April 11, 2006      








Important links

·            Lectures

·           Homework

·          References

·        Lab assignments and related material


Main Texts

·       Goldstein (1995).  Multilevel Statistical  Models.

·       Hox (1995). Applied Multilevel Analysis.


Note: Both texts present a mix of conceptual and quite technical material, all backed by excellent examples.  Concentrate on the concepts and examples, but be sure that you understand the connections between these and the formal models.  Unless you are a Biostatistics graduate student, skip the technical derivations.




Lecture  (T. A. Louis)

·       Course overview and key concepts

·       Basic Multi-level modeling and Shrinkage estimates

·       One-way ANOVA: Variance components and standard errors



·       Look over the course web page

·       Goldstein: Chapters 0, 1, 2

·       Hox:  1

·       Download WinBUGS and begin reading the manual

·       Singer J (1998). Using SAS PROC MIXED to Fit Multilevel Models, Hierarchical Models and Individual Growth

·       Models. Journal of Educational and Behavioral Statistics, 24(4): 323-335.

·       Diez-Roux  A (2000).  Multilevel Analysis in Public Health Research.  Ann. Rev. Public Health. 21:171-92.


Homework #1:  (due Thursday, April 6th)




02. THURSDAY, MARCH 30th  

Lecture (T. A. Louis)

·       Weighted means

·       More general linear MLMs

·       Examples of improving estimates



·        Jones AP, Jørgensen SH (2003). The use of multilevel models for the prediction of road accident outcomes. Accident Analysis and Prevention, 35: 59–69.

·       Goldstein on WinBugs

·        Rauh VA, Andrews HF, Garfinkel RS (2001). The Contribution of Maternal Age to Racial Disparities in Birthweight: A Multilevel Perspective. Am.  J. Public Health, 91: 1815-1824.

·       Stanek EJ, Shetterley SS, Allen LH, Pelto GH, Chavez A (1989).  A cautionary note on the use of autoregressive models in analysis of longitudinal data. Statistics in Medicine, 8: 1523-1528.




Lecture (T. A. Louis)

·       Examples: Teacher Expectancy; Diabetes control



·       Goldstein: 05 07

·       Hox: 2

·       Hofer et al. (1999). The unreliability of individual physician “report cards” for assessing the costs and quality of care of a chronic disease. JAMA, 281: 2098-2105.

·       Normand et al. (1996). Using admission characteristics to predict short-term mortality from myocardial infarction in elderly patients. Results from the Cooperative Cardiovascular Project. JAMA, 125: 1322-1328.

·       Normand et al. (1997). Statistical Methods for Profiling Providers of Medical Care: Issues and Applications. JASA, 92: 803-814.   




Lecture (T. A. Louis)

·        Non-linear models: Conditional and Marginal

·        Logistic/binary models

·        Crossover study


Homework #2:  (due Tuesday, April 18th)



·       Heagerty PJ, Zeger SL (1999). Marginalized Multi-level Models and Likelihood Inference. Statistical Science, 15: 1–26. (advanced).

·       Palmer et al. (1996).  Results from a randomized controlled trial in 16 ambulatory care group practices. Medical Care, 34, \#9: (Several articles).



05. TUESDAY, APRIL 11th 

Lecture (M. Griswold)

·       Non-linear models, continued

·       GEE



·       Goldstein: 06 08

·       Hox: 4  

·       Merlo J, Lynch JW, Yang M, Lindström M, Östergren PO, Niels Kristian Rasmusen NK, Lennart Råstam L. (2003). Effect of Neighborhood Social Participation on Individual Use of Hormone Replacement Therapy and Antihypertensive Medication: A Multilevel Analysis.   AJE, 157: 774-783.




Lecture (T. A. Louis and or Mike Griswold)

·       British Social Attitudes Survey

·       Bayesian analysis and its relation to Multi-level Models



·       Liu J, Louis TA, Pan W, Ma J, Collins A (2003).   Methods for estimating and interpreting provider-specific, standardized mortality ratios.  Health Services and Outcomes Research Methodology. 4: 135-149.

·       Diehr P, Yanez D, Ash A, Hornbrook M, Lin DY (1999). Methods for analyzing health care utilization costs. Ann. Rev. Public Health, 20: 125-144.


Homework #3:  (due Tuesday, April 25th).




Lecture (T. A. Louis)

·       Bayesian Analysis, continued



·       Goldstein: 10

·       Hox: 4.1

·       Affleck G, Tennen H, Keefe FJ, Lefebvre JC, Kashikar-Zuck S, Wright K, Starr K, Caldwell DS (1999). Everyday life with osteoarthritis or rheumatoid arthritis: independent effects of disease and gender on daily pain, mood, and coping. Pain, 83: 601-609. 

