Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387323217> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4387323217 abstract "Researchers in the behavioral and social sciences often use linear discriminant analysis (LDA) for predictions of group membership (classification) and for identifying the variables most relevant to group separation among a set of continuous correlated variables (description). In this paper, we compare existing linear classification algorithms for nonnormally distributed multivariate repeated measures data in a simulation study based on Likert-type data. It is widely accepted that, as a multivariate technique, LDA provides more accurate results by examining not only the relationship between the independent and dependent variables but also the relationships within the independent variables themselves. In educational and psychological research and other disciplines, longitudinal data are often collected which provide additional temporal information. However, linear classification methods for repeated measures data are rarely discussed in the literature despite these potential applications. These methods are more sensitive to actual group differences by taking the complex correlations between time points and variables into account, when compared to analyzing the data at each time point separately. Moreover, data in the behavioral and social sciences rarely fulfill the multivariate normality assumption, so we consider techniques that additionally do not require multivariate normality. The results show that methods which include multivariate outlier removal before parameter estimation as well as robust parameter estimation using generalized estimating equations (GEE) perform better than the standard repeated measures LDA which assumes multivariate normality. The results of the longitudinal support vector machine (SVM) were not competitive." @default.
- W4387323217 created "2023-10-04" @default.
- W4387323217 creator A5003763367 @default.
- W4387323217 creator A5082173616 @default.
- W4387323217 creator A5087165669 @default.
- W4387323217 date "2023-09-29" @default.
- W4387323217 modified "2023-10-05" @default.
- W4387323217 title "Linear classification methods for multivariate repeated measures data -- a simulation study" @default.
- W4387323217 doi "https://doi.org/10.48550/arxiv.2310.00107" @default.
- W4387323217 hasPublicationYear "2023" @default.
- W4387323217 type Work @default.
- W4387323217 citedByCount "0" @default.
- W4387323217 crossrefType "posted-content" @default.
- W4387323217 hasAuthorship W4387323217A5003763367 @default.
- W4387323217 hasAuthorship W4387323217A5082173616 @default.
- W4387323217 hasAuthorship W4387323217A5087165669 @default.
- W4387323217 hasBestOaLocation W43873232171 @default.
- W4387323217 hasConcept C105795698 @default.
- W4387323217 hasConcept C161584116 @default.
- W4387323217 hasConcept C163175372 @default.
- W4387323217 hasConcept C188321436 @default.
- W4387323217 hasConcept C2776157432 @default.
- W4387323217 hasConcept C33923547 @default.
- W4387323217 hasConcept C38180746 @default.
- W4387323217 hasConcept C41008148 @default.
- W4387323217 hasConcept C58489278 @default.
- W4387323217 hasConcept C69738355 @default.
- W4387323217 hasConcept C79337645 @default.
- W4387323217 hasConceptScore W4387323217C105795698 @default.
- W4387323217 hasConceptScore W4387323217C161584116 @default.
- W4387323217 hasConceptScore W4387323217C163175372 @default.
- W4387323217 hasConceptScore W4387323217C188321436 @default.
- W4387323217 hasConceptScore W4387323217C2776157432 @default.
- W4387323217 hasConceptScore W4387323217C33923547 @default.
- W4387323217 hasConceptScore W4387323217C38180746 @default.
- W4387323217 hasConceptScore W4387323217C41008148 @default.
- W4387323217 hasConceptScore W4387323217C58489278 @default.
- W4387323217 hasConceptScore W4387323217C69738355 @default.
- W4387323217 hasConceptScore W4387323217C79337645 @default.
- W4387323217 hasLocation W43873232171 @default.
- W4387323217 hasOpenAccess W4387323217 @default.
- W4387323217 hasPrimaryLocation W43873232171 @default.
- W4387323217 hasRelatedWork W1984050705 @default.
- W4387323217 hasRelatedWork W1997576769 @default.
- W4387323217 hasRelatedWork W2186366225 @default.
- W4387323217 hasRelatedWork W2783143617 @default.
- W4387323217 hasRelatedWork W2796824299 @default.
- W4387323217 hasRelatedWork W3193432347 @default.
- W4387323217 hasRelatedWork W4252446055 @default.
- W4387323217 hasRelatedWork W4309298396 @default.
- W4387323217 hasRelatedWork W596304944 @default.
- W4387323217 hasRelatedWork W2546755982 @default.
- W4387323217 isParatext "false" @default.
- W4387323217 isRetracted "false" @default.
- W4387323217 workType "article" @default.