeeuro_500_1000:as.factorcontraception_meeting_partneryes 1.00
## net_incomeeuro_1000_2000:as.factorcontraception_meeting_partneryes 1.00
## net_incomeeuro_2000_3000:as.factorcontraception_meeting_partneryes 1.00
## net_incomeeuro_gt_3000:as.factorcontraception_meeting_partneryes 1.00
## net_incomedont_tell:as.factorcontraception_meeting_partneryes 1.00
## relationship_duration_factorPartnered_upto28months:as.factorcontraception_meeting_partneryes 1.00
## relationship_duration_factorPartnered_upto52months:as.factorcontraception_meeting_partneryes 1.00
## relationship_duration_factorPartnered_morethan52months:as.factorcontraception_meeting_partneryes 1.00
## Bulk_ESS
## Intercept 2608
## age 1983
## net_incomeeuro_500_1000 1955
## net_incomeeuro_1000_2000 1789
## net_incomeeuro_2000_3000 2116
## net_incomeeuro_gt_3000 2516
## net_incomedont_tell 2655
## relationship_duration_factorPartnered_upto28months 2285
## relationship_duration_factorPartnered_upto52months 2401
## relationship_duration_factorPartnered_morethan52months 2472
## as.factorcontraception_meeting_partneryes 2226
## age:as.factorcontraception_meeting_partneryes 2005
## net_incomeeuro_500_1000:as.factorcontraception_meeting_partneryes 1938
## net_incomeeuro_1000_2000:as.factorcontraception_meeting_partneryes 1848
## net_incomeeuro_2000_3000:as.factorcontraception_meeting_partneryes 2161
## net_incomeeuro_gt_3000:as.factorcontraception_meeting_partneryes 2579
## net_incomedont_tell:as.factorcontraception_meeting_partneryes 2810
## relationship_duration_factorPartnered_upto28months:as.factorcontraception_meeting_partneryes 2124
## relationship_duration_factorPartnered_upto52months:as.factorcontraception_meeting_partneryes 2151
## relationship_duration_factorPartnered_morethan52months:as.factorcontraception_meeting_partneryes 2320
## Tail_ESS
## Intercept 2672
## age 2342
## net_incomeeuro_500_1000 2203
## net_incomeeuro_1000_2000 2414
## net_incomeeuro_2000_3000 2614
## net_incomeeuro_gt_3000 2695
## net_incomedont_tell 2481
## relationship_duration_factorPartnered_upto28months 2955
## relationship_duration_factorPartnered_upto52months 3132
## relationship_duration_factorPartnered_morethan52months 2326
## as.factorcontraception_meeting_partneryes 2474
## age:as.factorcontraception_meeting_partneryes 2195
## net_incomeeuro_500_1000:as.factorcontraception_meeting_partneryes 2620
## net_incomeeuro_1000_2000:as.factorcontraception_meeting_partneryes 2259
## net_incomeeuro_2000_3000:as.factorcontraception_meeting_partneryes 2773
## net_incomeeuro_gt_3000:as.factorcontraception_meeting_partneryes 2964
## net_incomedont_tell:as.factorcontraception_meeting_partneryes 2816
## relationship_duration_factorPartnered_upto28months:as.factorcontraception_meeting_partneryes 2757
## relationship_duration_factorPartnered_upto52months:as.factorcontraception_meeting_partneryes 2965
## relationship_duration_factorPartnered_morethan52months:as.factorcontraception_meeting_partneryes 2566
##
## 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).
Forest Plot for Effect Sizes
Complex Model
Model
m_selection_congruent_complex_includinghc = brm(congruent_contraception ~
(age + net_income + relationship_duration_factor +
education_years +
bfi_extra + bfi_neuro + bfi_agree + bfi_consc + bfi_open +
religiosity) *
contraception_meeting_partner,
data = data,
family = bernoulli("probit"),
inits = "0",
file = "m_selection_congruent_complex_includinghc")Summary
## Family: bernoulli
## Links: mu = probit
## Formula: congruent_contraception ~ (age + net_income + relationship_duration_factor + education_years + bfi_extra + bfi_neuro + bfi_agree + bfi_consc + bfi_open + religiosity) * contraception_meeting_partner
