Online Program

This workshop introduces the concepts and jargon of structural equation modeling (SEM) including path diagrams, latent variables, endogenous and exogenous variables, and goodness of fit. I will describe the similarities and differences between Stata's -sem- and -gsem- commands. Then I demonstrate how to fit many familiar models such as linear regression, multivariate regression, logistic regression, confirmatory factor analysis, and multilevel models using -sem- and -gsem-. I conclude demonstrating how to fit structural equation models that contain both structural and measurement components.

Outline & Objectives

Participants will learn about the following concepts and tools:
Observed and latent variables
Exogenous and endogenous variables
Recursive and nonrecursive models
Model assumptions
Checking the fit of a structural equation model
How to draw a path diagram using Stata’s SEM Builder
How to use Stata’s -sem- command syntax
How to use Stata’s -gsem- command syntax
Differences and similarities between -sem- and -gsem-
How to fit structural equation models by group
How to constraint model parameters
How to fit a mediation model using SEM
How to estimate descriptive statistics such as sample means, variance, and correlation with SEM
How to fit familiar models such as linear and logistic regression using SEM
How to fit confirmatory factor analysis (CFA) models using SEM

About the Instructor

Chuck Huber is a Senior Statistician at StataCorp and Adjunct Associate Professor of Biostatistics at the Texas A&M School of Public Health. In addition to working with Stata's team of software developers, he produces instructional videos for the Stata YouTube channel, writes blog entries, develops online NetCourses and gives talks about Stata at conferences and universities. Most of his current work is
focused on statistical methods used by psychologists and other behavioral scientists. He has
published in the areas of neurology, human and animal genetics, alcohol and drug abuse prevention, nutrition and birth defects. Dr. Huber currently teaches introductory biostatistics at Texas A&M where he previously taught categorical data analysis, survey data analysis, and statistical genetics.

Relevance to Conference Goals

Structural equation modeling has become increasingly popular for modeling the interrelationships among a group of variables. Many researchers us SEM to understand causal relationships in complex systems. This talk introduces this powerful tool using the popular statistical package Stata.

Thanks to its popularity and user-friendly environment, Microsoft Excel is widely used to gain data insights and make better decisions. However, compared to mainstream statistical software such as R, Excel lacks advanced statistical tools taken solely or integrated into procedures. On the other hand, R is a coding software associated to a steep learning curve. In order to interface the unlimited statistical possibilities of R with the user-friendly environment of Excel, two features have recently been developed within the XLSTAT software: 1) XLSTAT-R helps programmers develop user-friendly dialog boxes in Excel allowing users to launch customized R procedures directly on data selected in Excel with their mouse. 2) The XLSTAT-RNotebook allows writing R code in Excel cells with the possibility of capturing data in the form of Excel cell ranges. The outputs are also displayed in Excel. This makes it possible to create complex dashboards or reports in Excel made from R code. The created procedures can then be used by colleagues, students or clients who don’t necessarily know how to code. This tutorial shows how developers can build customized R procedures in an Excel dialog box or directly in Excel cells using XLSTAT.

Basic coding skills are required (preferably R).

Outline & Objectives

Outline:
1. Introduction to XLSTAT-R and the XLSTAT-RNotebook.
2. Application: Making the pam{cluster} R function available in an Excel dialog box and adding the possibility to customize several options and charts from within the dialog box.
3. Application: Developing a customized R-based dashboard in an Excel sheet using the XLSTAT-RNotebook.

Objectives:
At the end of this tutorial, participants will understand the basics of XLSTAT-R or the XLSTAT-RNotebook, used to develop R-based statistical applications or dashboards in Excel.

About the Instructor

Jean Paul Maalouf (PhD) is an independent statistical consultant with 10 years of experience. He has worked for 4 years at Addinsoft as the brand manager of the XLSTAT Software, leader in statistical software for Excel. He substantially contributed to the development of the XLSTAT-R engine and has created many of the default XLSTAT-R procedures included in XLSTAT solutions.

Relevance to Conference Goals

The open-source R software is known for its steep learning curve. Data-inspired decision makers often prefer relying on dashboards or user-friendly environments such as Microsoft Excel. This tutorial shows how data science, data analysis and modeling procedures built in R can be made available to any Excel user thanks to XLSTAT-R and the XLSTAT-RNotebook. These developments are possible under different collaboration scenarios. Chief programming statisticians are able to customize applications for decision makers. Consultants are able to set up Excel applications tailored to the specific needs of their customers. Professors are able to develop customized statistical programs in Excel to illustrate their courses.