Inflated Poisson Model Research Articles

Biomarkers associated with pulmonary exacerbations in a randomized trial of nintedanib for radiation pneumonitis

Background and purposeRadiation pneumonitis (RP) is a common side effect of thoracic radiotherapy and often has a long course characterized by acute exacerbations and progression to permanent lung fibrosis. There are no validated biomarkers of prognosis in patients diagnosed with RP. Materials and methodsWe analyzed a time course of serum chemokines, cytokines, and other proteins from patients with grade 2+ RP in a randomized clinical trial of a steroid taper plus nintedanib, a multiple tyrosine kinase inhibitor, versus placebo plus a steroid taper for the treatment of RP. Weighted gene correlation network analysis (WGCNA) and univariable zero inflated Poisson models were used to identify groups of correlated analytes and their associations with clinical outcomes. ResultsThirty enrolled patients had biomarker data available, and 17 patients had enough analytes tested for network analysis. WGNCA identified ten analytes, including transforming growth factor beta-1 (TGF-β1), monocyte chemoattractant protein-1 (MCP-1), and platelet-derived growth factor (PDGF), that in aggregate were correlated with the occurrence of pulmonary exacerbations (p = 0.008), the total number of acute pulmonary exacerbations (p = 0.002), and treatment arm (p = 0.036). By univariable analysis, an increase in rate of change of two components of the RP module were associated with an increased incidence rate of pulmonary exacerbations: interleukin 5 (IL-5, incidence rate ratio (IRR) 1.02, 95% CI 1.01–1.04, p = 0.002), and tumor necrosis factor superfamily 12 (TNFSF12, IRR 1.06, CI 1–1.11, p = 0.036). An increased slope of epidermal growth factor (EGF) was associated with a decreased incidence rate of exacerbations (IRR 0.94, CI 0.89–1, p = 0.036). ConclusionWe identified a panel of serum biomarkers that showed association with nintedanib treatment and acute pulmonary exacerbations in patients with RP. A confirmatory study will be needed to validate this panel for use as a prognostic tool in patients with RP.

Mixed zeros inflated poisson model: an application in grape disease control

Longitudinal data studies describe the behavior of a feature of observations over time through so-called mixed models, which bear this name because they contain fixed effects and random effects. Still, if many of the observations do not show such a characteristic, i.e., the amount of zeros observed is greater than expected, then we say that it is inflated data of zeros. This work aims to describe the applicability of a mixed zero inflated Poisson (ZIP) model to model the temporal progress of mildew (Plasmopara viticultura), which corresponds to fungal disease of the grape, more specifically in the cultivar BRS Vitória, and assess its tolerance for 6 different treatments. This is intended to evaluate the quality of the proposed model fit and to carry out tests comparing the treatment averages to point out which treatments are equally effective in the control of mildew, thus demonstrating the application of the mixed ZIP model in a real and significant problem. A mixed ZIP model was constructed based on methodologies found in the literature and for inference and estimation of the parameters the method of maximum likelihood was used. The results showed that the mixed ZIP model adjusted well to the data, and hypothesis testing for average pointed to equality in efficacy between some treatment groups, thus making it possible to obtain a treatment with fewer sprays within each group.

Innovation in Peruvian manufacturing industries: An analysis of the determinants of the goods and services introduced to the market

This paper addresses the determinants of the introduction of new goods and services, or significant improvements in existing ones, in the market (product innovation) by firms in the manufacturing sector. Using data from the 2018 Peru National Innovation Survey, count models are employed, specifically the Poisson Regression Model (RPM) and the Zero Inflated Poisson Model (ZIP). The findings reveal that research and development (R&D) spending and innovation training have the largest significant impact on the number of innovations introduced. In addition, a significant effect of firm size and collaboration with universities and/or firms on the product innovation process is observed. These results contribute to a better understanding of the drivers of innovation in the manufacturing industry.

Subjective and objective indicators of neighbourhood safety and physical activity among UK adolescents.