·       Finch et al. (2001). Substance use during pregnancy in the State of California USA. Social Science and Medicine




 Lecture (T. A. Louis)

·       Ranking

·       Discuss Midterm

·       Brief discussion of term project



·       O'Campo P (2003). Invited Commentary: Advancing Theory and Methods for Multilevel Models of Residential Neighborhoods and Health.   AJE, 157: 9-13.

·        Peters ML, Sorbi MJ, Kruise DA, Kerssens JJ,  Verhaak PFM, Bensing JM (2000). Electronic diary assessment of pain, disability and psychological adaptation in patients differing in duration of pain. Pain, 84:181-192.

·        Sampson RJ, Raudenbush SW, Earls F (1997). Neighborhoods and Violent Crime: A Multilevel Study of Collective  Efficacy. Science, 277: 918-924.


Homework #4: (due Tuesday, May 2nd).



09.  TUESDAY, April 25th  

Lecture (T. A. Louis)

·       Ranking continued

·       Introduction to Health Care Profiling

·       Case Studies: Normand, USRDS, Length of Stay

·       Discuss Term Project



·       Goldstein: 11

·       Hox: 3

·       Diggle et al. (1995). Statistical Issues in the analysis of disease risk near a point source using individual or spatially aggregated data.  Journal of Epidemiology and Community Health, 49: S20-S27.

·       Shen W, Louis TA (2000). Triple-Goal estimates for Disease Mapping. Statistics in Medicine, 19: 2295-2308. 

 ·        Louis TA, Shen W (1999). Innovations in Bayes and empirical Bayes methods: Estimating parameters, populations and ranks. Statistics in Medicine,

      18: 2493-2505


Homework: Project



In-class EXAM: 3:30--4:50 (ending at 5:00 sharp!)

·       Open book; open notes

·       3 problems; approximately 30 minutes to read and write down answers; 50 minutes to think

·       Problems will address issues such as:

-      Role of MLMs;  when and why to use, when/why not needed

-      Writing down a model; interpreting coefficients

-      Shrinkage estimation

-      Linear and logit linear models

-      Basic computations




·       To be assigned


Homework: Prepare project proposal



11. TUESDAY, MAY 2nd   

Lecture (M. Griswold)

·        Two-stage modeling and joint modeling



·       To be assigned





12. THURSDAY, MAY 4th 

Lecture (F. Dominici)

·       Applications of Multi-level Models to Spatial Epidemiology

1.    Spatial random effects

2.    Mapping

·       Case Studies: Pellegra, Scottish Lip cancer




·        Wakefield, J (2003). Sensitivity Analyses for Ecological Regression. Biometrics 59, 9-17.

·        Wakefield, J (2003). Ecological Inference in Epidemiology.  Presentation at the 2003 Meeting of the International Biometrics Society, Eastern North American Region.


Homework: Project



13. TUESDAY, MAY 9th 

Lecture (F. Dominici)

·       The National Mortality and Morbidity Air Pollution Study (NMMAPS) (Francesca Dominici)



·       Goldstein: 03 04

·       Hox:

·        Dominici F, McDermott A, Zeger SL, Samet JM (2003). National Maps of the Effects of Particulate Matter on Mortality: Exploring Geographical Variation.  Environmental Health Perspectives,  111: 39-43

·        Samet JM, Dominici F,  Curriero F,  Coursac I, Zeger SL 2002). Particulate Air Pollution and Mortality: Findings from 20 U.S. Cities. New England Journal of Medicine, 343: 1742-1757.



Homework: Project



14. THURSDAY, MAY 11th

 Lecture (M.  Griswold)

·       Design:  basic and advanced

·       Design example, tba



·        Rabe-Hesketh S, Yang s, Pickles A (2001). Multilevel models for censored and latent responses. Statistical Methods in Medical Research, 10: 409–427.

·        Statistical Society Working Party on Performance Monitoring in the Public Services (2003). Performance Indicators: Good, Bad, and Ugly. Royal Statistical Society.

·       Vaupel JW, Yashin AI (1985). Heterogeneity's ruses: Some surprising effects  of selection on population dynamics.  Am Statistician 39: 176-185. 


Homework: Project



 15. TUESDAY, MAY 16th

 Lecture (T. A. Louis)

·       Robustness and efficiency

o      Working Independence versus non-independence

o      Weighting trade-offs

o      Alternatives to the Gaussian distribution for REs



·       Goldstein: 09

·       Hox: 5

·       Dreams Design Example


Homework: Project


16. THURSDAY, MAY 18th

 Lecture (T. A. Louis)

·       Missing data    

·       If time: Measurement error: Basic types, Attenuation/de-attenuation, shape change

·       Coda


Homework: Project due by midnight, Friday, May 19th.