Latent class analysis

Vermunt, Jeroen K.

doi:10.1016/b978-0-12-818630-5.10075-2

Cited by 3 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LCA uses an algorithm where it analyses the responses of individuals in a set of variables. After this, it produces possible homogeneous subgroups that classify the population [29] . One of LCA's applications is through multigroup analysis.…”

Section: Latent Class Analysis (Lca) and Its Application In Education...mentioning

confidence: 99%

Exploring Latent Class Profiles of Mathematics Performance among Filipino Students: Insights from PISA 2022 Using Growth Mindset Indicators and Group Comparison Analysis

Chavez

2024

Preprint

View full text Add to dashboard Cite

This study explored the growth mindset among Filipino students and its impact on mathematics performance. It utilized the data from the PISA 2022 assessment. Growth mindset has been illustrated as the belief that abilities can be developed through effort. It is identified as a critical factor that influences educational outcomes. The primary aim of this study is to identify distinct latent class profiles based on growth mindset indicators among Filipino students. Also, it examined the relationship between these profiles and mathematics performance. The study is grounded in the growth mindset theory. This theory posits that students' beliefs about their intelligence and abilities can significantly influence their academic performance. Growth mindset is classified as a concept of multidimensional because it encompasses mental, physical, emotional, and spiritual aspects. Thus, this is also explored. Data from 6,791 Filipino students who participated in PISA 2022 were analyzed. The study employed Latent Class Analysis (LCA) to identify distinct growth mindset profiles based on student responses to mindset-related questions. Following the identification of profiles, ANOVA was used to determine differences in mathematics performance among the identified groups. Based on the results, there were three latent classes were identified: Limitation Acceptors, Optimistic Learners, and Mindset Explorers. Limitation Acceptors (50% of the students) predominantly believed in fixed intelligence and performed lower in mathematics. Optimistic Learners (17%) exhibited a strong growth mindset and achieved significantly higher mathematics scores. Mindset Explorers (33%) displayed ambivalence towards fixed and growth mindset statements, with mathematics performance similar to Limitation Acceptors. ANOVA results indicated a significant difference in mathematics performance among the three groups, with Optimistic Learners outperforming the other two.

show abstract

Section: Latent Class Analysis (Lca) and Its Application In Education...mentioning

confidence: 99%

Exploring Latent Class Profiles of Mathematics Performance among Filipino Students: Insights from PISA 2022 Using Growth Mindset Indicators and Group Comparison Analysis

Chavez

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Moderated latent variables analysis is performed to explore or test the assumption that parameters differ across unobserved segments or categories of moderator variables. When variables are categorical, this approach to data analysis is termed Latent Class Analysis (LCA; Lazarsfeld, 1950; for overviews, see Clogg, 1995;Vermunt, 2010; for recent applications, see Karim et al, 2023, Wiedermann & von Eye, 2016 for the following, see also Clogg & Goodman, 1985).…”

Section: Latent Class Analysis In Person-oriented Researchmentioning

confidence: 99%

“…Based on Clogg (1995, pp. 317 -318; see also Vermunt, 2010), the latent class model for categorical variables can be described as follows. Let y indicate a cell of the crossclassification of J observed variables, and let pY (y) be the joint density of these variables.…”

Section: Latent Class Analysis In Person-oriented Researchmentioning

confidence: 99%

Latent variables analysis in person-oriented research

Eye

Wiedermann

Weber

2023

jpor

View full text Add to dashboard Cite

In this article, we demonstrate that latent variable analysis can be of great use in person-oriented research. Starting with exploratory factor analysis of metric variables, we present an example of the problems that come with generalization of aggregate-level results to subpopulations. Oftentimes, results that are valid for populations do not represent subpopulations at all. This applies to confirmatory factor analysis as well. When variables are categorical, latent class analysis can be used to create latent variables that explain the covariation of observed variables. In an example, we demonstrate that latent class analysis can be applied to data from individuals, when the number of observation points is sufficiently large. In each case of latent variables analysis, the latent variables can be considered moderators of the structure of covariation among observed variables.

show abstract

Adaptation of Artificial Intelligence Literacy Scale: Latent Profile Analysis

Kırksekiz,

Yıldız,

Kıyıcı

et al. 2024

SUJE

View full text Add to dashboard Cite

Artificial intelligence literacy is vital for individuals' adaptation to the future workforce and societal changes by enabling them to understand and effectively use AI technologies and critically evaluate their impact on society. In this study, the validity and reliability of the artificial intelligence literacy scale in Turkish language were tested and the latent profiles of the students were determined. This methodological study was carried out with a total of 729 students between December 2023 and February 2024. Validity and reliability analyses were conducted with SPSS 27 and AMOS 24, and latent profile analysis was handled with R programming language. According to the results of the CFA analysis of the Artificial Intelligence Literacy Scale, the fit indices were found to be significant (X²/sd= 3.832, RMSEA=.062, CFI=.949, AGFI=.933, GFI=.960, NFI=.949, TLI=.928, IFI=.916). Considering the Cronbach Alpha value of the scale consisting of 4 sub-dimensions and 12 items, the internal consistency coefficientwas found to be 0.814. Since the lowest BIC value in the latent profile analysis was found in the VVV model, the VVV model was considered as the appropriate one in the study, and the class analyses were carried out through this model. With the LPA analysis, it was designated that the scale was divided into 3 classes. It was determined that the Artificial intelligence literacy scale is a valid and reliable measurement tool. After latent profile analysis, it was found out that the scale was divided into 3 classes.

show abstract

Latent class analysis

Cited by 3 publications

References 28 publications

Exploring Latent Class Profiles of Mathematics Performance among Filipino Students: Insights from PISA 2022 Using Growth Mindset Indicators and Group Comparison Analysis

Exploring Latent Class Profiles of Mathematics Performance among Filipino Students: Insights from PISA 2022 Using Growth Mindset Indicators and Group Comparison Analysis

Latent variables analysis in person-oriented research

Adaptation of Artificial Intelligence Literacy Scale: Latent Profile Analysis

Contact Info

Product

Resources

About