The health benefits of regular physical activity in adolescence are well-documented and many health-related behaviours are established in adolescence. The neighbourhood environment is a key setting for physical activity for adolescents and feeling unsafe in their neighbourhood may be a potential barrier to physical activity. This study aimed to examine associations between neighbourhood safety and physical activity using objective and subjective measures for both. Participants (n=10,913) came from the Millennium Cohort Study, a nationally representative UK longitudinal birth cohort. Linear regression and Zero Inflated Poisson models were used to examine associations between subjective and objective indicators of safety (self-reported safety, Index of Multiple Deprivation crime, Reported Crime Incidence) and physical activity (self-reported weekly and device-measured physical activity). Adolescents who feel unsafe in their neighbourhood, or who live in areas with high IMD crime or violent crime rates report 0.29 (95% CI -0.49, -0.09) 0.32 (95% CI -0.47, -0.16) and 0.20 (95% CI -0.39, -0.20) fewer days of physical activity, respectively. No associations were found between Reported Crime Incidence and either objective or subjective measures of physical activity. This study demonstrates varying associations between subjective safety and objective crime with physical activity levels in adolescence, highlighting the complexities around subjective and objective measurements and their associations with health outcomes.

零膨胀泊松模型的变量选择及应用

零膨胀泊松模型的变量选择及应用

P03-04 Perceived and objective indicators of neighbourhood safety and physical activity in early adolescence: a national cohort study

BackgroundThe health benefits of regular physical activity in adolescence are well-documented. Currently, young people in the UK are not achieving recommended levels of physical activity. The neighbourhood environment is a key setting for physical activity in adolescence. Due to lack of financial independence and mobility restrictions, adolescents spend a significant amount of time in their neighbourhood. Feeling unsafe in their neighbourhood may be a potential barrier to physical activity.This study aims to examine associations between objective and subjective measures of neighbourhood safety and physical activity.MethodsParticipants (n = 11,726) came from the Millennium Cohort Study; a nationally representative UK longitudinal birth cohort. At age 11 perceived neighbourhood safety was assessed via questionnaire and the Index of Multiple Deprivation (IMD) crime domain was linked to participant postcode data. At age 14, participants self-reported physical activity and a subsample (n = 4,813) also wore GENEActiv wrist-worn activity monitors for one weekday and one weekend day. Associations between perceived safety, IMD crime and self-reported physical activity were quantified using linear regression models. Zero Inflated Poisson (ZIP) models were used to examine associations with accelerometer-measured physical activity. We adjusted for parental education, family income, ethnicity and season of accelerometer wear. An interaction term for sex was tested to assess whether associations between perceived safety and physical activity differed by sex. Models were also stratified by sex.ResultsFeeling not safe compared to very safe was associated with 0.28 (95% CI -0.50, -0.06) fewer days of self-reported physical activity. However, no association was seen between perceived safety and accelerometer physical activity. Those living in the highest IMD crime areas reported on average 0.31 (95% CI -0.47, -0.15) fewer days of physical activity compared to those living in the lowest crime areas. Individuals living in the highest IMD crime areas achieved 5.56 fewer minutes of daily accelerometer-measured exercise than those in least crime areas.ConclusionsThis study demonstrates consistent associations between perceived safety and objective crime with physical activity levels in adolescence.

Application of Count Regression Models for Factors of Antenatal Care (ANC) Utilization in Ethiopia

