Editorial: Special issue on models for continuous data with a spike at zero

Böhning, Dankmar; Alfó, Marco

doi:10.1002/bimj.201500188

Cited by 6 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the problem of zero‐inflation is not confined to counts. Böhning and Alfò () cite several examples and discuss issues in the analysis of zero‐inflated continuous responses. Typically, in semi‐continuous data problems, a two‐part model is used to model the probability of a zero response in combination with a model for the mean response among positive outcomes.…”

Section: Discussionmentioning

confidence: 99%

Marginalized zero‐inflated Poisson models with missing covariates

et al. 2018

View full text Add to dashboard Cite

Unlike zero-inflated Poisson regression, marginalized zero-inflated Poisson (MZIP) models for counts with excess zeros provide estimates with direct interpretations for the overall effects of covariates on the marginal mean. In the presence of missing covariates, MZIP and many other count data models are ordinarily fitted using complete case analysis methods due to lack of appropriate statistical methods and software. This article presents an estimation method for MZIP models with missing covariates. The method, which is applicable to other missing data problems, is illustrated and compared with complete case analysis by using simulations and dental data on the caries preventive effects of a school-based fluoride mouthrinse program.

show abstract

Section: Discussionmentioning

confidence: 99%

Marginalized zero‐inflated Poisson models with missing covariates

et al. 2018

View full text Add to dashboard Cite

show abstract

“…A second major challenge is that there are a substantial number of incomes (approximately 32.48%) reported as zero, as exemplified in Figure 1. In other disciplines, such data comprising of one (or more) spikes at specific values along with a continuous distribution are known are semi‐continuous data (Bohning & Alfo 2016; Liu et al . 2019).…”

Section: Introductionmentioning

confidence: 99%

“…This takes the form of a mixture model, with one mixture component being a point mass at zero used to model the probability of an individual earning an income, and the second mixture component being a positive continuous distribution used to model the mean non‐zero income over time, conditional on earning an income. For modelling semi‐continuous responses comprising a point mass at zero and positive continuous data, mixture models are a popular although by no means the only approach; see the special issue edited by Bohning & Alfo (2016) as well as the recent review article by Liu et al . (2019).…”

Section: Introductionmentioning

confidence: 99%

A shared parameter mixture model for longitudinal income data with missing responses and zero rounding

Hui

Bondell²

2021

Aus NZ J of Statistics

View full text Add to dashboard Cite

Summary The analysis of longitudinal income data is often made challenging for several reasons. For example, in a national Australian survey on income over time, a non‐negligible proportion of responses are missing, and it is believed the missingness mechanism is non‐ignorable. Also, there are a large number of reported zero incomes, some of which may be true zeros (corresponding to individuals who legitimately do not earn an income), while some may be false zeros (corresponding to individuals choosing to round their income to zero). We propose a new shared parameter mixture (SPM) model for analysing semi‐continuous longitudinal income data, which addresses the two challenges of income non‐response and zero rounding. This is accomplished by jointly modelling an individual's underlying income together with the probability of missingness and rounding to zero, where both probabilities are permitted to vary in a smooth manner with their underlying non‐zero income. Applying the SPM model to the Australian income survey reveals that on average, older female individuals and individuals with a long‐term health condition are considerably less likely to earn an income, while income tended to be highest for male individuals on fixed‐term/permanent job contracts between ages 50 and 60. Furthermore there is evidence of both zero rounding, and conditional on the assumed missingness mechanism, individuals with incomes at the higher and lower ends are more likely to not report their income.

show abstract

“…For example, Liu, Strawderman, Cowen, and Shih (2010) generalized the two previous papers using a generalized gamma cost distribution with scale parameter depending on covariates; Deb, Munkin, and Trivedi (2006) give a Bayesian approach to jointly model health care expenditure as a two‐part model with insurance choice as an endogenous variable; and several authors have used similar joint models and Poisson or Negative Binomial distributions for correlated count data with hurdle or zero‐inflated components for zero counts (e.g., Deb & Trivedi, 2002; Min & Agresti, 2005; Winkelmann, 2004). Several papers in the recent Biometrical Journal Special issue: Models for continuous data with a spike at zero, summarized by Böhning and Alfò (2016) also use joint two‐part model approaches, for example, Chandra and Chambers (2016) for small area estimation, and Maruotti, Raponi, and Lagona (2016) for endogeneous variables in cost with zeros clustered by individuals. Recent reviews of work with two‐part models in the statistics and econometrics literature are given in Farewell, Long, Tom, Yiu, and Su (2017) and Deb, Norton, and Manning (2017).…”

Section: Introductionmentioning

confidence: 99%