{"chapter":3,"r.files":"3.1_OnePredictor.R","stan.files":"kidscore_momhs.stan","stan.obj.output":"kidscore_momhs","model.type":" One predictor","model.eq":"lm(kid_score ~ mom_hs)","reg.type":"lm"}
{"chapter":3,"r.files":"3.1_OnePredictor.R","stan.files":"kidscore_momiq.stan","stan.obj.output":"kidscore_momiq","model.type":" One predictor","model.eq":"lm(kid_score ~ mom_iq)","reg.type":"lm"}
{"chapter":3,"r.files":"3.2_MultiplePredictors.R","stan.files":"kidiq_multi_preds.stan","stan.obj.output":"kidiq_multi_preds","model.type":" Multiple predictors with no interaction","model.eq":"lm(kid_score ~ mom_hs + mom_iq)","reg.type":"lm"}
{"chapter":3,"r.files":"3.3_Interactions.R","stan.files":"kidiq_interaction.stan","stan.obj.output":"kidiq_interaction","model.type":" Multiple predictors with interaction","model.eq":"lm(kid_score ~ mom_hs + mom_iq + mom_hs","reg.type":"lm"}
{"chapter":3,"r.files":"3.4_StatInference.R","stan.files":"kidiq_multi_preds.stan","stan.obj.output":"kidiq_multi_preds","model.type":" Multiple predictors with no interaction","model.eq":"lm(kid_score ~ mom_hs + mom_iq)","reg.type":"lm"}
{"chapter":3,"r.files":"3.5_GraphDisplays.R","stan.files":"kidscore_momiq.stan","stan.obj.output":"stanfit.2","model.type":" One predictor","model.eq":"lm(kid_score ~ mom_iq)","reg.type":"lm"}
{"chapter":3,"r.files":"3.5_GraphDisplays.R","stan.files":"kidiq_multi_preds.stan","stan.obj.output":"stanfit.3","model.type":" Multiple predictors with no interaction","model.eq":"lm(kid_score ~ mom_hs + mom_iq)","reg.type":"lm"}
{"chapter":3,"r.files":"3.5_GraphDisplays.R","stan.files":"kidiq_interaction.stan","stan.obj.output":"stanfit.4","model.type":" Multiple predictors with interaction","model.eq":"lm(kid_score ~ mom_hs + mom_iq + mom_hs","reg.type":"lm"}
{"chapter":3,"r.files":"3.6_Diagnostics.R","stan.files":"kidscore_momiq.stan","stan.obj.output":"kidscore_momiq.sf","model.type":" One predictor","model.eq":"lm(kid_score ~ mom_iq)","reg.type":"lm"}
{"chapter":4,"r.files":"4.1_LinearTransformations.R","stan.files":"earn_height.stan","stan.obj.output":"earn_height","model.type":" A simple regression, raw data","model.eq":"lm(earn ~ height)","reg.type":"lm"}
{"chapter":4,"r.files":"4.2_Centering&Standardizing.R","stan.files":"kidiq_interaction.stan","stan.obj.output":"kidiq_interaction","model.type":" Multiple predictors with interaction, raw data","model.eq":"lm(kid_score ~ mom_hs + mom_iq + mom_hs","reg.type":"lm"}
{"chapter":4,"r.files":"4.2_Centering&Standardizing.R","stan.files":"kidiq_interaction_c.stan","stan.obj.output":"kidiq_interaction_c","model.type":" Centering","model.eq":"lm(kid_score ~ c_mom_hs + c_mom_iq","reg.type":"lm"}
{"chapter":4,"r.files":"4.2_Centering&Standardizing.R","stan.files":"kidiq_interaction_c2.stan","stan.obj.output":"kidiq_interaction_c2","model.type":" Centering based on an understandable reference point","model.eq":"lm(kid_score ~ c2_mom_hs + c2_mom_iq","reg.type":"lm"}
{"chapter":4,"r.files":"4.2_Centering&Standardizing.R","stan.files":"kidiq_interaction_z.stan","stan.obj.output":"kidiq_interaction_z","model.type":" Standardizing","model.eq":"lm(kid_score ~ z_mom_hs + z_mom_iq","reg.type":"lm"}
{"chapter":4,"r.files":"4.4_LogTransformations.R","stan.files":"logearn_height.stan","stan.obj.output":"logearn_height.sf","model.type":" Log transformations","model.eq":"lm(log(earn) ~ height)","reg.type":"lm"}
