Performance Comparison of Linear and Nonlinear Feature Selection Methods for the Analysis of Large Survey Datasets

Resource type
Date created
2019-03-21
Authors/Contributors
Abstract
Large survey databases for aging-related analysis are often examined to discover key factors that affect a dependent variable of interest. Typically, this analysis is performed with methods assuming linear dependencies between variables. Such assumptions however do not hold in many cases, wherein data are linked by way of non-linear dependencies. This in turn requires applications of analytic methods, which are more accurate in identifying potentially non-linear dependencies. Here, we objectively compared the feature selection performance of several frequently-used linear selection methods and three non-linear selection methods in the context of large survey data. These methods were assessed using both synthetic and real-world datasets, wherein relationships between the features and dependent variables were known in advance. In contrast to linear methods, we found that the non-linear methods offered better overall feature selection performance than linear methods in all usage conditions. Moreover, the performance of the non-linear methods was more stable, being unaffected by the inclusion or exclusion of variables from the datasets. These properties make non-linear feature selection methods a potentially preferable tool for both hypothesis-driven and exploratory analyses for aging-related datasets.
Document
Published as
Krakovska O, Christie G, Sixsmith A, Ester M, Moreno S (2019) Performance comparison of linear and non-linear feature selection methods for the analysis of large survey datasets. PLoS ONE 14 (3): e0213584. DOI: 10.1371/journal.pone.0213584
Publication title
PLoS ONE
Document title
Performance comparison of linear and non-linear feature selection methods for the analysis of large survey datasets
Date
2019
Volume
14
Issue
3
Publisher DOI
10.1371/journal.pone.0213584
Copyright statement
Copyright is held by the author(s).
Scholarly level
Peer reviewed?
Yes
Language
Member of collection
Attachment Size
journal.pone_.0213584.pdf 1.64 MB