Statistics and Causality : Methods for Applied Empirical Research.

Cover -- Title Page -- Copyright -- Contents -- List of Contributors -- Preface -- Acknowledgments -- Part I Bases of Causality -- Chapter 1 Causation and the Aims of Inquiry -- 1.1 Introduction -- 1.2 The Aim of an Account of Causation -- 1.2.1 The Possible Utility of a False Account -- 1.2.2 Inquiry's Aim -- 1.2.3 Role of "Intuitions -- 1.3 The Good News -- 1.3.1 The Core Idea -- 1.3.2 Taxonomizing "Conditions -- 1.3.3 Unpacking "Dependence -- 1.3.4 The Good News, Amplified -- 1.4 The Challenging News -- 1.4.1 Multiple Realizability -- 1.4.2 Protracted Causes -- 1.4.3 Higher Level Taxonomies and "Normal" Conditions -- 1.5 The Perplexing News -- 1.5.1 The Centrality of "Causal Process -- 1.5.2 A Speculative Proposal -- Chapter 2 Evidence and Epistemic Causality -- 2.1 Causality and Evidence -- 2.2 The Epistemic Theory of Causality -- 2.3 The Nature of Evidence -- 2.4 Conclusion -- Part II Directionality of Effects -- Chapter 3 Statistical Inference for Direction of Dependence in Linear Models -- 3.1 Introduction -- 3.2 Choosing the Direction of a Regression Line -- 3.3 Significance Testing for the Direction of a Regression Line -- 3.4 Lurking Variables and Causality -- 3.4.1 Two Independent Predictors -- 3.4.2 Confounding Variable -- 3.4.3 Selection of a Subpopulation -- 3.5 Brain and Body Data Revisited -- 3.6 Conclusions -- Chapter 4 Directionality of Effects in Causal Mediation Analysis -- 4.1 Introduction -- 4.2 Elements of Causal Mediation Analysis -- 4.3 Directionality of Effects in Mediation Models -- 4.4 Testing Directionality Using Independence Properties of Competing Mediation Models -- 4.4.1 Independence Properties of Bivariate Relations -- 4.4.2 Independence Properties of the Multiple Variable Model -- 4.4.3 Measuring and Testing Independence -- 4.5 Simulating the Performance of Directionality Tests -- 4.5.1 Results.

4.6 Empirical Data Example: Development of Numerical Cognition -- 4.7 Discussion -- Chapter 5 Direction of Effects in Categorical Variables: A Structural Perspective -- 5.1 Introduction -- 5.2 Concepts of Independence in Categorical Data Analysis -- 5.3 Direction Dependence in Bivariate Settings: Metric and Categorical Variables -- 5.3.1 Simulating the Performance of Nonhierarchical Log-Linear Models -- 5.4 Explaining the Structure of Cross-Classifications -- 5.5 Data Example -- 5.6 Discussion -- Chapter 6 Directional Dependence Analysis Using Skew-Normal Copula-Based Regression -- 6.1 Introduction -- 6.2 Copula-Based Regression -- 6.2.1 Copula -- 6.2.2 Copula-Based Regression -- 6.3 Directional Dependence in the Copula-Based Regression -- 6.4 Skew-Normal Copula -- 6.5 Inference of Directional Dependence Using Skew-Normal Copula-Based Regression -- 6.5.1 Estimation of Copula-Based Regression -- 6.5.2 Detection of Directional Dependence and Computation of the Directional Dependence Measures -- 6.6 Application -- 6.7 Conclusion -- Chapter 7 Non-Gaussian Structural Equation Models for Causal Discovery -- 7.1 Introduction -- 7.2 Independent Component Analysis -- 7.2.1 Model -- 7.2.2 Identifiability -- 7.2.3 Estimation -- 7.3 Basic Linear Non-Gaussian Acyclic Model -- 7.3.1 Model -- 7.3.2 Identifiability -- 7.3.3 Estimation -- 7.4 LINGAM for Time Series -- 7.4.1 Model -- 7.4.2 Identifiability -- 7.4.3 Estimation -- 7.5 LINGAM with Latent Common Causes -- 7.5.1 Model -- 7.5.2 Identifiability -- 7.5.3 Estimation -- 7.6 Conclusion and Future Directions -- Chapter 8 Nonlinear Functional Causal Models for Distinguishing Cause from Effect -- 8.1 Introduction -- 8.2 Nonlinear Additive Noise Model -- 8.2.1 Definition of Model -- 8.2.2 Likelihood Ratio for Nonlinear Additive Models -- 8.2.3 Information-Theoretic Interpretation.

