Back to Search
Start Over
Mediation analysis for count and zero-inflated count data
- Source :
- Statistical methods in medical research, vol 27, iss 9
- Publication Year :
- 2017
- Publisher :
- SAGE Publications, 2017.
-
Abstract
- Different conventional and causal approaches have been proposed for mediation analysis to better understand the mechanism of a treatment. Count and zero-inflated count data occur in biomedicine, economics, and social sciences. This paper considers mediation analysis for count and zero-inflated count data under the potential outcome framework with nonlinear models. When there are post-treatment confounders which are independent of, or affected by, the treatment, we first define the direct, indirect, and total effects of our interest and then discuss various conditions under which the effects of interest can be identified. Proofs are provided for the sensitivity analysis proposed in the paper. Simulation studies show that the methods work well. We apply the methods to the Detroit Dental Health Project’s Motivational Interviewing DVD trial for the direct and indirect effects of motivational interviewing on count and zero-inflated count dental caries outcomes.
- Subjects :
- Male
Michigan
Outcome Assessment
Epidemiology
Motivational interviewing
01 natural sciences
010104 statistics & probability
sensitivity analysis
0504 sociology
Health Information Management
Models
Outcome Assessment, Health Care
Statistics
Child
Dental health
05 social sciences
Confounding
Statistical
Outcome (probability)
Zero (linguistics)
Infectious Diseases
Child, Preschool
Public Health and Health Services
Female
Psychology
Algorithms
Count data
post-treatment confounder
Statistics and Probability
Statistics & Probability
Motivational Interviewing
Dental Caries
Article
Behavioral and Social Science
Humans
Dental/Oral and Craniofacial Disease
0101 mathematics
Preschool
Biomedicine
Models, Statistical
business.industry
sequential ignorability
050401 social sciences methods
Health Care
Nonlinear Dynamics
Total effects
Direct effect
business
indirect effect
Subjects
Details
- ISSN :
- 14770334 and 09622802
- Volume :
- 27
- Database :
- OpenAIRE
- Journal :
- Statistical Methods in Medical Research
- Accession number :
- edsair.doi.dedup.....df54b40de078fec7bbed2ae9c26a2033