Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/88203
PIRA download icon_1.1View/Download Full Text
Title: Optimizing count responses in surveys : a machine-learning approach
Authors: Fu, Q
Guo, X 
Land, KC
Issue Date: 1-Aug-2020
Source: Sociological methods and research, 1 Aug. 2020, v. 49, no. 3, p. 637-671
Abstract: 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.
Keywords: Survey methodology
Optimality
Experimental design
Search algorithm
Machine learning
Fisher information
Zero inflation
Right censoring
Poisson distribution
Publisher: SAGE Publications
Journal: Sociological methods and research 
ISSN: 0049-1241
EISSN: 1552-8294
DOI: 10.1177/0049124117747302
Rights: This is the accepted version of the publication Fu, Q., Guo, X., & Land, K. C., Optimizing count responses in surveys: A machine-learning approach, Sociological Methods and Research (Volume: 49 and issue: 3) pp. 637-671. Copyright © 2018 (The Author(s)). DOI: 10.1177/0049124117747302 which is published by Sage and is available at https://journals.sagepub.com/doi/10.1177/0049124117747302
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
SMR20170809.pdfPre-Published version976.37 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Final Accepted Manuscript
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

43
Citations as of May 22, 2022

Downloads

14
Citations as of May 22, 2022

SCOPUSTM   
Citations

4
Citations as of May 27, 2022

WEB OF SCIENCETM
Citations

3
Citations as of May 26, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.