Last revised: May 3, 2011
 

  General Information (MSword format):

• Syllabus 2011.
• Course log What we actually did and plan for next few weeks. .

• April 22: The final and data are available below.
• April 18:
  • Homework 4 is due Thursday April 28
  • The sas code from computer lab on Tuesday April 18 is linked under computer lab 4
• April 6: The finals (or projects) are due Tuesday May 10.
• March 29: Typo in the homework 3. On problem 1, part e, use Model p. Also the due date was changed to April 7.
• March 15:
  • The example of using hlmrsq works under the lecture notes on inference for marginal model.
  • The next computer lab instructions and homework are posted.
  • There is a computer lab on Thursday...don't forget your laptop.
• Jan 30: On Feb 10 (10am), Anne Roberston will visit class to discuss IRB requirements. Although this is important for all, it will be espeically important to those doing projects. Below are two related links:
  • Human Subjects Review page for the College of education that includes access to relevant forms is at.
  • Campus IRB site for the education modules.


• Jan 19: Optional: introduction to SAS will be given Thursday Jan 27, 9-10am. The material covered is the Handout under "Computers Lab 0". If you have used SAS before, there is no need to attend this session.
• Lecture meeting time: Most days lectures will be from 10:00-11:50am, including the first one.
• Computing: We will be running statistical software (SAS) using remote desktop connection. We will connect to a server that has the software. There are 2 things that you need before you can do this:
  • Your computer must be hooked up to the internet (campus, home, hotel, Espresso Royal, elsewhere).
  • You must be registered for the class. If you reccently registered, you may not yet have permission to login.

• Introduction.
  SAS programs that generated (most of) the statistics and graphs in the lecture notes:
  • Juinor School Project..
  • Hypothetical longitudinal example
  • Two schools from NELS88


• Models for clustered data: Fixed and random effects ANOVA and multiple regression. SAS code that produced statistics and graphics given in lecture note
  • NELS data for 10 schools. Run this program before the next one.
  • Generates statistics, fits models & produces graphics.


• Random Intercept Models.
  
  
  • ANCOVA.sas. Fits ANCOVA model to NELS88, N=10 data (includes centering a variable, model fitting using GLM, and SAS/GRAPH of model).
  • hsb1.sas. Creates SAS data set of level 1 data for the High School and Beyond data.
  • hsb2.sas. Creates SAS data set of level 2 data for the High School and Beyond data.
  • hsball.sas. Merges level 1 and level 2 high school and beyond sas datasets.
  • betwithin.sas. SAS/GRAPHS for looking between and within variability of SES in the high school and beyond data.
  • randomintercepts.sas. SAS PROC MIXED and fitting random intercept models (includes centering SES)...and some graphics.
  
  
• SAS for HLM.
  These will be used in lecture (they can also be used to reproduce the models for HSB data in the lecture notes on random intercept models):
  • HSB1 data. (level 1 data -- students)
  • HSB2 data (level 2 data -- schools)
  • SAS code to be discussed in lecture.
  • How to simulate multilevel data
  • Using SAS assist for graphics.
  • Using SAS insight. (interactive data analysis)
  This is from the introduction to SAS session:
  • Handout: Introduction to SAS by Example.


• Random Intercept and Slopes Models .
  
  
• text file of data. NELS88 data for N=23 school.
• school23.sas. SAS program that creates SAS data set for NEL88 data for N=23 school.
• NELS23.sas. SAS program that fits various random intercept and slope models to the NEL88 data for N=23 school.
• Centering & NELS data. Illustrates effects of different kinds of centering -- NEL88 data for N=23 school.
• SAS examples discussed in lecture.


• Estimation of Marginal Model .



• Statistical Inference: Marginal Model. (up-dated Oct 20, 2010). Note that I forgot to make correction regarding information criteria---they should only be used for MLE and not REML. The reasoning is similar to why can't test fixed effects using a likelihood ratio test. I'll explain in class.


• SAS commands for ddfm (Simulation to show what different choices for df yield).
• HSB1 data. (level 1 data -- students)
• HSB2 data (level 2 data -- schools)
• hlmrsq.sas SAS macro that computes R_1^2 and R_2^2.
• Recchia JSS paper describing the hlmrsq.sas macro and how to use it.
• SAS for fixed effects & Rsq. Illustrates various things.
• Example: computing p-value of mixture of chi-squares (i.e., test of variance).


• Random Effects.


• HSB1 data. (level 1 data -- students)
• HSB2 data (level 2 data -- schools)
• SAS program and EB estimates of U's.
• SAS commands for mini-study on micro sample size on U's.
• SAS commands for mini-study on macro sample size on estimates.
• SAS commands for mini-study on effects of non-normality onf the distribution of EB estimates.
• Using SAS/Insight. Interactive data analysis and exploration (great for looking at data).
• Using SAS/ASSIST to produce graphics. (Alternatives given in next lecture).



