Using latent class analysis to test developmental models*1 (original) (raw)
Related papers
Applications of confirmatory latent class analysis in developmental psychology
European Journal of Developmental Psychology, 2005
In the field of developmental, psychology researchers may have several competing theories with respect to their research subject. In this paper an approach will be proposed that can be used to select the best of these theories. It will be shown that a theory can be translated in a constrained latent class model using inequality constraints. This can be done for several (possibly competing) theories. Subsequently, fit-measures can be used to determine which model (and thus which theory) is supported most by the data. The approach will be introduced using data with respect to self-reported child and adult antisocial behaviour. It will be further illustrated using data obtained using the figural intersection task.
Principles and Applications of Latent Class Analysis in Psychological Research
The Irish Journal of Psychology, 2007
This paper provides an overview of latent class analysis (LCA) and its utility in contemporary psychological research. Rather than focussing on the statistical and mathematical underpinnings of this method of analysis, a nontechnical presentation of conceptual issues is offered. The paper therefore and why a psychologist may want to use LCA. A worked example of how some examples from the research literature are presented.
Classes in the balance: Latent class analysis and the balance scale task
Developmental Review, 2007
Latent class analysis (LCA) has been successfully applied to tasks measuring higher cognitive functioning, suggesting the existence of distinct strategies used in such tasks. With LCA it became possible to classify post hoc. This important step forward in modeling and analyzing cognitive strategies is relevant to the overlapping waves model for strategy development . Emerging minds: The process of change in children's thinking. New York: Oxford University Press.]. However, so far, developmental trends were not part of the statistical model. Moreover, the theoretical importance of the fact that a few distinct classes were found was weakened because not all these classes represented pure strategies. To address these two issues, we model the development in class membership by incorporating age and working memory as covariates in the LCA model. Previous findings that the classes are well demarcated are replicated. A developmental sequence is supported by a strong effect of age on class membership and a moderate effect of working memory. Classification itself is hardly affected by the covariates: the problem of difficult to characterize classes remains. Nevertheless, classes describe large proportions of children's responses, classes are robust and fit a developmental trend, and some classes represent mixed rule use. In the discussion, the theoretical status of the overlapping waves model is clarified.
Searching for ideal types: The potentialities of latent class analysis
Typologies play an important role in sociological theory and research. Basic to the use of (ideal) types is the notion that a subject's overt behavior can be conceived of as governed by his/her belonging or closeness to a particular underlying pure type. Many statistical techniques are in use to detect or construct these fundamental types, especially factor analysis. Much less attention has been paid to the possibilities that latent class analysis has to offer. Through an elaborate example, it is shown that the basic ideas of latent class analysis correspond eminently well with the use social scientists make of (ideal) types. Several important extensions of the basic latent class model along with significant new developments are discussed.
European Journal of Developmental Psychology, 2004
The aim of cognitive developmental research is to explain latent cognitive processes or structures by means of manifest variables such as age, cognitive behaviour, and environmental influences. In this paper the usefulness of the latent class regression model is discussed for studying cognitive developmental phenomena. Using this model, the relationships between latent and manifest variables can be explained by means of empirical data without the need of strong a priori assumptions made by a cognitive developmental theory. In the latent class regression model a number of classes are distinguished which may be characterized by particular cognitive behaviour. Environmental influences on cognitive behaviour may vary for different (developmental) classes. An application is given of the latent class regression model to transitive reasoning data. The results showed that a Five-Class model best fitted the data and that the latent classes differ with respect to age, strategy use (cognitive behaviour) and the influence of task characteristics (environmental influences) on the strategy use. The flexibility of the model in terms of mixed measurement levels and treatment of different cognitive variables offers a broad application to several cognitive developmental phenomena.
Frontiers in psychology, 2018
This paper illustrates two psychometric methods, latent class analysis (LCA) and taxometric analysis (TA) using empirical data from research probing children's mental representation in science learning. LCA is used to obtain a typology based on observed variables and to further investigate how the encountered classes might be related to external variables, where the effectiveness of classification process and the unbiased estimations of parameters become the main concern. In the step-wise LCA, the class membership is assigned and subsequently its relationship with covariates is established. This leading-edge modeling approach suffers from severe downward-biased estimations. The illustration of LCA is focused on alternative bias correction approaches and demonstrates the effect of modal and proportional class-membership assignment along with BCH and ML correction procedures. The illustration of LCA is presented with three covariates, which are psychometric variables operationaliz...
Determining Statistical Fit For Categorizing Individuals By Latent Class Analysis
Latent class analysis models have been used successfully to study criminal developmental trajectories, however there is a difference of opinion as to which approach results in the more accurate extraction of latent classes from the data. Traditional practice in research on latent traits uses the classify-analyze paradigm to assign participants to the latent class a priori, but then makes incorrect inferences about the class membership because it ignores the error in the data, the presence of which can cause bias in both the estimate and test statistic. A semiparametric mixed Poisson model incorporates an error term into the model that is specified to be unique to each participant and invariant across time and then uses semiparametric maximum likelihood estimators to produce accurate estimates of the parameters and generate estimates of the points of support beforehand. Additionally, the mixed model can offer an intermittency parameter (that distinguishes periods of non-offending from complete cessation of offending) for greater accuracy of outcome.
A REVIEW ON APPLICATIONS OF LATENT CLASS ANALYSIS
Latent class analysis (LCA) is considered to be an equivalent methodology for Factor Analysis, typically used for dichotomous or polytomous variables. The parameters of interest in a typical problem of latent class analysis are the unobserved proportion or size of the latent classes and the conditional item-response probabilities given the membership in a latent class. Based on the observed data on manifest variables, LCA provides a classification among the population. Manifest variables are called the "indicators" of a particular latent class. The present paper provides a review on the theory of latent class analysis and its wide area of applications in various disciplines such as