Measurement Error and Misclassification in statistical models: Basics and applications

DATE: 27-31 May 2019 (5 sessions)
TIME: 10:00 - 12:00 (a total of 10 hours)
LOCATION: BCAM Seminar room

In many practical situations the available data at hand do not exactly convey the information one is looking for. Frequently, the variables of interest cannot be observed directly or measured correctly, and one has to be satisfied with so-called surrogates or proxies, i.e., with somehow related, but different variables. Typical examples reach from the error of technical devices measuring, e.g., random measurements, to the handling of complex construct variables like dietary intake or quality of life. If one ignores the difference between the ideal variables and their observable counterparts and just plugs in the surrogates instead of the ideal variables (`naive estimation'), then all the estimators must be suspected to be severely biased, resulting in deceptive conclusions

This problem is referred to as measurement error if the variables are continuous and misclassification if they are discrete variables. In the last years there has been a considerable progress how to adjust for measurement error and misclassification in statistical models.

In this course we give a state-of-the-art overview, where the methods are illustrated by examples form different areas of research.


PROGRAMME:
1. Measurement error, misclassification: General definitions and overview
2. Effect of Misclassification on parameter estimation in statistical models and methods for adjustment
3. Measurement error in predictors in regression models.
4. The simulation and extrapolation (SIMEX) approach as a general tool for handling measurement error and/or misclassification
5. Application and case studies


REFERENCES:
[Carroll, RJ, Ruppert, D, Stefanski, LA and Crainiceanu, CM (2006). Measurement Error in Nonlinear Models. A Modern Perspective. Chapman & Hall, Boca Raton. 2nd edition.

Gustafson, P. Measurement Error and Misclassification in Statistics and Epidemiology. (2004) Impacts and Bayesian Correction, CRC Press, Boca Raton.
Shaw, PA, Deffner, V, Keogh, RH; Tooze, JA Dodd, KW Küchenhoff, H,Kipnis, V; Freedman, LS Epidemiologic analyses with error-prone exposures: review of current practice and recommendations. ANNALS OF EPIDEMIOLOGY, Volume: 28, 11, 821-828

Küchenhoff , H, Mwalili, SM, Lesaffre, E (2006). A general Method for dealing with misclassification in regression: The misclassification SIMEX. Biometrics 62, 85-96.


PREREQUISITES:
Basic statistical knowledge in regression

COURSE MATERIALS:
The slides and the software used in the course are avaliable here.

*Registration is free, but mandatory before May 24th: To sign-up go to https://forms.gle/TCskLEaAnsSQEMP57 and fill the registration form. Student grants are available. Please, let us know if you need support for travel and accommodation expenses when you fill the form.

• BCAMCourse_2019_05_27