8.2.4 Likelihood Ratio and Independence-Based Methods -- 8.3 Post-Nonlinear Causal Model -- 8.3.1 The Model -- 8.3.2 Identifiability of Causal Direction -- 8.3.3 Determination of Causal Direction Based on the PNL Causal Model -- 8.4 On the Relationships Between Different Principles for Model Estimation -- 8.5 Remark on General Nonlinear Causal Models -- 8.6 Some Empirical Results -- 8.7 Discussion and Conclusion -- Part III Granger Causality and Longitudinal Data Modeling -- Chapter 9 Alternative Forms of Granger Causality, Heterogeneity, and Nonstationarity -- 9.1 Introduction -- 9.2 Some Initial Remarks on the Logic of Granger Causality Testing -- 9.3 Preliminary Introduction to Time Series Analysis -- 9.4 Overview of Granger Causality Testing in the Time Domain -- 9.5 Granger Causality Testing in the Frequency Domain -- 9.5.1 Two Equivalent Representations of a VAR(a) -- 9.5.2 Partial Directed Coherence (PDC) as a Frequency-Domain Index of Granger Causality -- 9.5.3 Some Preliminary Comments -- 9.5.4 Application to Simulated Data -- 9.6 A New Data-Driven Solution to Granger Causality Testing -- 9.6.1 Fitting a uSEM -- 9.6.2 Extending the Fit of a uSEM -- 9.6.3 Application of the Hybrid VAR Fit to Simulated Data -- 9.7 Extensions to Nonstationary Series and Heterogeneous Replications -- 9.7.1 Heterogeneous Replications -- 9.7.2 Nonstationary Series -- 9.8 Discussion and Conclusion -- Chapter 10 Granger Meets Rasch: Investigating Granger Causation with Multidimensional Longitudinal Item Response Models -- 10.1 Introduction -- 10.2 Granger Causation -- 10.3 The Rasch Model -- 10.4 Longitudinal Item Response Theory Models -- 10.5 Data Example: Scientific Literacy in Preschool Children -- 10.6 Discussion -- Chapter 11 Granger Causality for Ill-Posed Problems: Ideas, Methods, and Application in Life Sciences -- 11.1 Introduction.

11.1.1 Causality Problems in Life Sciences -- 11.1.2 Outline of the Chapter -- 11.1.3 Notation -- 11.2 Granger Causality and Multivariate Granger Causality -- 11.2.1 Granger Causality -- 11.2.2 Multivariate Granger Causality -- 11.3 Gene Regulatory Networks -- 11.4 Regularization of Ill-Posed Inverse Problems -- 11.5 Multivariate Granger Causality Approaches Using l1 and l2 Penalties -- 11.6 Applied Quality Measures -- 11.7 Novel Regularization Techniques with a Case Study of Gene Regulatory Networks Reconstruction -- 11.7.1 Optimal Graphical Lasso Granger Estimator -- 11.7.2 Thresholding Strategy -- 11.7.3 An Automatic Realization of the GLG-Method -- 11.7.4 Granger Causality with Multi-Penalty Regularization -- 11.7.5 Case Study of Gene Regulatory Network Reconstruction -- 11.8 Conclusion -- Chapter 12 Unmeasured Reciprocal Interactions: Specification and Fit Using Structural Equation Models -- 12.1 Introduction -- 12.2 Types of Reciprocal Relationship Models -- 12.2.1 Cross-Lagged Panel Approaches -- 12.2.2 Granger Causality -- 12.2.3 Epistemic Causality -- 12.2.4 Reciprocal Causality -- 12.3 Unmeasured Reciprocal and Autocausal Effects -- 12.3.1 Bias in Standardized Regression Weight -- 12.3.2 Autocausal Effects -- 12.3.3 Instrumental Variables -- 12.4 Longitudinal Data Settings -- 12.4.1 Monte Carlo Simulation -- 12.4.2 Real-World Data Examples -- 12.5 Discussion -- Part IV Counterfactual Approaches and Propensity Score Analysis -- Chapter 13 Log-Linear Causal Analysis of Cross-Classified Categorical Data -- 13.1 Introduction -- 13.2 Propensity Score Methods and the Collapsibility Problem for the Logit Model -- 13.3 Theorem On Standardization and the Lack of Collapsibility of the Logit Model -- 13.4 The Problem of Zero-Sample Estimates of Conditional Probabilities and the Use of Semiparametric Models to Solve the Problem.

13.4.1 The Problem of Zero-Sample Estimates of Conditional Probabilities -- 13.4.2 Method for Obtaining Adjusted Two-Way Frequency Data for the Analysis of Association between X and Y -- 13.4.3 Method for Obtaining an Adjusted Three-Way Frequency Table for the Analysis of Conditional Association -- 13.5 Estimation of Standard Errors in the Analysis of Association with Adjusted Contingency Table Data -- 13.6 Illustrative Application -- 13.6.1 Data -- 13.6.2 Software -- 13.6.3 Analysis -- 13.7 Conclusion -- Chapter 14 Design- and Model-Based Analysis of Propensity Score Designs -- 14.1 Introduction -- 14.2 Causal Models and Causal Estimands -- 14.3 Design- and Model-Based Inference with Randomized Experiments -- 14.3.1 Design-Based Formulation -- 14.3.2 Model-Based Formulation -- 14.4 Design- and Model-Based Inferences with PS Designs -- 14.4.1 Propensity Score Designs -- 14.4.2 Design- versus Model-Based Formulations of PS Designs -- 14.4.3 Other Propensity Score Techniques -- 14.5 Statistical Issues with PS Designs in Practice -- 14.5.1 Choice of a Specific PS Design -- 14.5.2 Estimation of Propensity Scores -- 14.5.3 Estimating and Testing the Treatment Effect -- 14.6 Discussion -- Chapter 15 Adjustment when Covariates are Fallible -- 15.1 Introduction -- 15.2 Theoretical Framework -- 15.2.1 Definition of Causal Effects -- 15.2.2 Identification of Causal Effects -- 15.2.3 Adjusting for Latent or Fallible Covariates -- 15.3 The Impact of Measurement Error in Covariates on Causal Effect Estimation -- 15.3.1 Theoretical Impact of One Fallible Covariate -- 15.3.2 Investigation of the Impact of Fallible Covariates in Simulation Studies -- 15.3.3 Investigation of the Impact of Fallible Covariates in an Empirical Study -- 15.4 Approaches Accounting for Latent Covariates -- 15.4.1 Latent Covariates in Propensity Score Methods.

15.4.2 Latent Covariates in ANCOVA Models.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.