Adequate antenatal care is necessary to improve the health status of peoples in a country as it contributes the reduction of infant and maternal mortalities. The coverage and the quality of antenatal care plays significant role in maternal health. Ethiopia has witnessed an encouraging improvement in the ANC coverage (at least one visit) in the last decade from 62% in 2016 to 74% in 2019. But only 43% of women had at least four ANC visits during their last pregnancy. The purpose of this study is to identify factors that affect antenatal care visits based on 2019 Ethiopia Mini Demographic and Health Survey (EMDHS) dataset using count regression model. A total of 8,885 women aged 15-49 years were asked for the EMDHS-2019 out of which 3,927 women were illegible and asked for their ANC experiences for their last pregnancy. This empirical study aimed at investigating the impacts of the socioeconomic and demographic characteristics on the utilization of antenatal care. To investigate the impacts of the factors on the number of ANC visits, count models such as Poisson, Negative Binomial (NB), Zero Inflated Poisson (ZIP) and Zero-inflated negative binomial (ZINB) models were examined to select the best fitted model. The selection criterion Akaike information criterion (AIC), Bayesian information criterion (BIC) and Log Likelihood were applied to select the best model. The ZIP model was found to be the best fitted model for the data. Based on ZIP model, the explanatory variables region, age, place of residence, education, religion, wealth index and marital status were statistically significant factors on the frequency of ANC visits. Hence, efforts are still required to put on creating and expanding awareness on the utilization of ANC. The policy makers along with both private sectors and civil societies have to facilitate the increase of awareness and the experiences of the utilization of ANC in consideration of households within different groups of a society. Keywords: EMDHS-2019, antenatal care, Count Regression model DOI: 10.7176/JHMN/101-02 Publication date: June 30 th 2022

The impact of socioeconomic status, general health and oral health on Health-Related Quality of Life, Oral Health-Related Quality of Life and mental health among Polish older adults

BackgroundThe study aims to evaluate the impact of socioeconomic status, general health and oral health parameters on Health-Related Quality of Life (HRQoL), Oral Health-Related Quality of Life (OHRQoL) and mental health in elderly urban residents of South-Western Poland.MethodsThe 500 residents of Wroclaw, aged 65 and older provided demographic and personal information as well as their medical history. A patient's oral condition were determined based on the clinical oral examination.Quality of Life was assessed using Euro-Quality of Life (EQ-5D), Oral Health Impact Profile-14 (OHIP-14) and Patient Health Questionnaire (PHQ-9).The association between exposure (socioeconomic status, general health and oral health) and outcome (HRQoL, OHRQoL and mental health variables) were analyzed with the use of four models: P – Poisson model, NB-Negative Binomial model, ZIP – Zero Inflated Poisson model, ZINB – Zero Inflated Negative Binomial model.ResultsThe best model turned out to be the ZINB model, in which a negative binomial distribution in the count equation is assumed. In this model, only 13 independent variables had a significant effect on HRQoL, OHRQoL, and mental health. HRQoL assessed with the EQ-5D is significantly influenced by: living conditions 0.133 (95% CI: 0.001, 0.267, p = 0.049), income -0.348 (95%CI: -0.466, -0.230, p < 0.001), diabetes mellitus 0.437 (95%CI: 0.250, 0.624, p < 0.001), myocardial infarction 0.454 (95% CI: 0.151, 0.757, p = 0.003), stroke 0.543 (95%CI: 0.094, 0.992, p = 0.018) and renal disease 0.466 (95% CI: 0.206, 0.726, p < 0.001). Factors negatively affecting OHRQOL are: the need for oral treatment 0.278 (95%CI: 0.104, 0.452, p = 0.002), the number of missing teeth 0.053 (95%CI: 0.039, 0.067, p < 0.001) and gender 0.271 (95%CI: 0.015, 0.527, p = 0.038) and age -0.025 (95%CI: -0.042, -0.008, p = 0.003). An important factor influencing the level of depression assessed by the PHQ-9 questionnaire may be the material condition -0.225 (95%CI: -0.349, -0.101, p < 0.001). It should be emphasized that living with other people may be a factor that significantly increases the probability of avoiding the occurrence of depression symptoms.ConclusionThe study concerning elderly residents of the macroregion in Poland found the impact of socioeconomic, general health and oral health parameters on Health-Related Quality of Life, Oral Health-Related Quality of Life and mental health. Research on the quality of life of the elderly at the local level allowed to assess the factors linked to quality of life of older adults.

