scholarly journals Latent Class Analysis for Estimating an Unknown Population Size – with Application to Censuses

2021 ◽  
Vol 37 (3) ◽  
pp. 673-697
Author(s):  
Bernard Baffour ◽  
James J. Brown ◽  
Peter W.F. Smith
Keyword(s):  
Latent Class Analysis ◽  
Population Size ◽  
Latent Class ◽  
Population Estimation ◽  
Class Analysis ◽  
Multiple Sources ◽  
Capture Recapture ◽  
Using Data ◽  
Log Linear ◽  
Us Census

Abstract Estimation of the unknown population size using capture-recapture techniques relies on the key assumption that the capture probabilities are homogeneous across individuals in the population. This is usually accomplished via post-stratification by some key covariates believed to influence individual catchability. Another issue that arises in population estimation from data collected from multiple sources is list dependence, where an individual’s catchability on one list is related to that of another list. The earlier models for population estimation heavily relied upon list independence. However, there are methods available that can adjust the population estimates to account for dependence among lists. In this article, we propose the use of latent class analysis through log-linear modelling to estimate the population size in the presence of both heterogeneity and list dependence. The proposed approach is illustrated using data from the 1988 US census dress rehearsal.

scholarly journals Typology of Customer Retention Schemes in the Private Sports Sector During COVID-19: Analyzing the Behavior of Martial Arts Instructors Using Latent Class Analysis

2021 ◽  
pp. 58
Author(s):  
◽  
Keyword(s):  
Latent Class Analysis ◽  
Martial Arts ◽  
Latent Class ◽  
Customer Retention ◽  
High Volume ◽  
Class Analysis ◽  
Technological Means ◽  
Using Data ◽  
The Impact ◽  
And Training

The COVID-19 pandemic brought new challenges in all aspects of life. It largely brought the sports sector to a halt: major events were postponed or canceled, while gyms and training centers were closed due to repeated lockdowns and social distancing rules and regulations. In the private sports sector, some instructors adopted technological means of maintaining contact with their students in an attempt to retain customers and maintain a high volume of cash flow. Our work focuses on the martial arts (MA) sector in Israel during two crucial periods in 2020: The first lockdown of March through June, when all sports activities were banned, and the period following it, when trainers were allowed to commence training under some regulations. Using data collected from 199 MA instructors, we test for their level and means of engagement with trainees during the lockdown, and the impact these had on customer retention in the period that followed. Using latent class analysis, we establish an empirically based typology of retention schemes (low contact, high contact, and maverick), and test whether these influenced the financial performance of MA studios. Our findings show that the financial damage and the return rate of trainees do not vary between the three types. We offer some insights into the uniqueness of the MA field, and how this may explain these counter-intuitive results.

scholarly journals Multidimensional dependency subgroups in community-dwelling older adults: A latent class analysis

2020 ◽  
Vol 52 (2) ◽  
pp. 101-109
Author(s):  
Kely Rely ◽  
Delfino Vargas-Chanes ◽  
Carmen García-Peña ◽  
Guillermo Salinas-Escudero ◽  
Luis-Miguel Gutiérrez-Robledo ◽  
...  
Keyword(s):  
Older Adults ◽  
Latent Class Analysis ◽  
Latent Class ◽  
Community Dwelling ◽  
Future Research ◽  
Class Analysis ◽  
Class Membership ◽  
Fit Statistics ◽  
Nationally Representative ◽  
Using Data

Objectives: Use latent class analysis (LCA) to identify patterns of multidimensional dependency in a sample of older adults and assess sociodemographic, predictors of class membership. Material and methods: Longitudinal data were usedfrom the Mexican Health and Aging Study (MHAS). 7,920 older adults, 55% women, were recruited. LCA were used to identify meaningful subgroups. LCA was conducted using MPlus version. The final class model was chosen based on the comparison of multiple fit statistics and theoretical parsimony, with models of increasing complexity analyzed sequentially until the best fitting model was identified. Covariates were incorporated to explore the association between these variables and class membership. Results: Three classes groups based on the nine indicators were identified: “Active older adults” was comprised of 64% of the sample participants, “Relatively independent” and “Physically impaired” were comprised of 26% and 10% of the sample. The “Active older adults” profile comprised the majority of respondents who exhibited high endorsement rates across all criteria. The profiles of the “Active older adults” and “Relatively independent” were comparatively more uniform. Finally, respondents belonging to the “Physically impaired” profile, the smallest subgroup, encompassed the individuals most susceptible to a poor dependency profile. Conclusions: These findings highlighted the usefulness to adopt a person-centered approach rather than a variable-centered approach, suggesting directions for future research and tailored interventions approaches to older adults with particular characteristics. Based on patterns of multidimensional dependency, this study identified a typology of dependency using data from a large, nationally representative survey.

scholarly journals Job strain in working retirees in Europe: a latent class analysis

2019 ◽  
Vol 40 (9) ◽  
pp. 2040-2060
Author(s):  
Ellen Dingemans ◽  
Kène Henkens
Keyword(s):  
Latent Class Analysis ◽  
Working Conditions ◽  
Latent Class ◽  
High Strain ◽  
Job Strain ◽  
Economic Status ◽  
Logit Analysis ◽  
Class Analysis ◽  
Using Data