## Data: data (Number of observations: 774)
## Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
## total post-warmup draws = 4000
##
## Population-Level Effects:
## Estimate Est.Error
## Intercept -1.23 1.06
## age 0.12 0.02
## net_incomeeuro_500_1000 0.13 0.18
## net_incomeeuro_1000_2000 -0.01 0.27
## net_incomeeuro_2000_3000 -0.71 0.37
## net_incomeeuro_gt_3000 -0.86 0.55
## net_incomedont_tell -0.42 0.45
## relationship_duration_factorPartnered_upto28months -0.39 0.20
## relationship_duration_factorPartnered_upto52months -1.00 0.21
## relationship_duration_factorPartnered_morethan52months -1.21 0.23
## education_years -0.02 0.02
## bfi_extra 0.04 0.10
## bfi_neuro 0.00 0.11
## bfi_agree -0.30 0.13
## bfi_consc -0.09 0.12
## bfi_open 0.17 0.13
## religiosity 0.03 0.05
## contraception_meeting_partneryes 1.79 1.45
## age:contraception_meeting_partneryes -0.16 0.03
## net_incomeeuro_500_1000:contraception_meeting_partneryes -0.44 0.26
## net_incomeeuro_1000_2000:contraception_meeting_partneryes -0.14 0.35
## net_incomeeuro_2000_3000:contraception_meeting_partneryes 0.45 0.50
## net_incomeeuro_gt_3000:contraception_meeting_partneryes 0.90 0.80
## net_incomedont_tell:contraception_meeting_partneryes 0.27 0.67
## relationship_duration_factorPartnered_upto28months:contraception_meeting_partneryes -0.05 0.30
## relationship_duration_factorPartnered_upto52months:contraception_meeting_partneryes 0.00 0.31
## relationship_duration_factorPartnered_morethan52months:contraception_meeting_partneryes 0.36 0.33
## education_years:contraception_meeting_partneryes 0.03 0.03
## bfi_extra:contraception_meeting_partneryes -0.02 0.14
## bfi_neuro:contraception_meeting_partneryes 0.16 0.16
## bfi_agree:contraception_meeting_partneryes 0.52 0.18
## bfi_consc:contraception_meeting_partneryes 0.38 0.16
## bfi_open:contraception_meeting_partneryes -0.44 0.17
## religiosity:contraception_meeting_partneryes -0.03 0.08
## l-90% CI u-90% CI
## Intercept -3.00 0.50
## age 0.09 0.16
## net_incomeeuro_500_1000 -0.17 0.43
## net_incomeeuro_1000_2000 -0.44 0.44
## net_incomeeuro_2000_3000 -1.33 -0.09
## net_incomeeuro_gt_3000 -1.74 0.04
## net_incomedont_tell -1.15 0.33
## relationship_duration_factorPartnered_upto28months -0.72 -0.05
## relationship_duration_factorPartnered_upto52months -1.35 -0.67
## relationship_duration_factorPartnered_morethan52months -1.58 -0.84
## education_years -0.05 0.02
## bfi_extra -0.12 0.20
## bfi_neuro -0.18 0.17
## bfi_agree -0.52 -0.08
## bfi_consc -0.29 0.11
## bfi_open -0.03 0.39
## religiosity -0.06 0.11
## contraception_meeting_partneryes -0.58 4.17
## age:contraception_meeting_partneryes -0.21 -0.12
## net_incomeeuro_500_1000:contraception_meeting_partneryes -0.87 -0.01
## net_incomeeuro_1000_2000:contraception_meeting_partneryes -0.70 0.43
## net_incomeeuro_2000_3000:contraception_meeting_partneryes -0.36 1.27
## net_incomeeuro_gt_3000:contraception_meeting_partneryes -0.43 2.19
## net_incomedont_tell:contraception_meeting_partneryes -0.81 1.36
## relationship_duration_factorPartnered_upto28months:contraception_meeting_partneryes -0.55 0.43
## relationship_duration_factorPartnered_upto52months:contraception_meeting_partneryes -0.51 0.51
## relationship_duration_factorPartnered_morethan52months:contraception_meeting_partneryes -0.17 0.89
## education_years:contraception_meeting_partneryes -0.01 0.07
## bfi_extra:contraception_meeting_partneryes -0.25 