Likelihood-based methods for the zero-one-two inflated Poisson model with applications to biomedicine

ABSTRACT To model count data with excess zeros, ones and twos, for the first time we introduce a so-called zero-one-two-inflated Poisson (ZOTIP) distribution, including the zero-inflated Poisson (ZIP) and the zero-and-one-inflated Poisson (ZOIP) distributions as two special cases. We establish three equivalent stochastic representations for the ZOTIP random variable to develop important distributional properties of the ZOTIP distribution. The Fisher scoring and expectation–maximization (EM) algorithms are derived to obtain the maximum likelihood estimates of parameters of interest. Bootstrap confidence intervals are also provided. Testing hypotheses are considered, simulation studies are conducted, and two real data sets are used to illustrate the proposed methods.

Model Regresi Hurdle Negative Binomial (HNB) untuk Pemodelan Konsumsi Rokok di Provinsi Sulawesi Tengah

The average expenditure on cigarettes per capita in Sulawesi Tengah Province has increased in 2020. There are several factors that can affect a person's cigarette consumption including gender, age, education and health. To model cigarette consumption with several influencing factors can be use the poison regression model or the Zero Inflated Poisson (ZIP) model. However, the two regression models cannot solve the excess zero and overdispersion problems so use the Hurdle Negative Binomial (HNB) regression model. The results of the analysis of cigarette consumption data in Central Sulawesi Province using the HNB model provide the best modeling results compared to the poisson regression model and the ZIP model because it has the smallest Akaike's Information Criterion (AIC) value. The results of testing the factors that significantly influence cigarette consumption in Central Sulawesi Province in the HNB regression model, namely the count model are gender, age and health. Whereas in the zerohurdle model, it is gender, age and education.

PEMODELAN FAKTOR-FAKTOR YANG MEMPENGARUHI KEMATIAN IBU MELAHIRKAN DI JAWA TENGAH DENGAN ZERO INFLATED POISSON REGRESSION

One of the targets of the Sustainable Development Goals (SDGs) is to reduce the maternal mortality rate by 2030. In reducing the maternal mortality rate, it is necessary to first study the factors that influence it. The number of maternal mortality rate in Central Java Province in 2018 was a discrete random variable that had a Poisson distribution and had many zero values. Generally, a model was used to counting data is Poisson regression model. However, the maternal mortality that has many zero values caused overdispersion. Therefore, Poisson model was not relevant in that case. In this paper, we used Zero Inflated Poisson (ZIP) model to overcome overdispersion caused by many zero values. The results of the research show that ZIP model can explained influence the number of maternal mortality. Based on this research, the factors such as provision of tablets, pregnant women who experience obstetric complications, and households with a clean and healthy lifestyle can explain the number of maternal mortality.

Prediction of the days in hospital for next year using ensemble learning

There are many difficulties in predicting problems in real life with an individual model. In order to solve these problems, we use combined these models using an ensemble learning. Combined models can be applied to the prediction of the number of days in hospital. In this paper, we use the 2011 National Sample Cohort Database to construct a combined model using an ensemble learning and predict the number of days in hospital in 2013. Also, we consider the zero inflated poisson models and hurdle poisson models considering that the days in hospital as the response variable have excess zeros. For the problem of overdispersion, we consider the zero inflated negative binomial models and hurdle negative binomial models. As baseline models, we consider the generalized additive models and the generalized linear models using the poisson and negative binomial distributions. Finally, we consider the combined models using ensemble learning. We use the National Sample Cohort Database by National Health Insurance Service and apply eight models to this data. Finally, we suggest the best prediction model by the accuracy criterion of the root mean squared logarithmic error which penalizes an under-predicted estimate greater than an over-predicted estimate.

