Software for the ENAR Short Course on Measurement Error Models

• Stata Programs
  
  
  • How to download the measurement error programs for regression calibration, SIMEX and Instrumental Variables into Stata for eventual runs. This also points to many worked examples, and if you go to Stata's web page (http://www.stata.com) you can get more detailed help.
    • PDF File
      
    
    
  • Regression Calibration in Stata With Replicates
    This program and output illustrates how to run a logistic regression using regression calibration in the Framingham data set with replicates of what we call W. The factors measured without error are age (AGE) and smoking status (SMOKE). The replicated prodictors of transformed systolic blood pressure are LSBP2 and LSBP3.
    • The Stata data set
      
    • The Stata do file after you open the Stata data set, go to "File" and "do" and select this one
      
    • PDF File of an example
      
    • PDF File of Help file
      
    
    
  • SIMEX in Stata With Replicates
    This program and output illustrates how to run a logistic regression using SIMEX in the Framingham data set with replicates of what we call W. The facotrs measured without error are age (AGE) and smoking status (SMOKE). The replicated prodictors of transformed systolic blood pressure are LSBP2 and LSBP3.
    • PDF File of an example
      
    • PDF File of an simex graph
      
    • PDF File of Help file
      
    • The Stata data set
      
    • The Stata do file after you open the Stata data set, go to "File" and "do" and select this one
      
    
    
  • Regression Calibration and SIMEX in Stata With Replicates or Without Replicates and With Known Measurement error variance
    This material is more or less lifted directly from our book. Make sure you start by opening the Framingham data
    • PDF File almost from the book
      
    • The Stata data set
      
    • The Stata do file after you open the Stata data set, go to "File" and "do" and select this one. Because it bootstraps SIMEX, it is a little bit slow. However, this illustrates the code for 1 variable measured with error and two variables measured with error.
      
    
    
  • Instrumental variables in Stata for linear regression, nondifferential error
    This material uses the WISH Data (I have created a fake version of it)
    • The Stata data set
      
    • The Stata do file after you open the Stata data set, go to "File" and "do" and select this one.
      
    • pdf file of the commands
      
    
    
  • Instrumental variables in Stata for logistic regression, nondifferential error
    This material uses the CHD-Cholesterol-LDL Data
    • The Stata data set
      
    • The Stata do file after you open the Stata data set, go to "File" and "do" and select this one.
      
    • pdf file of the commands
      
    
    
  
  
• Structural Modeling via GLLAMM in Stata
  
  The software package gllamm in Stata allows you to fit measurement error models in a structural framework with normally distributed measurement error and normally distributed true X given the other covariates. The implementations given here are restricted to a scalar covariate measured with error, although it is possible to extend this.
  • Overview of what GLLAMM does, with reference to Framingham
    • PDF File
      
    
    
  • The Framingham data as a Stata data set
    • PDF File
      
    
    
  • Command for GLLAMM when there are replicates. Includes how to get the GLLAMM software
    • PDF File
      
    
    
  • Command for GLLAMM when there are No replicates.
    • PDF File
      
    
    
  • Output for GLLAMM when there are replicates. Note that this gives you the exposential of the parameter estimates, i.e., the odds ratio.
    • PDF File
      
    
    
  • Output for GLLAMM when there are No replicates. Note that this gives you the exposential of the parameter estimates, i.e., the odds ratio.
    • PDF File
      
    
    
  
  
• SAS Proc Mixed Program for the OPEN Data set
  This program was written by Doug Midthune of the National Cancer Institute. Fitting measurement error models in PROC Mixed is possible, but as the example shows, the latent variable nature of the problem makes it a complex task. The program basically computes the mean and covariance matrix of the data and then does maximum likelihood.
  • SAS Program without Covariates
    
  • SAS Program with Covariates
    
  • OPEN-like data structure (simulated data)
    
  
  
• R2WinBUGS Programs
  • The OPEN data without covariates. The data is simulated.
    • Simulated Data Set
      
    • Read me file (Must be saved, since it is rich text format)
      
    • Main program that needs to be sourced
      
    • WinBUGS commands
      
    
    
  • The Framingham data without covariates.
    • Simulated Data Set
      
    • Read me file (Must be saved, since it is rich text format. Also, many of the files alluded to need to be generated)
      
    • Main program that needs to be sourced
      
    • WinBUGS commands
      
      
  • The Nevada Test Site (simulated) data without covariates.
    • Simulated Data Set
      
    • Read me file, in text
      
    • Main program that needs to be sourced
      
    • WinBUGS commands
      
      
      
    
    
• R Programs for SIMEX
  There is an R package for SIMEX that handles at least generalized linear models. What is illustrated there is the Framingham example.
  • The Framingham data suitable for R
    • PDF File
      
    
    
  • Directions for using SIMEX in R. You have to input the measurement error variance.
    • PDF File
      
    
    
  • The R script for the Framingham data
    • PDF File
      
    
    
  • The output from R
    • PDF File
      
    
    
  • The SIMEX trace plot
    • PDF File