{"chapter":4,"r.files":"4.4_LogTransformations.R","stan.files":"log10earn_height.stan","stan.obj.output":"log10earn_height.sf","model.type":" Log transformations","model.eq":"lm(log10(earn) ~ height)","reg.type":"lm"}
{"chapter":4,"r.files":"4.4_LogTransformations.R","stan.files":"logearn_height_male.stan","stan.obj.output":"logearn_height_male.sf","model.type":" Log transformations","model.eq":"lm(log(earn) ~ height + male)","reg.type":"lm"}
{"chapter":4,"r.files":"4.4_LogTransformations.R","stan.files":"logearn_logheight.stan","stan.obj.output":"logearn_logheight.sf","model.type":" Log transformations","model.eq":"lm(log(earn) ~ log(height) + male)","reg.type":"lm"}
{"chapter":4,"r.files":"4.5_OtherTransformations.R","stan.files":"kidscore_momwork.stan","stan.obj.output":"kidscore_momwork.sf","model.type":" Discrete predictor","model.eq":"lm(kid_score ~ as.factor(mom_work))","reg.type":"lm"}
{"chapter":4,"r.files":"4.6_RegressionModelsForPrediction.R","stan.files":"mesquite.stan","stan.obj.output":"mesquite.sf","model.type":" Models for prediction","model.eq":"lm(weight ~ diam1 + diam2 + canopy_height + total_height","reg.type":"lm"}
{"chapter":4,"r.files":"4.6_RegressionModelsForPrediction.R","stan.files":"mesquite_log.stan","stan.obj.output":"mesquite_log.sf","model.type":" Models for prediction","model.eq":"lm(log(weight) ~ log(diam1) + log(diam2)","reg.type":"lm"}
{"chapter":4,"r.files":"4.6_RegressionModelsForPrediction.R","stan.files":"mesquite_volume.stan","stan.obj.output":"mesquite_volume.sf","model.type":" Models for prediction","model.eq":"lm(log(weight) ~ log(canopy_volume))","reg.type":"lm"}
{"chapter":4,"r.files":"4.6_RegressionModelsForPrediction.R","stan.files":"mesquite_vas.stan","stan.obj.output":"mesquite_vas.sf","model.type":" Models for prediction","model.eq":"lm(log(weight) ~ log(canopy_volume) + log(canopy_area)","reg.type":"lm"}
{"chapter":4,"r.files":"4.6_RegressionModelsForPrediction.R","stan.files":"mesquite_va.stan","stan.obj.output":"mesquite_va.sf","model.type":" Models for prediction","model.eq":"lm(log(weight) ~ log(canopy_volume)","reg.type":"lm"}
{"chapter":4,"r.files":"4.6_RegressionModelsForPrediction.R","stan.files":"mesquite_vash.stan","stan.obj.output":"mesquite_vash.sf","model.type":" Models for prediction","model.eq":"lm(log(weight) ~ log(canopy_volume) + log(canopy_area)","reg.type":"lm"}
{"chapter":5,"r.files":"5.1_LogisticRegressionWithOnePredictor.R","stan.files":"nes_logit.stan","stan.obj.output":"nes_logit.sf","model.type":" One predictor","model.eq":"glm(vote ~ income, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":5,"r.files":"5.2_InterpretingLogisticRegressionCoef.R","stan.files":"nes_logit.stan","stan.obj.output":"sf","model.type":" One predictor","model.eq":"glm(vote ~ income, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":5,"r.files":"5.4_LogisticRegressionWellsinBangladesh.R","stan.files":"wells_dist.stan","stan.obj.output":"wells_dist.sf","model.type":" One predictor","model.eq":"glm(switched ~ dist, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":5,"r.files":"5.4_LogisticRegressionWellsinBangladesh.R","stan.files":"wells_dist100.stan","stan.obj.output":"wells_dist100.sf","model.type":" One predictor","model.eq":"glm(switched ~ dist/100, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":5,"r.files":"5.4_LogisticRegressionWellsinBangladesh.R","stan.files":"wells_d100ars.stan","stan.obj.output":"wells_d100ars.sf","model.type":" Multiple predictors with no interaction","model.eq":"glm(switched ~ dist/100 + arsenic, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":5,"r.files":"5.5_LogisticRegressionWithInteractions.R","stan.files":"wells_interaction.stan","stan.obj.output":"wells_interaction.