Menu Content/Inhalt
Seminars Print
previous year previous month next month next year
See by year See by month See by week See Today Search Jump to month
Uschi Mueller-Harknett, Texas A&M University Print
Friday, 27 April 2012, 14:30 - 15:30

Uschi Mueller-Harknett, Texas A&M University


Complete Case Analysis Revisited

Abstract: The fastest and simplest method of dealing with missing data is listwise deletion, i.e. using only cases that are completely observed. It is well known, though, that a statistical analysis based on those data does not always perform well. Approaches which impute missing values often give better results. However, we can identify situations where a complete case analysis is appropriate and sometimes even optimal.

I present a general method for obtaining limiting distributions of complete case statistics for missing data models from those of the corresponding statistics when all data are observed. This provides a convenient method of adapting established methods without (reproducing) lengthy proofs.

The methodology is illustrated by analyzing inference procedures for partially linear regression models with responses missing at random: we derive asymptotically efficient estimators of the slope parameter and present an asymptotically distribution free test for fitting a normal distribution to the errors.

Location: Plaine, building NO, 9th floor, salle des Professeurs
Contact: Jacqueline Bottemanne, This e-mail address is being protected from spam bots, you need JavaScript enabled to view it