• Model Building. (up-dated APril 11, 2011...changed pages 156 - 172)
  • New SAS programs:
    • NELS data for N=23 schools (from Kreft & de Leeuw).
    • SAS Exploratory data analysis: Fixed Effects
    • SAS Exploratory data analysis: Random Effects
    • Modeling the data & diagnostics.
  • Old SAS programs:
    • eda.sas SAS program including commands for exploratory data analyses (SAS/GRAPH, R^2meta, R^2_j, means structure, etc).
    • Simulations.sas. SAS program running first simulation and exploration of random structure.
    • Simulation_long.sas. SAS program running second simulation and exploration of random structure. This has a different sigma^2's and tau's.
    • New Variance EDA.sas. Exploratory data analyses of random structure for example given in class.
    • SAS v9.1 experimental diagnostics..
  
  
  
• Longitudinal Data Analysis
  • Lecture notes on Longitudinal Data and HLM.
  • Lecture notes on Serial Correlation..
  • HLM for Riesby data. (data from Hedeker web-site plus additional analyses I did).
  • Error Structures Simulation:
    • Random Effects Only.
    • First Order Auto Regressive, AR(1).
    • First Moving Average, MA(1).
    • First Order Auto Regressive Moving Average, ARMA(1,1).
  
  
  
• Multilevel Logistic Regression.
• Longitudinal study on depression. (data from Agresti, 2002)
• Longitudinal study on respiratory infections. (data from Skrondal & Rabe-Hesketh,2004)
• Simmulation study & demonstration.
• I will not be posting the Rodkin et al. data set or SAS code.
• Rasch and 2pl model fit to LSAT6.
• Rasch and 2pl model fit to General Social Suvery Vocabulary items with covariate. (This example will be discussed in class (time permitting) but it is the not in notes).

• Computer Lab Session 0 (optional): Introduction to SAS
  • HSB1 data sas file (level 1 data -- students)
  • Handout: Introduction to SAS by Example
  • Using SAS assist for graphics.
  • Using SAS insight. (interactive data analysis)
  • Slick online SAS training from SAS.com


• Computer Lab Session 1: (bring laptop)
  • SAS program and data.
  • Computer Lab instructions.
  • SAS program that does it all.


• Computer Lab Session 2: (bring laptop)
  • SAS program and data for Lab 2.
  • Computer Lab instructions & description of data.
  • SAS program that does it all. (available after homework 2 turned in).


• Computer Lab Session 3: bring laptop....March 17
  • Computer Lab instructions. We will use data and your programs from previous labs. (code will be posted right before the lab).
  • hlmrsq.sas SAS macro that computes R_1^2 and R_2^2.
  • SAS program that does it all.


• Computer Lab Session 4: April 14 & 18
  • Computer Lab Instructions.
  • SAS MACRO that draw a random sample of data.
  • SAS program needed for computer lab 4.
  • Some SAS code for exploring preliminary random effects structure
  • SAS from Lab 4, April 18, session 1. This is the sas code that we developed in the lab. The first model using REG that was fit treated hours_TV and hours_computer_games as a nominal variable and the second model treated these varaibles as numeric.
  • SAS that does it all (suggestion: run this in sections rather than all at once.

• Homework Number 1:
  • Homework assignment 1.
  • Answer Key.
  • SAS code for solutions
  
  
  
• Homework Number 2
  • Homework assignment 2.
  • Answer Key
  • SAS program for solutions.
  
  
• Homework Number 3:
  • Homework assignment 3. Typo in the homework 3. On problem 1, part e, use Model p. Due date is April 7 (Thursday)
  • Answer key.
  • SAS forHomework assignment 4.
  
  
• Homework Number 4:
  • Homework assignment 4.
  • Answer key.
  • SAS code for this homework.
  • SAS code for exploring random effects (wasn't required for homework but could be useful for future).
  
  
• Final Exam and Projects are due Tuesday May 10, 2011 by 5pm.
  • The final exam and The data.
  • What to include in a Final Project.

• MLbook.sas. Create SAS data for examples in Chapters 4 and 5.
• Ch4_examples.sas. Example 2-level analyses from Chapter 4 (random intercept models).
• Ch5_examples.sas. Example 2-level analyses from Chapter 5 (random intercept and slopes).
• Ch12_examples.sas. Examples analyses from Chapter 12 (longitudinal data analysis), including creating sas dataset.

• School23.sas. SAS code that creates data set and fits models reported in Kreft & de Leeuw.
• school23.dat. Raw data file that is used as input to school23.sas.

• Ones specific to multilevel modeling:
• Centre for Multilevel Modelling. This site includes trainting materials, publications, reviews of multilevel software, data sets, a BBC audio program featuring Harvey Goldstein, and more..
• Tom Snijders' multilevel web-site. This has data & various material that's used in Snijders & Bosker An Introduction to Basic and Advanced Multilevel Modeling as well as other multilevel stuff.
• Scientific software international home page. Student version of HLM program can be downloaded from this site.
• NELS88 data: various data sets used in Kreft & de Leeuw (Introducing heirarchical linear modeling)
• Using SAS PROC MIXED to fit multilevel, heirarchical models, and individual growth models. Downloadable paper by Judith Singer. Other papers also downloadable.
• General ones:
• CIforP.f: A FORTRAN program that computes large sample confidence intervals for a proportion.
• pvalue.f: A FORTRAN program that computes p-values and (bonferroni) critical values for the standard normal, chi-squared, t, and F distributions (and for correlations). For users of PC type computers, pvalue.exe is an executable (i.e. already compiled) program.