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ dist/100 + arsenic + dist/100","reg.type":"glm"}
{"chapter":5,"r.files":"5.5_LogisticRegressionWithInteractions.R","stan.files":"wells_interaction_c.stan","stan.obj.output":"wells_interaction_c.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ c_dist100 + c_arsenic","reg.type":"glm"}
{"chapter":5,"r.files":"5.5_LogisticRegressionWithInteractions.R","stan.files":"wells_daae_c.stan","stan.obj.output":"wells_daae_c.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ c_dist100 + c_arsenic + c_dist100","reg.type":"glm"}
{"chapter":5,"r.files":"5.5_LogisticRegressionWithInteractions.R","stan.files":"wells_dae_c.stan","stan.obj.output":"wells_dae_c.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ c_dist100 + c_arsenic + c_dist100","reg.type":"glm"}
{"chapter":5,"r.files":"5.5_LogisticRegressionWithInteractions.R","stan.files":"wells_dae_inter_c.stan","stan.obj.output":"wells_dae_inter_c.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ c_dist100 + c_arsenic + c_educ4","reg.type":"glm"}
{"chapter":5,"r.files":"5.6_EvaluatingCheckingComparing.R","stan.files":"wells_predicted.stan","stan.obj.output":"wells_predicted.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ c_dist100 + c_arsenic + c_educ4","reg.type":"glm"}
{"chapter":5,"r.files":"5.6_EvaluatingCheckingComparing.R","stan.files":"wells_predicted_log.stan","stan.obj.output":"wells_predicted_log.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ c_dist100 + c_log_arsenic + c_educ4","reg.type":"glm"}
{"chapter":5,"r.files":"5.7_AveragePredictiveComparisons.R","stan.files":"wells_dae.stan","stan.obj.output":"wells_dae.sf","model.type":" Multiple predictors with no interaction","model.eq":"glm(switched ~ dist/100 + arsenic + educ/4,","reg.type":"glm"}
{"chapter":5,"r.files":"5.7_AveragePredictiveComparisons.R","stan.files":"wells_dae_inter.stan","stan.obj.output":"wells_dae_inter.sf","model.type":" Multiple predictors with interction","model.eq":"glm(switched ~ dist/100 + arsenic + educ/4","reg.type":"glm"}
{"chapter":5,"r.files":"5.8_IdentifiabilityAndSeparation.R","stan.files":"separation.stan","stan.obj.output":"separation.sf","model.type":" One predictor","model.eq":"glm(y ~ x, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":6,"r.files":"6.4_ProbitRegression.R","stan.files":"wells_probit.stan","stan.obj.output":"wells_probit.sf1","model.type":" One predictor","model.eq":"glm(switc ~ dist100, family=binomial(link=\"probit\"))","reg.type":"glm"}
{"chapter":6,"r.files":"6.7_MoreComplexGLM.R","stan.files":"earnings1.stan","stan.obj.output":"earnings1.sf1","model.type":" Multiple predictors with no interaction","model.eq":"glm(earn_pos ~ height + male, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":6,"r.files":"6.7_MoreComplexGLM.R","stan.files":"earnings2.stan","stan.obj.output":"earnings2.sf1","model.type":" Log transformations","model.eq":"lm(log(earnings) ~ height + male)","reg.type":"lm"}
