A Generalized Dynamic Factor Model for Panel Data: Estimation with a Two-Cycle Conditional Expectation-Maximization Algorithm

University of Massachusetts at Amherst Department of Resource Economics Working Paper No. 2013-1

43 Pages Posted: 18 Jan 2013

See all articles by Nikolaos Zirogiannis

Nikolaos Zirogiannis

University of Massachusetts at Amherst - Department of Resource Economics

Yorghos Tripodis

Boston University - School of Public Health, Department of Biostatistics

Date Written: January 16, 2013

Abstract

We develop a generalized dynamic factor model for panel data with the goal of estimating an unobserved index. While similar models have been developed in the literature of dynamic factor analysis, our contribution is threefold. First, contrary to simple dynamic factor analysis where multiple attributes of the same subject are measured at each time period, our model also accounts for multiple subjects. It is therefore suitable to a panel data framework. Second, our model estimates a unique unobserved index for every subject for every time period, as opposed to previous work where a temporal index common to all subjects was used. Third, we develop a novel iterative estimation process which we call the Two-Cycle Conditional Expectation-Maximization (2CCEM) algorithm and is flexible enough to handle a variety of different types of datasets. The model is applied on a panel measuring attributes related to the operation of water and sanitation utilities.

Keywords: Dynamic Factor Models, EM algorithm, Panel Data, State-Space models, IBNET

JEL Classification: C32, C33, C51, Q25

Suggested Citation

Zirogiannis, Nikolaos and Tripodis, Yorghos, A Generalized Dynamic Factor Model for Panel Data: Estimation with a Two-Cycle Conditional Expectation-Maximization Algorithm (January 16, 2013). University of Massachusetts at Amherst Department of Resource Economics Working Paper No. 2013-1, Available at SSRN: https://ssrn.com/abstract=2201608 or http://dx.doi.org/10.2139/ssrn.2201608

Nikolaos Zirogiannis (Contact Author)

University of Massachusetts at Amherst - Department of Resource Economics ( email )

Department of Operations and Information Managemen
Amherst, MA 01003
United States
413.545.5736 (Phone)
413.545.5853 (Fax)

HOME PAGE: http://people.umass.edu/nzirogia/index.html

Yorghos Tripodis

Boston University - School of Public Health, Department of Biostatistics ( email )

715 Albany Street
Boston, MA 02118
United States
617.638.5488 (Phone)

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
144
Abstract Views
897
rank
230,836
PlumX Metrics