AbstractScientific research has made great progress towards a better understanding of the determinants and consequences of working after retirement. However, working conditions in post-retirement jobs remain largely unexplored. Therefore, using information on working conditions such as job demands, job control and work hours, we investigate whether working retirees can be categorised by the quality of their jobs. Using data from the Survey of Health, Ageing and Retirement in Europe, we perform latent class analysis on a sample of 2,926 working retirees in 11 European countries. The results point to the existence of two sub-groups of working retirees. The first is confronted with high-strain jobs, while the second sub-group participates in low-strain jobs. Subsequent (multi-level) logit analysis undertaken to describe the two classes further suggests that classification in either group is predicted by the socio-economic status of working retirees and by the context of poverty in old age in the countries in question. We conclude that working after retirement in a high-strain job may be conceptually different from working in a low-strain job.

scholarly journals Attitudes towards working in retirement: a latent class analysis of older workers’ motives

2020 ◽  
Author(s):  
Moritz Hess ◽  
Laura Naegele ◽  
Jana Mäcken
Keyword(s):  
Latent Class Analysis ◽  
Older Workers ◽  
Latent Class ◽  
Class Analysis ◽  
Highly Educated ◽  
Work Arrangements ◽  
Employed Women ◽  
Retirement Decisions ◽  
Using Data ◽  
Preferred Hours

Abstract One of the fastest growing labour market groups is working pensioners, meaning those who work past the statutory retirement age whilst receiving a pension. Previous research has investigated the motives of this group and found very heterogeneous reasons for employment in retirement. However, little is known about the expectations and preferred work arrangements of older workers regarding a potential post-retirement employment. Using data from the German survey transitions and old age potential, we explore older workers’ motives, preferences and expectations towards working in retirement. Results show that about half of the respondents plan to work in addition to receiving a pension; however, the share is higher amongst men and those with higher levels of education. The motives for staying in post-retirement employment vary as well: using latent class analysis, we find four distinct patterns of motives that can be classified as (1) financially-driven, (2) status-driven, (3) contact and fun-driven, as well as (4) generativity-driven, underlining the complexity of retirement decisions. Furthermore, preferences regarding arrangements when combining work and retirement are very heterogeneous. Whilst highly educated men want to work as self-employed, women and those with lower qualifications want to stay in their old jobs. Only small differences were found regarding preferred hours (about 17) and days per week (2.24). In summary, the results show that the rapidly growing group of working pensioners and their preferences should be seen as characterised by differences by those responsible for creating these post-retirement employment opportunities.

scholarly journals Measuring efficiency of federally qualified health centers : a multi model approach using data envelopment analysis (DEA) and latent class analysis (LCA)

2021 ◽  
Author(s):  
◽  
Rohith Madhi Reddy
Keyword(s):  
Health Care ◽  
Data Envelopment Analysis ◽  
Latent Class Analysis ◽  
Latent Class ◽  
Health Centers ◽  
Data Envelopment ◽  
Class Analysis ◽  
Federally Qualified Health Centers ◽  
Dea Model ◽  
Using Data

There are 1300 federally qualified health centers (FQHCs) in the United States providing the health care to underserved and uninsured population. These FQHCs serve the patients irrespective of their ability to pay. Using the resources effectively, these FQHCs can provide better health care. In this study of prenatal care, we measure the efficiencies of the FQHCs using data envelopment analysis (DEA). As in service industry, where quality is of at most importance, we used two different DEA approaches considering quality called the Two model DEA approach by (Shimshak, D., and Lenard, M.L.,2007) and Quality adjusted DEA approach by (Sherman, H.D., and Zhu, J, 2006). Efficient frontiers are determined by using these DEA approaches. There are differences that exists across FQHCs due to various factors to include demographic characteristics of patients visited the FQHCs, operational characteristics of health centers. Latent class analysis is performed before performing the DEA to classify the FQHCs into different classes based on the regional and population measures. Four different models namely aggregated Shimshak and Lenard and aggregated Sherman and Zhu models (DEA model is run on the whole sample), partitioned S and L and partitioned S and Z models (DEA model is run individually by class) have been used to determine the efficiencies of the FQHCs. Using the S and L approach, it is found that the FQHCs that formed the efficient frontier is of smaller FQHCs whereas the S and Z approach has a mix of small and large FQHCs. Based on the results determined, more insights are provided on the FQHCs and the models used in the analysis.

scholarly journals A new three-step method for using inverse propensity weighting with latent class analysis

2021 ◽  
Author(s):  
F. J. Clouth ◽  
S. Pauws ◽  
F. Mols ◽  
J. K. Vermunt
Keyword(s):  
Latent Class Analysis ◽  
Latent Class ◽  
Causal Effect ◽  
Measurement Model ◽  
Class Analysis ◽  
Class Membership ◽  
Step Method ◽  
Using Data ◽  
Inference Techniques ◽  
Inverse Propensity Weighting

AbstractBias-adjusted three-step latent class analysis (LCA) is widely popular to relate covariates to class membership. However, if the causal effect of a treatment on class membership is of interest and only observational data is available, causal inference techniques such as inverse propensity weighting (IPW) need to be used. In this article, we extend the bias-adjusted three-step LCA to incorporate IPW. This approach separates the estimation of the measurement model from the estimation of the treatment effect using IPW only for the later step. Compared to previous methods, this solves several conceptual issues and more easily facilitates model selection and the use of multiple imputation. This new approach, implemented in the software Latent GOLD, is evaluated in a simulation study and its use is illustrated using data of prostate cancer patients.

Sign in / Sign up

Export Citation Format

Share Document