Modeling Zero Inflation and Over-Dispersion in Domestic Package Insurance Claims Portfolio: A Case of Madison Insurance Company-Kenya

The standard Poisson distribution is widely used as a mechanism for regression modeling of count data outcomes. However, the suitability of this modeling technique is only limited to equi-dispersed count data outcomes. This is due to the fact that this modeling technique does not take into account the problems associated with over dispersion and excess zeros in many data sets as with insurance claims data. The study objective is to model domestic package insurance claims frequency using zero inflated and hurdle models since insurance portfolios are characterized by the non-occurrence of claims over a given time interval. This non-occurrence of claims over a given time interval usually leads to the Zero-Inflation and Dispersion associated with insurance claims data. The study consequently evaluates the performance of the Poisson, Zero Inflated Poisson (ZIP) and Hurdle Poisson (HP) models in determining the model that best models the domestic package insurance claims data. This is then used to estimate, predict and determine the heterogeneity of occurrence of the aforementioned insurance claims. The statistical Hosmer-Lemeshow tests is used to define the suitability of the fitted model to estimate the zero-inflation and over-dispersion characteristic of the data. To determine the presence of outliers and the distribution of residuals, the Residual Pearson and Deviance statistics are used. Data on a number of claims for domestic package insurance policy from Madison Insurance ltd, Kenya spanning from 2014 to 2018 (261 weeks) is used in the study.

A goodness-of-fit test for zero-inflated Poisson mixed effects models in tree abundance studies

Field studies in ecology often make use of data collected in a hierarchical fashion, and may combine studies that vary in sampling design. For example, studies of tree recruitment after disturbance may use counts of individual seedlings from plots that vary in spatial arrangement and sampling density. To account for the multi-level design and the fact that more than a few plots usually yield no individuals, a mixed effects zero inflated Poisson model is often adopted. Although it is a convenient modeling strategy, various aspects of the model could be misspecified. A comprehensive test procedure, based on the cumulative sum of the residuals, is proposed. The test is proven to be consistent, and its convergence properties are established as well. The application of the proposed test is illustrated by a real data example and simulation studies.

Multivariate zero-and-one inflated Poisson model with applications

This paper extends the univariate zero-and-one inflated Poisson (ZOIP) distribution (Melkersson & Olsson, 1999; Zhang et al., 2016) to its multivariate version, which can be used to model correlated multivariate count data with large proportions of zeros and ones marginally. More importantly, this new multivariate ZOIP distribution possesses a flexible dependency structure; i.e., the correlation coefficient between any two random components could be either positive or negative depending on the values of the parameters. The important distributional properties are explored and some useful statistical inference methods without and with covariates are developed. Simulation studies are conducted to evaluate the performance of the proposed methods. Finally, two real data sets on healthcare and insurance are used to illustrate the proposed methods.

Alternative count Bayesian models for genetic evaluation of litter traits in pigs

We compared Hurdle Poisson (Hupoisson), Zero Inflated Poisson (Zipoisson), Poisson and Gaussian Bayesian mixed models for genetic evaluation of litter traits in pigs (number of piglets born alive – NBA; number of piglets weaned – NW; and mortality during the suckling period – MORT). The models’ goodness-of-fit was based on Deviance Information Criteria (DIC), Model Posterior Probabilities (MPP) and Mean Square Error (MSE). The Hupoisson model provided the best fit to MORT, even showing higher heritability estimate (0.13, with credibility interval from 0.0745 to 0.2809). The Hupoisson model proposed in the present study was suitable for genetic evaluation of mortality during the suckling period, and can be indicated as a novel approach to treat count data with excess of zeros under a genetic and breeding viewpoint. The Gaussian model outperformed the other models for NBA and NW.

