Latent variable mixture modelling of treated drug misuse in Ireland

This study provides analyses and profiles of illegal drug usage in the Republic of Ireland. Two questions are addressed: a) can individuals be grouped into homogeneous classes based upon their type of drug consumption, and b) how do these classes differ in terms of other key background variables? The data reported in this study is from the National Drug Treatment Reporting System database in the Republic of Ireland. All analyses were carried out in collaboration with the Drug Misuse Research Division (the Irish REITOX / EMCDDA focal point). This database contains information on all 6994 individuals who received treatment for drug problems in the Republic of Ireland during 2000. The analysis was conducted in four steps. First, a single class model was examined in order to establish the respective probability associated with each drug type. Second, a series of unconditional latent class models was examined. This was done to establish the optimal number of latent classes required to describe the data, and to establish the relative size of each latent class. From this analysis the conditional probabilities for each individual, within a given class, were examined for typical profiles. Third, a series of conditional models was then examined in terms of key predictors (age and early school leavers). This analysis was conducted using MPlus 2.13. In the final stage of the research, the parameter estimates obtained from the multinomial logistic regression model (that was previously used to express the probability of an individual being in a given latent class, conditional on a series of covariates) were graphically modelled within EXCEL and the respective functions described. The results from this analysis will be described in terms of a) the profiling of typical serious drug misuse in Ireland, b) the clustering of drug types and, c) the respective importance of key background variables. The various profiles obtained are discussed in terms of health care strategies in Ireland.

Download Full-text

A Two-Stage Conditional Estimation Procedure for Unrestricted Latent Class Models

Journal of Educational Statistics ◽

10.3102/10769986005002129 ◽

1980 ◽

Vol 5 (2) ◽

pp. 129-156 ◽

Cited By ~ 2

Author(s):

George B. Macready ◽

C. Mitchell Dayton

Keyword(s):

General Class ◽

Latent Class ◽

Estimation Procedure ◽

Error Rates ◽

Latent Class Models ◽

Parameter Estimates ◽

Probability Models ◽

Two Stage ◽

Conditional Estimation ◽

Class Models

A variety of latent class models has been presented during the last 10 years which are restricted forms of a more general class of probability models. Each of these models involves an a priori dependency structure among a set of dichotomously scored tasks that define latent class response patterns across the tasks. In turn, the probabilities related to these latent class patterns along with a set of “Omission” and “intrusion” error rates for each task are the parameters used in defining models within this general class. One problem in using these models is that the defining parameters for a specific model may not be “identifiable.” To deal with this problem, researchers have considered curtailing the form of the model of interest by placing restrictions on the defining parameters. The purpose of this paper is to describe a two-stage conditional estimation procedure which results in reasonable estimates of specific models even though they may be nonidentifiable. This procedure involves the following stages: (a) establishment of initial parameter estimates and (b) step-wise maximum likelihood solutions for latent class probabilities and classification errors with iteration of this process until stable parameter estimates across successive iterations are obtained.

Download Full-text

Association of in Utero Antibiotic Exposure With Childhood Ear Infection Trajectories: A National Birth Cohort Study

10.21203/rs.3.rs-83291/v1 ◽

2020 ◽

Author(s):

Yanhong Jessika Hu ◽

Jing Wang ◽

Joseph Irvin Harwell ◽

Melissa Wake

Keyword(s):

Birth Cohort ◽

Latent Class ◽

Multinomial Logistic Regression ◽

Antibiotic Use ◽

In Utero ◽

Latent Class Models ◽

Antibiotic Exposure ◽

Ear Infection ◽

Increased Risk ◽

In Pregnancy

Abstract BackgroundMost prescribed medicines during pregnancy are antibiotics, with unknown effects on a foetus and on the infant’s acquired microbiome. This study investigates associations between in utero antibiotic exposure and ear infection trajectories over the first decade of life, hypothesising effects on early or persistent, rather than later-developing, ear infections.MethodsDesign & Participants: The Longitudinal Study of Australian Children (LSAC) birth cohort recruited a nationally-representative sample of 5107 infants in 2004. Measures: Mothers reported antibiotic use in pregnancy when a child was 3-21 months old (wave 1), and ongoing problems with ear infection every 2 years spanning ages 0-1 to 10-11 years (waves 1 to 6). Analysis: Latent class models identified ear infection trajectories, and univariable and multivariable multinomial logistic regression determined odds of adverse trajectories by antibiotic exposure. Results4500 (88.1% of original sample) children contributed (mean baseline age 0.7 years; 51.3% boys); 10.4% of mothers reported antibiotic use in pregnancy. Four probability trajectories for ear infection emerged: “consistently low” (86.2%), “moderate to low” (5.6%), “low to moderate” (6.7%) and “consistently high” (1.4%). Antibiotic use in pregnancy was associated with children following “consistently high” (aOR 2.06, 95% CI 1.09 to 3.91, p=0.03) and “moderate to low” (aOR 1.78, 95% CI 1.25 to 2.53, p=0.001) trajectories.ConclusionsAntibiotic use in pregnancy is associated with an increased risk of persistent and early childhood ear infections. This highlights the wisdom of cautious antibiotic use during pregnancy, and the need for study of potential mechanisms underlying these associations.

