Maximum entropy in the mean methods in propensity score matching for interval and noisy data

In this paper, we propose maximum entropy in the mean methods for propensity score matching classification problems. We provide a new methodological approach and estimation algorithms to handle explicitly cases when data is available: (i) in interval form; (ii) with bounded measurement or observatio...

Descripción completa

Detalles Bibliográficos
Autores: Smale, A., Bagdadli, S., Cotton, R., Dello Russo, S., Dickmann, M., Dysvik, A., Gianecchini, M., Ka¿e, R., Lazarova, M., Astrid, R., Rozo, P., Verbruggen, M.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2018
País:Colombia
Institución:Universidad de los Andes
Repositorio:Séneca: repositorio Uniandes
Idioma:inglés
OAI Identifier:oai:repositorio.uniandes.edu.co:1992/47072
Acceso en línea:http://hdl.handle.net/1992/47072
https://www.tandfonline.com/doi/abs/10.1080/03610926.2018.1497656
Access Level:acceso abierto
Palabra clave:Propensity score matching
Observational studies
Maximum entropy in the mean
Data with bounded errors
Interval data
Descripción
Sumario:In this paper, we propose maximum entropy in the mean methods for propensity score matching classification problems. We provide a new methodological approach and estimation algorithms to handle explicitly cases when data is available: (i) in interval form; (ii) with bounded measurement or observational errors; or (iii) both as intervals and with bounded errors. We show that entropy in the mean methods for these three cases generally outperform benchmark error-free approaches.