Model Selection for Count Data with Excess Number of Zero Counts

Zero inflated models have been widely studied in statistical literature. Zero inflated Poisson model and hurdle model are the most commonly used models for modeling the overdispersed count data. In adddition to this, recent studies shows that a nonparametric and data dependent technique known as artificial neural networks (ANN) produce better performance for modeling the over dispersed and zero inflated count data. In this paper, we compared the performance of different models such as zero inflated Poisson model, hurdle model and ANN for modelling the zero inflated count data in terms of standardized MSE, SE, bias and relative efficiency. An application study is carried out for both the simulated data set and real data set. Also for checking the suitability of these three models, we verified the group membership of the models, by adopting three classification techniques known as discriminant analysis, CART and random forest. We proposed an algorithm for selecting the better model among a set of models and computed the misclassification rates for a zero inflated count data set using different classifiers.

Bayesian Zero- Inflated Poisson model for prognosis of demographic factors associated with using crystal meth in Tehran population.

Background: Use of methamphetamine (MA) and other stimulants has increased steadily over the past 10 years. Risk factor evaluation to reduce the problem in the community is one solution to protect people from addiction. This study aimed at using Bayesian zeroinflated Poisson (ZIP) model to investigate the relationship between the number of using crystal meth and some demographic factors in Tehran population. Methods: A cross-sectional study was conducted to investigate crystal meth abuse in Tehran, the capital of Iran, in 2012. Stratified sampling method was used to select samples from 22 urban areas of Tehran. Trained researchers referred to the public places, such as streets, parks, squares, and libraries, to perform face-to-face interviews with the randomly selected samples. Bayesian ZIP model was used to perform the analysis, and SAS 9.3 program was used for data analysis. Results: A total of 993 individuals were studied. According to Bayesian ZIP model, sex (mean= -0.27, 95%CI (-0.485, -0.061)), age (mean= 0.03, 95%CI (0.018, 0.043)), high school level education (mean= 1.276, 95%CI (0.699, 01.9)), diploma level education (mean= 10.4, 95%CI (0.511, 1.69)), and university level education (mean= 0.69, 95%CI (0.142, 1.33)) were all found to have significant associations with crystal meth usage, being the dependent variable. Conclusion: Males, those with higher education levels, and older people in Tehran population are more likely to use crystal meth. This demographic information may be useful in designing preventive programs. Moreover, it is better to analyze count data with excessive zeroes using Bayesian zero- inflated model instead of the usual count models.

Are Negative Peer Influences Domain Specific? Examining the Influence of Peers and Parents on Externalizing and Drug Use Behaviors.

Most studies tend to characterize peer influences as either positive or negative. In a sample of 1815 youth from 14 different schools in Caracas, Venezuela, we explored how two types of peer affiliations (i.e., deviant and drug-using peers) differentially mediated the paths from positive parenting to youth's externalizing behavior and licit and illicit drug use. We used Zero Inflated Poisson models to test the probability of use and the extent of use during the past 12months. Results suggested that peer influences are domain specific among Venezuelan youth. That is, deviant peer affiliations mediated the path from positive parenting to youth externalizing behaviors, and peer drug-using affiliations mediated the paths to the drug use outcomes. Mediation effects were partial, suggesting that parenting explained unique variance in the outcomes after accounting for both peer variables, gender, and age. We discuss implications for the development of screening tools and for prevention interventions targeting adolescents from different cultures.

Fault Location for the Intermittent Connection Problems on CAN Networks

Fieldbus technology plays an important role in manufacturing systems. Hence, the reliability of the network is critical to the performance and the safety of the system. Among various factors that affect the reliability of the network, the intermittent connection (IC) of the network cable is a common but challenging troubleshooting problem since its location is difficult to identify. IC problems may result in degraded network performance or system level failures in severe cases. In this paper, a novel model-based fault location method is developed for IC problems on controller area networks. By passively capturing IC-induced network errors, two sets of error events are defined for each node, based on which generalized zero inflated Poisson models are used to describe the patterns of the error events. A two-step IC fault location procedure is proposed by examining the statistical significance of the corresponding error events using the fitted models. Case studies are conducted to demonstrate the proposed method on different IC location scenarios. Experiment results show that the locations of the IC problems identified by the proposed method agree well with the experiment setup conditions.