0.21
## bfi_neuro:contraception_meeting_partneryes -0.09 0.42
## bfi_agree:contraception_meeting_partneryes 0.23 0.81
## bfi_consc:contraception_meeting_partneryes 0.12 0.65
## bfi_open:contraception_meeting_partneryes -0.71 -0.17
## religiosity:contraception_meeting_partneryes -0.16 0.09
## Rhat Bulk_ESS
## Intercept 1.00 3298
## age 1.00 2945
## net_incomeeuro_500_1000 1.00 3233
## net_incomeeuro_1000_2000 1.00 2964
## net_incomeeuro_2000_3000 1.00 2990
## net_incomeeuro_gt_3000 1.00 3884
## net_incomedont_tell 1.00 3740
## relationship_duration_factorPartnered_upto28months 1.00 3655
## relationship_duration_factorPartnered_upto52months 1.00 3199
## relationship_duration_factorPartnered_morethan52months 1.00 3183
## education_years 1.00 3151
## bfi_extra 1.00 3863
## bfi_neuro 1.00 3560
## bfi_agree 1.00 3814
## bfi_consc 1.00 4218
## bfi_open 1.00 3678
## religiosity 1.00 4245
## contraception_meeting_partneryes 1.00 3048
## age:contraception_meeting_partneryes 1.00 2707
## net_incomeeuro_500_1000:contraception_meeting_partneryes 1.00 3141
## net_incomeeuro_1000_2000:contraception_meeting_partneryes 1.00 2788
## net_incomeeuro_2000_3000:contraception_meeting_partneryes 1.00 2897
## net_incomeeuro_gt_3000:contraception_meeting_partneryes 1.00 3869
## net_incomedont_tell:contraception_meeting_partneryes 1.00 3671
## relationship_duration_factorPartnered_upto28months:contraception_meeting_partneryes 1.00 3155
## relationship_duration_factorPartnered_upto52months:contraception_meeting_partneryes 1.00 2994
## relationship_duration_factorPartnered_morethan52months:contraception_meeting_partneryes 1.00 2902
## education_years:contraception_meeting_partneryes 1.00 3304
## bfi_extra:contraception_meeting_partneryes 1.00 3804
## bfi_neuro:contraception_meeting_partneryes 1.00 3377
## bfi_agree:contraception_meeting_partneryes 1.00 3708
## bfi_consc:contraception_meeting_partneryes 1.00 3987
## bfi_open:contraception_meeting_partneryes 1.00 3691
## religiosity:contraception_meeting_partneryes 1.00 4063
## Tail_ESS
## Intercept 2892
## age 2654
## net_incomeeuro_500_1000 2904
## net_incomeeuro_1000_2000 2656
## net_incomeeuro_2000_3000 2642
## net_incomeeuro_gt_3000 2798
## net_incomedont_tell 3000
## relationship_duration_factorPartnered_upto28months 2718
## relationship_duration_factorPartnered_upto52months 3061
## relationship_duration_factorPartnered_morethan52months 3070
## education_years 3123
## bfi_extra 3092
## bfi_neuro 2630
## bfi_agree 3029
## bfi_consc 3039
## bfi_open 2958
## religiosity 2874
## contraception_meeting_partneryes 2879
## age:contraception_meeting_partneryes 2960
## net_incomeeuro_500_1000:contraception_meeting_partneryes 3391
## net_incomeeuro_1000_2000:contraception_meeting_partneryes 3165
## net_incomeeuro_2000_3000:contraception_meeting_partneryes 2763
## net_incomeeuro_gt_3000:contraception_meeting_partneryes 2712
## net_incomedont_tell:contraception_meeting_partneryes 2948
## relationship_duration_factorPartnered_upto28months:contraception_meeting_partneryes 2774
## relationship_duration_factorPartnered_upto52months:contraception_meeting_partneryes 2822
## relationship_duration_factorPartnered_morethan52months:contraception_meeting_partneryes 3245
## education_years:contraception_meeting_partneryes 2994
## bfi_extra:contraception_meeting_partneryes 3195
## bfi_neuro:contraception_meeting_partneryes 3264
## bfi_agree:contraception_meeting_partneryes 2764
## bfi_consc:contraception_meeting_partneryes 2967
## bfi_open:contraception_meeting_partneryes 2754
## religiosity:contraception_meeting_partneryes 3085
##
## 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).
Forest Plot for Effect Sizes