Download Full-text

Bayesian Multilevel Latent Class Models for the Multiple Imputation of Nested Categorical Data

Journal of Educational and Behavioral Statistics ◽

10.3102/1076998618769871 ◽

2018 ◽

Vol 43 (5) ◽

pp. 511-539 ◽

Cited By ~ 1

Author(s):

Davide Vidotto ◽

Jeroen K. Vermunt ◽

Katrijn van Deun

Keyword(s):

Multiple Imputation ◽

Mixture Model ◽

Categorical Data ◽

Latent Class ◽

Real Data ◽

Latent Class Models ◽

Parameter Estimates ◽

Complex Interactions ◽

Analysis Models ◽

Class Models

With this article, we propose using a Bayesian multilevel latent class (BMLC; or mixture) model for the multiple imputation of nested categorical data. Unlike recently developed methods that can only pick up associations between pairs of variables, the multilevel mixture model we propose is flexible enough to automatically deal with complex interactions in the joint distribution of the variables to be estimated. After formally introducing the model and showing how it can be implemented, we carry out a simulation study and a real-data study in order to assess its performance and compare it with the commonly used listwise deletion and an available R-routine. Results indicate that the BMLC model is able to recover unbiased parameter estimates of the analysis models considered in our studies, as well as to correctly reflect the uncertainty due to missing data, outperforming the competing methods.

Download Full-text

998Use of antibiotics in pregnancy and ear infection trajectories in children

International Journal of Epidemiology ◽

10.1093/ije/dyab168.694 ◽

2021 ◽

Vol 50 (Supplement_1) ◽

Author(s):

Jing Wang ◽

Jing Wang

Keyword(s):

Latent Class ◽

Multinomial Logistic Regression ◽

Latent Class Models ◽

Ear Infection ◽

Physician Visits ◽

Additional Information ◽

Increased Risk ◽

Antibiotics Use ◽

Ear Infections ◽

In Pregnancy

Abstract Background Exposure to antibiotics during pregnancy can exercise a teratogenic effect on foetuses. Middle ear infection represents the most common cause of physician visits for sick children. Its patterns may be partly explained by antibiotics use during pregnancy. This study aimed to investigate the associations between antibiotics use in pregnancy and ear infection trajectories. Methods Design & Participants: Birth cohort assessed biennially from 2004 to 2014 spanning ages 0-1 to 10-11 years in the Longitudinal Study of Australian Children. Measures: Mothers-reported antibiotics use in pregnancy; Parent-reported ongoing ear infections (waves 1 to 6). Analysis: Latent class models identified ear infection trajectories. Multinomial logistic regression quantified associations between antibiotics use in pregnancy and ear infection trajectories. Results of the 4500 included children (mean age at baseline wave 0.7 years, 51.3% boys), 10.4% had parent-reported antibiotics use in pregnancy. Four probability trajectories of ear infection emerged: “consistently low” (86.2%), “moderate to low” (5.6%), “low to moderate” (6.7%), and “consistently high” (1.4%). Antibiotics use in pregnancy was associated children following “moderate to low” (OR 1.8, 95% CI 1.3 to 2.6) and “consistently high” (OR 2.1, 95% CI 1.1 to 4.0) trajectories. Conclusions Antibiotics use in pregnancy increases the risk of persistent and early ear infections in the offspring, implying that reducing unnecessary antibiotics use during pregnancy may prevent childhood ear infections. Additional information on classes and timing of antibiotics exposure at different stages of pregnancy and ear infections resistance could further explain this relationship and inform interventional studies. Key messages Antibiotics use in pregnancy is associated with an increased risk of persistent and early ear infections in the offspring.

Download Full-text