Examining Ways to Handle Non-Random Missingness in CEA through Econometric and Statistics Lenses

Missing data in experiments can bias estimates if not appropriately addressed. This is of particular concern in cost-effectiveness analysis where bias in either the cost or effect estimate could bias the entire cost effectiveness estimate. Complicated experimental designs, such as cluster randomized trials (CRT) or longitudinal data call for even greater care when addressing missingness. The purpose of this paper is to compare two sample selection models designed to address bias resulting from non-random missingless when applied to a longitudinal CRT. From the statistics literature we consider the Diggle Kenward model and from the econometrics literature we consider the Heckman model. Both of these models will be used to analyze the twelve-month outcomes of a worksite weight loss program, as well as used in a simulation experiment.


Issue Date:
2015
Publication Type:
Conference Paper/ Presentation
PURL Identifier:
http://purl.umn.edu/205690
Total Pages:
32




 Record created 2017-04-01, last modified 2017-08-28

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)