Comparison
compare_models = loo(m_selection_congruent_simple_includinghc,
m_selection_congruent_complex_includinghc)LooIC first model: 933.83
LooIC second model: 941.28
Model Comparisons: The difference between models is -3.73 compared to a standard error of 5.42
## Output of model 'm_selection_congruent_simple_includinghc':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -466.9 12.7
## p_loo 22.4 1.7
## looic 933.8 25.4
## ------
## Monte Carlo SE of elpd_loo is 0.1.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Output of model 'm_selection_congruent_complex_includinghc':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -470.6 13.9
## p_loo 37.9 2.1
## looic 941.3 27.8
## ------
## Monte Carlo SE of elpd_loo is 0.1.
##
## Pareto k diagnostic values:
## Count Pct. Min. n_eff
## (-Inf, 0.5] (good) 771 99.6% 1268
## (0.5, 0.7] (ok) 3 0.4% 1243
## (0.7, 1] (bad) 0 0.0% <NA>
## (1, Inf) (very bad) 0 0.0% <NA>
##
## All Pareto k estimates are ok (k < 0.7).
## See help('pareto-k-diagnostic') for details.
##
## Model comparisons:
## elpd_diff se_diff
## m_selection_congruent_simple_includinghc 0.0 0.0
## m_selection_congruent_complex_includinghc -3.7 5.4LooIC first model: 963.57
LooIC second model: 933.83
Model Comparisons: The difference between models is -14.87 compared to a standard error of 7.54
## Output of model 'm_selection_congruent_simple':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -481.8 10.6
## p_loo 10.4 0.6
## looic 963.6 21.2
## ------
## Monte Carlo SE of elpd_loo is 0.0.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Output of model 'm_selection_congruent_simple_includinghc':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -466.9 12.7
## p_loo 22.4 1.7
## looic 933.8 25.4
## ------
## Monte Carlo SE of elpd_loo is 0.1.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Model comparisons:
## elpd_diff se_diff
## m_selection_congruent_simple_includinghc 0.0 0.0
## m_selection_congruent_simple -14.9 7.5LooIC first model: 971.32
LooIC second model: 941.28
Model Comparisons: The difference between models is -15.02 compared to a standard error of 8.74
## Output of model 'm_selection_congruent_complex':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -485.7 11.1
## p_loo 17.4 0.7
## looic 971.3 22.2
## ------
## Monte Carlo SE of elpd_loo is 0.1.
##
## All Pareto k estimates are good (k < 0.5).
## See help('pareto-k-diagnostic') for details.
##
## Output of model 'm_selection_congruent_complex_includinghc':
##
## Computed from 4000 by 774 log-likelihood matrix
##
## Estimate SE
## elpd_loo -470.6 13.9
## p_loo 37.9 2.1
## looic 941.3 27.8
## ------
## Monte Carlo SE of elpd_loo is 0.1.
##
## Pareto k diagnostic values:
## Count Pct. Min. n_eff
## (-Inf, 0.5] (good) 771 99.6% 1268
## (0.5, 0.7] (ok) 3 0.4% 1243
## (0.7, 1] (bad) 0 0.0% <NA>
## (1, Inf) (very bad) 0 0.0% <NA>
##
## All Pareto k estimates are ok (k < 0.7).
## See help('pareto-k-diagnostic') for details.
##
## Model comparisons:
## elpd_diff se_diff
## m_selection_congruent_complex_includinghc 0.0 0.0
## m_selection_congruent_complex -15.0 8.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