{"chapter":6,"r.files":"6.8_ConstructiveChoiceModels.R","stan.files":"wells_logit.stan","stan.obj.output":"wells_logit.sf1","model.type":" One predictor","model.eq":"glm(switc ~ dist100, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":7,"r.files":"7.3_SimulationForNonLinearPredictions.R","stan.files":"congress.stan","stan.obj.output":"congress.sf1","model.type":" Multiple predictors with no interaction","model.eq":"lm(vote_88 ~ vote_86 + incumbency_88)","reg.type":"lm"}
{"chapter":7,"r.files":"7.4_PredictiveSimulationForGLM.R","stan.files":"wells.stan","stan.obj.output":"wells.sf1","model.type":" One predictor","model.eq":"glm(switc ~ dist, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":7,"r.files":"7.4_PredictiveSimulationForGLM.R","stan.files":"earnings1.stan","stan.obj.output":"earnings1.sf1","model.type":" Multiple predictors with no interaction","model.eq":"glm(earn_pos ~ height + male, family=binomial(link=\"logit\"))","reg.type":"glm"}
{"chapter":7,"r.files":"7.4_PredictiveSimulationForGLM.R","stan.files":"earnings2.stan","stan.obj.output":"earnings2.sf1","model.type":" Log transformations","model.eq":"lm(log(earnings) ~ height + male)","reg.type":"lm"}
{"chapter":8,"r.files":"8.2_FakeDataSimulationToUnderstandResidualPlots.R","stan.files":"grades.stan","stan.obj.output":"grades.sf1","model.type":" One predictor","model.eq":"lm(final ~ midterm)","reg.type":"lm"}
{"chapter":8,"r.files":"8.3_SimulatingFromTheFittedModel.R","stan.files":"lightspeed.stan","stan.obj.output":"lightspeed.sf1","model.type":" Zero predictors","model.eq":"lm(y ~ 1)","reg.type":"lm"}
{"chapter":8,"r.files":"8.3_SimulatingFromTheFittedModel.R","stan.files":"roaches.stan","stan.obj.output":"roaches.sf1","model.type":" Poisson regression with exposure","model.eq":"glm (y ~ roach1 + treatment + senior, family=poisson,","reg.type":"glm"}
{"chapter":8,"r.files":"8.3_SimulatingFromTheFittedModel.R","stan.files":"roaches_overdispersion.stan","stan.obj.output":"roaches_overdispersion.sf1","model.type":" Poisson overdispersion regression","model.eq":"glm(y ~ roach1 + treatment + senior,","reg.type":"glm"}
{"chapter":8,"r.files":"8.4_PredictiveSimulationToCheckFitOfTimeSeriesModels.R","stan.files":"unemployment.stan","stan.obj.output":"unemployment.sf1","model.type":" One predictor","model.eq":"lm(y ~ y_lag)","reg.type":"lm"}
{"chapter":9,"r.files":"9.3_RandomizedExperiments.R","stan.files":"electric_tr.stan","stan.obj.output":"sf.1","model.type":" One predictor","model.eq":"lm(post_test ~ treatment)","reg.type":"lm"}
{"chapter":9,"r.files":"9.3_RandomizedExperiments.R","stan.files":"electric_trpre.stan","stan.obj.output":"sf.2","model.type":" Multiple predictors without interaction","model.eq":"lm(post_test ~ treatment + pre_test)","reg.type":"lm"}
{"chapter":9,"r.files":"9.4_TreatmentInteractionsAndPoststratification.R","stan.files":"electric_tr.stan","stan.obj.output":"electric_tr.sf","model.type":" One predictor","model.eq":"lm(post_test ~ treatment)","reg.type":"lm"}
{"chapter":9,"r.files":"9.4_TreatmentInteractionsAndPoststratification.R","stan.files":"electric_trpre.stan","stan.obj.output":"electric_trpre.sf","model.type":" Multiple predictors without interaction","model.eq":"lm(post_test ~ treatment + pre_test)","reg.type":"lm"}
