Modelling causal relationships is of the utmost importance in both the social and biomedical sciences. Assessing existence, sign, and direction of mutual relationships among the variables of a dataset can in fact serve many purposes: effect evaluation of policy interventions, detection of the mediating role played by some exposure to medical treatments, analysis of direct and indirect effects generated by external changes in many different contexts.
Typically, causal models are based on systems of equations, which are analysed using regression analysis techniques. The estimated relations are often mapped in diagrams or flow graphs.
The objective of this course is to provide participants with a gentle introduction to the essential toolset, mainly applied, for the implementation of simple structural equation models (SEM) for causal modelling in Stata, using the Stata package sem. This course offers two perspectives upon the issue, one focused on models where cross-section datasets are available; the other focused on times-series data. The former allows for causal path analysis. The latter also permits scenario-building and policy evaluation over time.
At the end of the course, participants will be able to autonomously undertake simple but effective causal designs studies to identify, estimate and test for both direct and indirect effects, pathways, and scenario building.
The course will be highly practical and focused on Stata applications using the sem package.
In common with Timberlake courses’ philosophy, participants will obtain extensive hands-on experience of the issues under consideration, working on example datasets from both the social and biomedical sciences under the careful guidance of the course instructor.
Too burdensome technical treatment will be avoid. Participants will be practise real world applications.
Session 1: An Introduction to Causal Modelling
- Causality in the social and bio-medical sciences: an overview
- What is causality? A simple explanation
- The linear regression approach
- The concepts of exogeneity and endogeneity of a variable
- Systems of equations and their main objects
- Modelling causality with cross-section and time-series datasets
Session 2: The Structural Equation Modelling (SEM) Language in Stata
- What is SEM?
- Variable definition within SEM
- Statistical models using SEM
- The sem and gsem Stata commands
- The sem syntax
- Path syntax using sem
- The model _description_options
- The option method ( ) and vce ( )
- The option covstructure for defining the structure of the variance/covariance matrix
- A simplified mathematical notation of SEM
- Assumptions under SEM estimation
- The Stata SEM Builder for graphical estimation
Session 3: A SEM Example - The Confirmatory Factor Analysis (CFA)
- What is CFA?
- CFA protocol – an illustrative example
- Model specification
- Graphical representation of a CFA model/li>
- Model assessment
- Model modification
- Practical examples using sem for CFA in Stata
Session 1: Using SEM for Path-Analysis
- Structural equation modelling for path models
- Path-model terminology and notation
- Mediation and moderation
- Estimation of direct, indirect, and total effects
- Estimation of a full structural equation model
- Tests for SEM reliability and goodness-of-fit
Session 2: Path-Analysis Applications using Stata
- A further look at the implementation of Stata’s SEM packages sem
- Using the SEM Builder: a series of illustrative examples
- Fitting, modifying and constraining a SEM with sem
- Interpreting the results
- Practical examples using Stata
Day 3 (Half Day)
Session 1: Modelling with Time-Series Data using Stata
- Structural modelling with times-series and panel data: an overview
- Building time-series structural models in Stata using the forecast package
- Model specification and identification
- Model validation with static and dynamic forecasts
- Practical examples in Stata using real datasets
Session 2: Policy Evaluation
- Policy evaluation via scenario-building
- Dynamic response to exogenous and endogenous shocks
- Practical examples in Stata using real datasets
30% Theory, 30% Demonstration and 40% Practical
Principal texts for pre/post course reading:
- Wooldridge, J.M. (2010). Econometric Analysis of cross section and panel data. Chapter 21. Cambridge: MIT Press.
- Acock, A.C, 2013. Discovering Structural Equation Modeling Using Stata, Stata Press.
- Stata Corp, 2017. “forecast — Econometric model forecasting”, STATA USER’S GUIDE RELEASE 15
DAILY TIMETABLE (subject to minor changes)
|Time||Session / Description|
||Arrival & Registration
||Tea/coffee break (Feedback Session)
- It is required some knowledge of basic econometrics: notion of conditional expectation and related properties; point and interval estimation; regression model and related properties; probit and logit regression.
- Basic knowledge of the Stata software
- Student registrations: Attendees must provide proof of full time student status at the time of booking to qualify for student registration rate (valid student ID card or authorised letter of enrolment).
- Additional discounts are available for multiple registrations.
- Cost includes course materials, lunch and refreshments.
- Delegates are provided with temporary licences for the software(s) used in the course and will be instructed to download and install the software prior to the start of the course. (Alternatively, laptops can be hired for a fee of £10.00 (ex. VAT) per day).
- If you need assistance in locating hotel accommodation in the region, please notify us at the time of booking.
- Payment of course fees required prior to the course start date.
- Registration closes 5-calendar days prior to the start of the course.
- 100% fee returned for cancellations made over 28-calendar days prior to start of the course.
- 50% fee returned for cancellations made 14-calendar days prior to the start of the course.
- No fee returned for cancellations made less than 14-calendar days prior to the start of the course.
The number of delegates is restricted. Please register early to guarantee your place.