Master
2021/2022

## Analysis of Covariance Models

Category 'Best Course for New Knowledge and Skills'

Type:
Compulsory course (Applied Statistics with Network Analysis)

Area of studies:
Applied Mathematics and Informatics

Delivered by:
International laboratory for Applied Network Research

When:
2 year, 1, 2 module

Mode of studies:
offline

Open to:
students of all HSE University campuses

Instructors:
Valentina Kuskova

Master’s programme:
Applied Statistics with Network Analysis

Language:
English

ECTS credits:
6

### Course Syllabus

#### Abstract

This course is designed for MASNA students who would like to acquire a significant familiarity with the statistical techniques known collectively as "structural equation modeling," "causal modeling," or "analysis of covariance structures."

#### Learning Objectives

- To provide you with an understanding of the basic principles of latent variable structural equation modeling and lay the foundation for future learning in the area.
- To explore the advantages and disadvantages of latent variable structural equation modeling, and how it relates to other methods of analysis.
- To develop your familiarity, through hands on experience, with the major structural equation modeling programs, so that you can use them and interpret their output.
- To develop and/or foster critical reviewing skills of published empirical research using structural equation modeling.

#### Expected Learning Outcomes

- Know the basic idea of implied matrices and what is happening in SEM.
- Know the major structural equation modeling programs.
- Know how to translate conceptual thinking into models that can be estimated.
- Be able to use the major SEM programs to estimate common types of models: Multi-equation path analysis models
- Be able to use the major SEM programs to estimate common types of models: Path models with fixed, non-zero error terms
- Be able to use the major SEM programs to estimate common types of models: Models with multiple mediating effects.
- Be able to use the major SEM programs to estimate common types of models: Latent variable multi-equation models.
- Be able to use the major SEM programs to estimate common types of models: Formative indicator models.
- Be able to use the major SEM programs to estimate common types of models: Second-order factor models.
- Be able to use the major SEM programs to estimate common types of models: Multi-group models with mean structures.
- Be able to use the major SEM programs to estimate common types of models: Models with latent variable interactions.
- Be able to use the major SEM programs to estimate common types of models: Latent growth curve models, latent state-trait-occasion models, etc.
- Have an understanding common problems related to model specification, identification, and estimation.
- Have a working knowledge of the different ways to analyze models with covariance structures.
- Be able to use the major SEM programs to estimate common types of models: Multi-level models (If time permits).

#### Course Contents

- Course Introductiona. Course Requirements b. A Model of the Research Process
- Problem Selection and Conceptualizationa. Choosing a Worthwhile Topic b. Defining Constructs c. Generating Hypotheses
- Fundamentals of LVSEM (Part 1)
- Basic Modela. Path Diagrams b. Rules for Determining Model Parameters c. Model Implied Covariance Structure
- Fundamentals of LVSEM (Part 2)a. Parameter Estimation b. Identification
- Fundamentals of LVSEM (Part 3)a. Model Testing and Evaluation b. Two-Step Approach for Testing Models
- Software ProgramsLISREL 8.8, Amos 6, Mplus 4.21, EQS 6.1
- Observed Variable Models – Path Analysisa. What is path analysis? b. Example model c. Modeling Measurement Error in Path Analysis Models
- Testing Mediationa. Direct and Indirect Effects b. Testing Indirect Effects
- Effect Decompositiona. Latent Variable Structural Equation Models b. What is confirmatory factor analysis? c. What is a structural regression model? d. The Consequences of Measurement Error e. Controlling for Method Biases and “Third Variables”
- Measurement Model Specificationa. Types of Measurement Relations b. Specification of Second-Order Measurement Relationships c. Item Parceling
- Assessing Construct Validity and Reliabilitya. Validity b. Reliability c. Scaling Procedures
- Multiple Groups Analysisa. Multiple Group Analyses b. Analysis of Mean Structures c. Imposing Constraints Within and Between Groups d. Cross-Validation of Measurement and/or Structural Relationships e. Examples
- Latent Variable Interactionsa. Why use this? b. Model Specification
- Latent Change Analysisa. What is latent change analysis? b. Simple One Factor LCA Model c. Level and Shape Model d. Studying Correlates and Predictors of Latent Change
- Special Topics

#### Assessment Elements

- Answers to Readings Questions
- Basics Exam
- Path Analysis and Mediating Effects
- Latent Variable Model
- Moderating Effects with Latent Variables
- Special Topic Presentation

#### Interim Assessment

- Interim assessment (1 module)0.4 * Answers to Readings Questions + 0.6 * Basics Exam
- Interim assessment (2 module)0.25 * Latent Variable Model + 0.25 * Moderating Effects with Latent Variables + 0.25 * Path Analysis and Mediating Effects + 0.25 * Special Topic Presentation

#### Bibliography

#### Recommended Core Bibliography

- Netemeyer, R. G., Sharma, S., & Bearden, W. O. (2003). Scaling Procedures : Issues and Applications. Thousand Oaks, Calif: SAGE Publications, Inc. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=321358
- Raykov, T., & Marcoulides, G. A. (2006). A First Course in Structural Equation Modeling (Vol. 2nd ed). Mahwah, NJ: Routledge. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=188193

#### Recommended Additional Bibliography

- Byrne, B. M. (1998). Structural Equation Modeling With Lisrel, Prelis, and Simplis : Basic Concepts, Applications, and Programming. Mahwah, N.J.: Psychology Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=582749
- Byrne, B. M. (2000). Structural Equation Modeling With AMOS : Basic Concepts, Applications, and Programming. Mahwah, N.J.: Psychology Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=54805