{"chapter":9,"r.files":"9.4_TreatmentInteractionsAndPoststratification.R","stan.files":"electric_inter.stan","stan.obj.output":"electric_inter.sf","model.type":" Multiple predictors with interaction","model.eq":"lm(post_test ~ treatment + pre_test + treatment","reg.type":"lm"}
{"chapter":9,"r.files":"9.4_TreatmentInteractionsAndPoststratification.R","stan.files":"electric_inter.stan","stan.obj.output":"sf","model.type":" Multiple predictors with interaction","model.eq":"lm(post_test ~ treatment + pre_test + treatment","reg.type":"lm"}
{"chapter":9,"r.files":"9.5_ObservationalStudies.R","stan.files":"electric_supp.stan","stan.obj.output":"sf","model.type":" Multiple predictors without interaction","model.eq":"lm(post_test ~ supp + pre_test)","reg.type":"lm"}
{"chapter":10,"r.files":"10.4_LackOfOverlapWhenTreat.AssignmentIsUnknown.R","stan.files":"ideo_two_pred.stan","stan.obj.output":"ideo_two_pred.sf1","model.type":" Multiple predictors without interaction","model.eq":"lm(score1 ~ party + x)","reg.type":"lm"}
{"chapter":10,"r.files":"10.4_LackOfOverlapWhenTreat.AssignmentIsUnknown.R","stan.files":"ideo_two_pred.stan","stan.obj.output":"ideo_two_pred.sf2","model.type":" Multiple predictors without interaction","model.eq":"lm(score1 ~ party + x)","reg.type":"lm"}
{"chapter":10,"r.files":"10.4_LackOfOverlapWhenTreat.AssignmentIsUnknown.R","stan.files":"ideo_interactions.stan","stan.obj.output":"ideo_interactions.sf1","model.type":" Multiple predictors with interaction","model.eq":"lm(score1 ~ party + x + party","reg.type":"lm"}
{"chapter":10,"r.files":"10.4_LackOfOverlapWhenTreat.AssignmentIsUnknown.R","stan.files":"ideo_reparam.stan","stan.obj.output":"ideo_reparam.sf1","model.type":" Multiple predictors without interaction","model.eq":"lm(score1 ~ party + z1 + z2)","reg.type":"lm"}
{"chapter":10,"r.files":"10.5_CasualEffectsUsingIV.R","stan.files":"sesame_one_pred_a.stan","stan.obj.output":"sesame_one_pred_a.sf1","model.type":" One predictor","model.eq":"lm(watched ~ encouraged)","reg.type":"lm"}
{"chapter":10,"r.files":"10.5_CasualEffectsUsingIV.R","stan.files":"sesame_one_pred_a.stan","stan.obj.output":"sesame_one_pred_b.sf1","model.type":" One predictor","model.eq":"lm(watched ~ encouraged)","reg.type":"lm"}
{"chapter":10,"r.files":"10.6_IVinaRegressionFramework.R","stan.files":"sesame_one_pred_a.stan","stan.obj.output":"sesame_one_pred_2a.sf1","model.type":" One predictor","model.eq":"lm(watched ~ encouraged)","reg.type":"lm"}
{"chapter":10,"r.files":"10.6_IVinaRegressionFramework.R","stan.files":"sesame_one_pred_a.stan","stan.obj.output":"sesame_one_pred_2b.sf1","model.type":" One predictor","model.eq":"lm(watched ~ encouraged)","reg.type":"lm"}
{"chapter":12,"r.files":"12.2_PartialPoolingWithNoPredictors.R","stan.files":"radon_intercept.stan","stan.obj.output":"radon_intercept.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ 1 + (1 | county))","reg.type":"lmer"}
{"chapter":12,"r.files":"12.3_PartialPoolingWithPredictors.R","stan.files":"radon_complete_pool.stan","stan.obj.output":"radon_complete_pool.sf1","model.type":" One predictor","model.eq":"lm(y ~ x)","reg.type":"lm"}
{"chapter":12,"r.files":"12.3_PartialPoolingWithPredictors.R","stan.files":"radon_no_pool.stan","stan.obj.output":"radon_no_pool.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ x + (1 | county))","reg.type":"lmer"}
