Optimizing Count Responses in Surveys: A Machine-learning Approach

Accepted

Journal Article

© 2018, The Author(s) 2018. Count responses with grouping and right censoring have long been used in surveys to study a variety of behaviors, status, and attitudes. Yet grouping or right-censoring decisions of count responses still rely on arbitrary choices made by researchers. We develop a new method for evaluating grouping and right-censoring decisions of count responses from a (semisupervised) machine-learning perspective. This article uses Poisson multinomial mixture models to conceptualize the data-generating process of count responses with grouping and right censoring and demonstrates the link between grouping-scheme choices and asymptotic distributions of the Poisson mixture. To search for the optimal grouping scheme maximizing objective functions of the Fisher information (matrix), an innovative three-step M algorithm is then proposed to process infinitely many grouping schemes based on Bayesian A-, D-, and E-optimalities. A new R package is developed to implement this algorithm and evaluate grouping schemes of count responses. Results show that an optimal grouping scheme not only leads to a more efficient sampling design but also outperforms a nonoptimal one even if the latter has more groups.

Full Text

Duke Authors

Cited Authors

  • Fu, Q; Guo, X; Land, KC

Published Date

  • January 1, 2018

Published In

Electronic International Standard Serial Number (EISSN)

  • 1552-8294

International Standard Serial Number (ISSN)

  • 0049-1241

Digital Object Identifier (DOI)

  • 10.1177/0049124117747302

Citation Source

  • Scopus