CoChat
Sign Up
Cited by 1,204Psychometric Methodologies and TestingBayesian Methods and Mixture ModelsStatistical Methods and Applications

Practitioner’s guide to latent class analysis: Methodological considerations and common pitfalls

Open access
Sinha, Pratik, Calfee, Carolyn S., Delucchi, Kevin L.·2021·Critical Care Medicine
DOI 10.1097/ccm.0000000000004710PMC PMC7746621
Open this paper in CoChat — free account

Abstract

Latent class analysis is a probabilistic modeling algorithm that allows clustering of data and statistical inference. There has been a recent upsurge in the application of latent class analysis in the fields of critical care, respiratory medicine, and beyond. In this review, we present a brief overview of the principles behind latent class analysis. Furthermore, in a stepwise manner, we outline the key processes necessary to perform latent class analysis including some of the challenges and pitfalls faced at each of these steps. The review provides a one-stop shop for investigators seeking to apply latent class analysis to their data.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1097/ccm.0000000000004710

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • LCGA findings should be interpreted with caution, as larger sample sizes are generally preferable when using this technique.

    “LCGA facilitates the classification of individuals according to their most likely trajectory, although findings should be interpreted with caution, as larger sample sizes are generally preferable when using this technique. (Sinha et al., 2021).”

    From Long-term cardiometabolic effects of early institutionalization and foster care: Evidence from the Bucharest Early Intervention Project (2026) · cites this paper as Sinha et al., 2021

    In Step 2: Data Set-up (page not available), the paper calls LCA a large-sample method and says smaller samples, particularly N < 300, yield less reliable results. In What is Latent Class Analysis? (page not available), it describes class-membership probabilities, but it defines its discussion of LCA primarily around cross-sectional models. The cited passages do not specifically establish the sample-size advice for LCGA or trajectory classification. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • In LCA, the probabilities of class membership are obtained, which allows statistical inference when determining the most appropriate number of classes for a population, not clear-cut class assignments as occurs in cluster analysis.

    “In LCA, the probabilities of class membership are obtained, which in turn allows statistical inference when determining the most appropriate number of classes for a population [44], not clear-cut class assignments as occurs in cluster analysis.”

    From Recommendations for empirical syndemics analyses: A stepwise methodological guide (2024) · cites this paper as [44]

    The “LCA vs Cluster Analysis” section says LCA estimates class-membership probabilities rather than simply separating observations into clusters, and that LCA permits statistical inference about the appropriate number of classes. It attributes that inference to fit statistics generated by LCA’s model-based approach, not to the membership probabilities themselves. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • The four-class BMI trajectory model demonstrated reasonable entropy (0.88), suggesting accurate class separation.

    “In this context, although our four-class BMI trajectory model demonstrated reasonable entropy (0.88), suggesting accurate class separation, the results of the LCGA should be interpreted with caution, as a larger sample size would likely provide higher fit accuracy and greater generalizability (Sinha et al., 2021).”

    From Long-term cardiometabolic effects of early institutionalization and foster care: Evidence from the Bucharest Early Intervention Project (2026) · cites this paper as Sinha et al., 2021

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

2 of the 56 references couldn’t be matched to a known paper.

Research works printed but not linked: 5

  1. [20]McLachlan GJ, Lee SX, Rathnayake SI: Finite Mixture Models. In: Annual Review of Statistics and Its Application, Vol 6 Reid N (Ed).
  2. [21]McLachlan G, Peel D: Finite Mixture Models. New York, John Wiley & Sons, 2000
  3. [34]Nylund KL, Asparouhov T, Muthen BO: Deciding on the number of classes in latent class analysis and growth mixture modeling: A Monte Carlo simulation study (vol 14, pg 535, 2007). Structural Equation Modeling-a Multidisciplinary Journal 2008; 15(1): 182– 182
  4. [37]Finch WH, Bronk KC: Conducting Confirmatory Latent Class Analysis Using Mplus. Structural Equation Modeling: A Multidisciplinary Journal 2011; 18(1): 132– 151
  5. [55]McLachlan GJ: On boostrapping the likelihood ratio test statistic for the number of components in a nomal mixture. Journal of the Royal Statistical Society Series C-Applied Statistics 1987; 36(3): 318– 324

Cited by

Sorted by citations

Related

Authors
Sinha, P., Calfee, C. S., & Delucchi, K. L.
Affiliations
University of California, San Francisco (US)
ORCID
Venue
Critical Care Medicine
Publisher
Ovid Technologies (Wolters Kluwer Health)
Published
2020-11-09
Volume
49
Issue
1
Pages
e63-e79
ISSN
0090-3493 (ISSN-L)
DOI
10.1097/ccm.0000000000004710
PMC
PMC7746621
OpenAlex
W3102547229
Cited by
1,204
References
56
Citations by year
2026: 386 · 2025: 382 · 2024: 290 · 2023: 98 · 2022: 35 · 2021: 13
FWCI
7.14
Type
journal article
Language
en
Open access
Locations
  • Critical Care Medicine (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
Funders
  • National Heart, Lung, and Blood Institute (R35HL140026)
  • National Institute of General Medical Sciences (T32GM008440)
Topics
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
  • Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Methods and Mixture Models
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
Keywords
latent class analysis, clustering, stochastic modeling, statistical inference, intensive care, respiratory medicine, methodological pitfalls, data analysis pipeline
MeSH terms
Latent Class Analysis, Data Interpretation, Statistical, Humans, Statistics as Topic

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review