{"chapter":12,"r.files":"12.4_FittingMLMinR.R","stan.files":"radon_intercept.stan","stan.obj.output":"radon_intercept.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ 1 + (1 | county))","reg.type":"lmer"}
{"chapter":12,"r.files":"12.4_FittingMLMinR.R","stan.files":"radon_no_pool.stan","stan.obj.output":"radon_no_pool.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ x + (1 | county))","reg.type":"lmer"}
{"chapter":12,"r.files":"12.8_Prediction.R","stan.files":"radon_group.stan","stan.obj.output":"#radon_group.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ x + u + (1 | county))","reg.type":"lmer"}
{"chapter":13,"r.files":"13.1_VaryingIntercepts&Slopes.R","stan.files":"radon_vary_si.stan","stan.obj.output":"radon_vary_si.sf1","model.type":" Multilevel model with varying slope and intercept","model.eq":"lmer(y ~ 1 + (1 + x | county))","reg.type":"lmer"}
{"chapter":13,"r.files":"13.1_VaryingIntercepts&Slopes.R","stan.files":"y_x.stan","stan.obj.output":"radon_no_pool.sf1","model.type":" One predictor","model.eq":"lm(y ~ x)","reg.type":"lm"}
{"chapter":13,"r.files":"13.1_VaryingIntercepts&Slopes.R","stan.files":"y_x.stan","stan.obj.output":"radon_complete_pool.sf1","model.type":" One predictor","model.eq":"lm(y ~ x)","reg.type":"lm"}
{"chapter":13,"r.files":"13.1_VaryingIntercepts&Slopes.R","stan.files":"radon_inter_vary.stan","stan.obj.output":"radon_inter_vary.sf1","model.type":" Multilevel model with varying slope and intercept","model.eq":"lmer(y ~ u + u","reg.type":"lmer"}
{"chapter":13,"r.files":"13.4_UnderstandingCorrelationsBetweenIntercepts&Slopes.R","stan.files":"earnings_vary_si.stan","stan.obj.output":"earnings_vary_si.sf1","model.type":" Multilevel model with varying slope and intercept","model.eq":"lmer(log(earn) ~ 1 + (1 + height | eth))","reg.type":"lmer"}
{"chapter":13,"r.files":"13.4_UnderstandingCorrelationsBetweenIntercepts&Slopes.R","stan.files":"earnings_vary_si.stan","stan.obj.output":"earnings_vary_si.sf2","model.type":" Multilevel model with varying slope and intercept","model.eq":"lmer(log(earn) ~ 1 + (1 + height | eth))","reg.type":"lmer"}
{"chapter":13,"r.files":"13.5_Non-NestedModels.R","stan.files":"pilots.stan","stan.obj.output":"pilots.sf1","model.type":" Multilevel model with several group level predictors","model.eq":"lmer(y ~ 1 + (1 | group) + (1 | scenario))","reg.type":"lmer"}
{"chapter":13,"r.files":"13.5_Non-NestedModels.R","stan.files":"earnings_latin_square.stan","stan.obj.output":"earnings_latin_square.sf1","model.type":" Multilevel model with several group level predictors","model.eq":"lmer(y ~ 1 + (1 + x | eth) + (1 + x | age)","reg.type":"lmer"}
{"chapter":14,"r.files":"14.1_State-LevelOpinionsFromNationalPolls.R","stan.files":"election88.stan","stan.obj.output":"election88.sf1","model.type":" Multilevel model with varying intercept","model.eq":"glmer(y ~ black + female + (1 | state), family=binomial(link=\"logit\"))","reg.type":"glmer"}
{"chapter":14,"r.files":"14.1_State-LevelOpinionsFromNationalPolls.R","stan.files":"election88_full.stan","stan.obj.output":"election88_full.sf1","model.type":" Multilevel model with several group level predictors","model.eq":"glmer(y ~ black + female + v_prev_full + (1 | age) + (1 | age_edu)","reg.type":"glmer"}
