Introduction to health measurement

This is a series of lectures about epidemiology, health measures, and the analysis of measurement instrument assessing health-related quality of life.

Lectures

1. Epidemiology and Clinical Trials: A Methodological Approach. screen | print
   Short overview of epidemiology (types of design with their pros and cons, concept of causality, common errors in the literature) and RCTs (how they differ from observational studies, key concepts to ensure the validity of the findings, CONSORT statement).
2. Biostatistics: A Refresher. screen | print
   A survey of common analysis techniques for group comparisons (difference in central tendencies, measures of association and concordance, regression).
3. Introduction to psychometrics. screen | print
   Summary of the main approaches to scale construction, taxonomy of related concepts (reliability, validity).
4. Assessing the psychometric properties of a questionnaire. screen | print
   Illustration of basic factor analysis and IRT-related methods to validate a measurement instrument, using a case study on anxiety from the PROMIS project.

Practicals

The tutorial focus on the low baby weight study discussed during the second lecture. Analysis are done using the R statistical software which can be downloaded from CRAN. Additional packages are required: rms (depends on Hmisc), coin, effects (depends on colorspace), and vcd.

The R code can be viewed as an HTML page (R script here), and is commented in the following document: lwb.R: Code explained (PDF, 17 pp.).

Bibliography

Here are two papers on predictive modeling in biomedical research:

• Harrell, F.E. Jr, Margolis, P.A., Gove, S., Mason, K.E., Mulholland, E.K., Lehmann, D., Muhe, L., Gatchalian, S., and Eichenwald, H.F.. (1998). Development of a clinical prediction model for an ordinal outcome: the World Health Organization Multicentre Study of Clinical Signs and Etiological agents of Pneumonia, Sepsis and Meningitis in Young Infants. WHO/ARI Young Infant Multicentre Study Group. Statistics in Medicine, 17(8): 909-44.
• Harrell, F.E. Jr, Lee, K.L., and Mark, D.B. (1996). Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Statistics in Medicine, 15(4): 361-87.

Additional recommended readings: Harrell, F. Regression Modeling Strategies, Springer, 2001, and/or Steyerberg, EW, Clinical Prediction Models, Springer, 2009.; Senn, S. Statistical Issues in Drug Development, Wiley, 2009 (2nd ed.).

There was a dedicated issue on Applying Item Response Theory to Enhance Health Outcomes Assessment in the Quality of Life Research journal (2007); the list of articles is available here. There are many good textbooks, including:

• Fayers, PM and Machin, D. Quality of Life: The Assessment, Analysis and Interpretation of Patient-Reported Outcomes, Wiley, 2007.
• Streiner, DL and Norman, GR. Health Measurement Scales, Oxford University Press, 2008 (4th ed.).
• Walters, SJ. Quality of Life Outcomes in Clinical Trials and Health-Care Evaluation, Wiley, 2009.
• Devet, HCV, Terwee, CB, Mokkink, LB and Knol, DL. Measurement in Medicine, Cambridge University Press, 2011.