Interdisciplinary Statistics in Mexico: AME Virtual Meeting, September 10–11, 2020, and 34 FNE, Acatlán, Mexico, September 22–24, 2021

Description

​The volume includes a collection of peer-reviewed contributions from among those presented at the FNE, the main conference organized every two years by the Mexican Statistical Society (AME), and the 2020 AME Virtual Meeting. Statistical research in Latin America is prolific and research networks span both within and outside the region. As much of the work is typically carried out and published in Spanish, a large portion of the interested public is denied access to interesting findings, and the goal of this volume is therefore to provide access to selected works from Mexican collaborators and their international research networks to a wider audience. It may be especially attractive to academics interested in the latest methodological advances, while professionals from other disciplines may also find value in these new tools for data analysis. In 2021, the conference broadly focused on the interdisciplinary aspects of Statistics. Preface Contents A Methodological Proposal to Model and Evaluate the Complexity of the Mexican Geo-Electoral System 1 Introduction 2 Methodological Framework 2.1 Conceptualization of Electoral Complexity 2.2 Statistical Indicators for Quantifying Electoral Complexity 2.3 Data Transformation, Electoral Complexity Indices, and Stratification 3 ECI Construction and Stratification 3.1 Exploratory Analysis and PCA Implementation 3.2 Clustering Analysis and Stratification with K-Means 4 Electoral Complexity Ranking and Stratification Results 5 Conclusions References A Spatial Analysis of Drug Dealing in Mexico City 1 Introduction 2 Background 2.1 Drug Dealing as Part of Organized Crime 2.2 Research Approaches 3 Methodology 4 Results 4.1 Univariate Global and Local Moran's I 4.2 Bivariate Global and Local Moran's I 5 Discussion and Conclusions References Bayesian Hierarchical Multinomial Modeling of the 2021 Mexican Election Outcomes with Censored Samples 1 Introduction 2 Background 2.1 Estimation Methods in the 2021 Quick Count 2.2 NBM Model Background 2.3 The Bias Problem 3 The NBM Model 3.1 Specification 3.2 Consistency of Our Modeling Assumptions 3.3 Fitting Procedure 3.4 Model Adequacy 4 The 2021 Mexican Elections 4.1 Data and Sample Design 4.2 Results 5 Conclusions and Future Work References Assessing Hospitalization for SARS-CoV-2 Confirmed Cases by a Cross-Entropy Weighted Ensemble Classifier 1 Introduction 2 Material 2.1 Dataset Description 2.2 Data Analysis 3 Cross-entropy Weighted Ensemble Classifier 4 Results 5 Discussion 6 Conclusion References Emotion Analysis to Identify Risk of Committing Suicide Using Statistical Learning 1 Background 2 Materials and Methods 2.1 Emotion Mining 2.2 Statistical Learning Methods 2.3 Training and Test Datasets 3 Results 3.1 Supervised Models 3.2 Unsupervised Model 3.3 Model Comparison 3.4 Testing the Models with a New Test Set: COVID-19 4 Conclusions References Characterizing Groups Using Latent Class Mixed Models: Antiretroviral Treatment Adherence Analysis 1 Introduction 2 Materials 2.1 Population 2.2 Data Collection 2.3 ART Adherence Definition 3 Latent Class Mixture Models 4 Results 4.1 Latent Classes from ART Adherence 4.2 Latent Classes for Bivariate Response of CD4/CD8 Ratio and CD4+T Within Groups of Adherence 5 Discussion and Conclusions References A Dynamic Model for Analyzing the Public Health Policy of the Mexican Government During the COVID-19 Pandemic 1 Introduction 2 Related Work 3 Methods 3.1 SIRD Model 3.2 Transmission Rate Model 3.3 Recovery Rate Estimation 3.4 Bayesian Inference 4 Results 5 Conclusions References Social Lag in the Municipalities of the State of Guerrero, México 1 Introduction 2 Methodology 2.1 CONEVAL 2.2 Clustering 3 Application 4 Results 4.1 CONEVAL 4.2 Cluster 4.3 Comparison 5 Conclusions References Challenges in Performing the Quick Counts of the National Electoral Institute in Mexico 1 Introduction 2 The Model 3 The Code 3.1 The Functional Code 3.2 First Idea: Use the Sample Design 3.3 Second Idea: Reach Out to the Community 4 Concluding Remarks References Sampling Design and Poststratification to Correct Lack of Information in Bayesian Quick Counts 1 Introduction 2 Model and Specifications 3 Sample Design 4 Incomplete Sample Estimation 4.1 General Strategy 4.2 Poststratification 4.3 Credibility Level Correction 5 Election Day 6 Conclusions References Maximum Likelihood Estimation for a Markov-Modulated Jump-Diffusion Model 1 Introduction 2 Markov-Modulated Jump-Diffusion Model 3 Methodology for the Maximum Likelihood Estimators 3.1 Identify the Jumps of the MJP 3.2 Estimate the Distribution of the Jumps 3.3 Estimate the Coefficients of the GBM 3.4 MLE of Q 4 Simulation Study 5 Real Data 6 Conclusions References Estimating the Composition of the Chamber of Deputies in the Quick Count for the 2021 Federal Election in Mexico 1 Introduction 1.1 The Quick Count 2 The Chamber of Deputies 2.1 Conformation 3 Estimation 3.1 Sampling Design 3.2 Bootstrap Estimation 4 Incomplete Samples 4.1 Multiple Imputation 5 Election Day: June 6, 2021 5.1 Election Day Strategy 5.2 Arrival of Information 5.3 Estimations 6 Discussion A Appendix: Transforming Votes into Seats in the Deputy Chamber A.1 Relative Majority A.2 Voting Types Considered in the Law A.3 Proportional Representation References Bayesian Analysis of Homicide Rates in Mexico from 2000 to 2012 1 Introduction 2 Literature Review 3 Data 4 Model Specification 5 Analysis and Results 6 Concluding Remarks References Index