{"chapter":19,"r.files":"19.4_RedundantParameters&IntentionallyNonidentifiableModels.R","stan.files":"radon.stan","stan.obj.output":"radon.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ 1 + (1 | county))","reg.type":"lmer"}
{"chapter":19,"r.files":"19.4_RedundantParameters&IntentionallyNonidentifiableModels.R","stan.files":"radon_redundant.stan","stan.obj.output":"radon_redundant.sf1","model.type":" Multilevel model with redundant parameterization","model.eq":"lmer(y ~ 1 + (1 | county))","reg.type":"lmer"}
{"chapter":19,"r.files":"19.4_RedundantParameters&IntentionallyNonidentifiableModels.R","stan.files":"pilots.stan","stan.obj.output":"pilots.sf1","model.type":" Multilevel model with several group level predictors","model.eq":"lmer(y ~1 + (1 | treatment) + (1 | airport))","reg.type":"lmer"}
{"chapter":19,"r.files":"19.4_RedundantParameters&IntentionallyNonidentifiableModels.R","stan.files":"election88.stan","stan.obj.output":"election88.sf1","model.type":" Multilevel model with varying intercept","model.eq":"glmer(y ~ black + female + female","reg.type":"glmer"}
{"chapter":19,"r.files":"19.5_ParameterExpansion.R","stan.files":"pilots_expansion.stan","stan.obj.output":"pilots_expansion.sf1","model.type":" Multilevel model with parameter expansion","model.eq":"lmer(y ~ 1 + (1 | treatment) + (1 | airport))","reg.type":"lmer"}
{"chapter":19,"r.files":"19.5_ParameterExpansion.R","stan.files":"election88_expansion.stan","stan.obj.output":"election88_expansion.sf1","model.type":" Multilevel model with parameter expansion","model.eq":"glmer(y ~ black + female + female","reg.type":"glmer"}
{"chapter":20,"r.files":"20.5_MultilevelPowerCalculationUsingFake-DataSimulation.R","stan.files":"hiv.stan","stan.obj.output":"hiv.sf1","model.type":" Multilevel model with varying intercept and slope","model.eq":"lmer(y ~ 1 + (1 + time | person))","reg.type":"lmer"}
{"chapter":20,"r.files":"20.5_MultilevelPowerCalculationUsingFake-DataSimulation.R","stan.files":"hiv_inter.stan","stan.obj.output":"hiv.sf2","model.type":" Multilevel model with group level predictors and interaction","model.eq":"lmer(y ~ time","reg.type":"lmer"}
{"chapter":21,"r.files":"21.6_SummarizingtheAmmountofPartialPooling.R","stan.files":"radon_vary_intercept_a.stan","stan.obj.output":"radon_vary_intercept_a.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ x + (1 | county))","reg.type":"lmer"}
{"chapter":21,"r.files":"21.6_SummarizingtheAmmountofPartialPooling.R","stan.files":"radon_vary_intercept_b.stan","stan.obj.output":"radon_vary_intercept_b.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ x + (1 | county))","reg.type":"lmer"}
{"chapter":21,"r.files":"21.7_AddingAPredictorCanIncreaseResidualVariance.R","stan.files":"radon_vary_intercept_nofloor.stan","stan.obj.output":"radon_vary_intercept_nofloor.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ u + (1 | county))","reg.type":"lmer"}
{"chapter":21,"r.files":"21.7_AddingAPredictorCanIncreaseResidualVariance.R","stan.files":"radon_vary_intercept_floor.stan","stan.obj.output":"radon_vary_intercept_floor.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ u + x + (1 | county))","reg.type":"lmer"}
{"chapter":21,"r.files":"21.7_AddingAPredictorCanIncreaseResidualVariance.R","stan.files":"radon_vary_intercept_floor2.stan","stan.obj.output":"radon_vary_intercept_floor2.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ u + x + x_mean + (1 | county))","reg.type":"lmer"}
{"chapter":22,"r.files":"22.4_DoingANOVUsingMLM.R","stan.files":"anova_radon_nopred.stan","stan.obj.output":"anova_radon_nopred.sf1","model.type":" Multilevel model with varying intercept","model.eq":"lmer(y ~ 1 + (1 | county))","reg.type":"lmer"}
{"chapter":23,"r.files":"23.1_MultilevelAspectsofDataCollection.R","stan.files":"electric_1a.stan","stan.obj.output":"electric_1a.sf1","model.type":" Multilevel model with varying slope and intercept","model.eq":"lmer(y ~ 1 + (1 | pair) + (treatment | grade))","reg.type":"lmer"}
{"chapter":23,"r.files":"23.1_MultilevelAspectsofDataCollection.R","stan.files":"electric_1b.stan","stan.obj.output":"electric_1b.sf1","model.type":" Multilevel model with varying slope and intercept","model.eq":"lmer(y ~ treatment + pre_test + (1 | pair))","reg.type":"lmer"}
{"chapter":23,"r.files":"23.1_MultilevelAspectsofDataCollection.R","stan.files":"electric_1c.stan","stan.obj.output":"electric_1c.sf1","model.type":" Multilevel model with varying slope and intercept","model.eq":"lmer(y ~ 1 + (1 | pair) + (treatment + pre_test | grade))","reg.type":"lmer"}
{"chapter":23,"r.files":"23.1_MultilevelAspectsofDataCollection.R","stan.files":"electric_one_pred.stan","stan.obj.output":"electric_one_pred.sf1","model.type":" Linear model with one predictor","model.eq":"lm(post_test ~ treatment)","reg.type":"lm"}
{"chapter":23,"r.files":"23.1_MultilevelAspectsofDataCollection.R","stan.files":"electric_multi_preds.stan","stan.obj.output":"electric_multi_preds.sf1","model.type":" Linear model with multiple predictors and without interaction","model.eq":"lm(post_test ~ treatment + pre_test)","reg.type":"lm"}
{"chapter":24,"r.files":"24.2_BehavioralLearningExperiment.R","stan.files":"dogs.stan","stan.obj.output":"dogs.sf1","model.type":" Multilevel model","model.eq":"glmer(y ~ n_avoid + n_shock, family=binomial(link=\"logit\"))","reg.type":"glmer"}
{"chapter":25,"r.files":"25.4_RadomImputationofaSingleVariable.R","stan.files":"earnings.stan","stan.obj.output":"earnings.sf1","model.type":" Single level model with multiple predictors","model.eq":"lm(earnings ~ male + over65 + white + immig + educ_r + workmos","reg.type":"lm"}
{"chapter":25,"r.files":"25.4_RadomImputationofaSingleVariable.R","stan.files":"earnings.stan","stan.obj.output":"earnings.sf2","model.type":" Single level model with multiple predictors","model.eq":"lm(earnings ~ male + over65 + white + immig + educ_r + workmos","reg.type":"lm"}
{"chapter":25,"r.files":"25.4_RadomImputationofaSingleVariable.R","stan.files":"earnings_pt1.stan","stan.obj.output":"earnings_pt1.sf1","model.type":" Single level model with multiple predictors","model.eq":"glm(earnings ~ male + over65 + white + immig + educ_r + any_ssi","reg.type":"glm"}
{"chapter":25,"r.files":"25.4_RadomImputationofaSingleVariable.R","stan.files":"earnings_pt2.stan","stan.obj.output":"earnings_pt2.sf1","model.type":" Single level model with multiple predictors","model.eq":"lm(earnings ~ male + over65 + white + immig + educ_r + any_ssi","reg.type":"lm"}
{"chapter":25,"r.files":"25.5_ImputationofSeveralMissingVariables.R","stan.files":"earnings2.stan","stan.obj.output":"earnings2.sf1","model.type":" Single level model with multiple predictors","model.eq":"lm(earnings ~ interest + male + over65 + white + immig + educ_r","reg.type":"lm"}