Relative importance analysis for count regression models

Modeling COVID-19 daily cases in Senegal using a generalized Waring regression model

COVID-19 is currently threatening countries in the world. Presently in Nigeria, there are about 29,286 confirmed cases, 11,828 discharged and 654 deaths as of 6th July 2020. It is against this background that this study was targeted at modeling daily cases of COVID-19’s deaths in Nigeria using count regression models like; Poisson Regression (PR), Negative Binomial Regression (NBR) and Generalized Poisson Regression (GPR) model. The study aim at fitting an appropriate count Regression model to the confirmed, active and critical cases of COVID-19 in Nigeria after 118 days. The data for the study was extracted from the daily COVID-19 cases update released by the Nigeria Centre for Disease Control (NCDC) online database from February 28th, 2020 – 6th, July 2020. The extracted data were used in the simulation of Poisson, Negative Binomial, and Generalized Poisson Regression model with a program written in STATA version 14 and fitted to the data at a 5% significance level. The best model was selected based on the values of -2logL, AIC, and BIC selection test/criteria. The results obtained from the analysis revealed that the Poisson regression could not capture over-dispersion, so other forms of Poisson Regression models such as the Negative Binomial Regression and Generalized Poisson Regression were used in the estimation. Of the three count Regression models, Generalized Poisson Regression was the best model for fitting daily cumulative confirmed, active and critical COVID-19 cases in Nigeria when overdispersion is present in the predictors because it had the least -2log-Likelihood, AIC, and BIC. It was also discovered that active and critical cases have a positive and significant effect on the number of COVID-19 related deaths in Nigeria.

This paper introduces a novel modification of the negative binomial distribution, which serves as a generalization encompassing both negative binomial and zero-inflated negative binomial distributions. This innovative distribution offers flexibility by accommodating an arbitrary number of inflation points at various locations. The paper explores key distributional properties associated with this modified distribution. Additionally, this study proposes several estimators designed to obtain estimates for the unknown parameters. Furthermore, the paper introduces a new count regression model that utilizes the modified distribution. To assess the performance of the proposed distribution and the count regression model, a comprehensive Monte Carlo simulation study is conducted. In the final stage of the paper, a real-world dataset is scrutinized to ascertain the superiority of the proposed model. This empirical analysis contributes to validating the practical applicability and effectiveness of the newly introduced distribution in comparison to existing models.

Introduction: The need to model the impact of some demographic indicators on the frequency of household visits to healthcare centres in Nigeria's community is very important for preventing and spreading community diseases. This study aimed to investigate the effect of the patents' age, gender, marital status, type of illness and amount spent on the frequency of visits to community health care centres in Nigeria and to compared Negative Binomial Regression (NBR) and Generalized Poisson Regression (GPR) models to determine the preferred count regression model for the number of household visits to health centres in some communities in Nigeria. Methods: Survey of 132640 households in some Nigeria communities obtained from the 2018/2019 Nigeria Living Standard Survey (NLSS) were extracted from the National Bureau of Statistics (NBS) in collaboration with the World Bank. The Negative Binomial and Generalised Poisson regression models were used to investigate the five demographic variables on the frequency of visit to the community health centres. The performance of the count regression model was assessed using the Chi-square -2log Likelihood Statistic (2logL), Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) selection criteria. Results: Findings from the study showed that the type of illness and amount spent has a significantly positive effect on the number of household members' visits to the community health care centres in Nigeria while age, gender, and marital status was discovered to have a negative effect on the number of household members' visits to the community health care centres in Nigeria. Conclusion: The Nigeria Government, health centre management and community healthcare service providers' need to be aware that the amount spent and the nature of illness determines the level of health care services utilisation in the Nigeria community, hence the need for the drastic reduction in charges to encourage a household visit to the community health centres whenever the need arises.

This study investigates the determinants of smoking behavior among young adults in Khuzestan province, southwest Iran, using two-level count regression models. Given the high prevalence of smoking-related diseases and the social impact of smoking, understanding the factors influencing smoking habits is crucial for effective public health interventions. We conducted a cross-sectional analysis of 1,973 individuals aged 18-35 years, using data from the Daily Smoking Consumption Survey (DSCS) in Khuzestan province collected in 2023. A variety of count regression models, including Poisson, Negative Binomial, Conway-Maxwell Poisson, and their zero-inflated counterparts, were evaluated. The best-fitting model was selected based on goodness-of-fit indices. Approximately 90% of participants were non-smokers. Among smokers, the prevalence of light, moderate, and heavy smoking was 47.7, 19.0, and 33.3%, respectively. The two-level Zero-Inflated Conway-Maxwell Poisson (ZICMP) model provided the appropriate fit for the data. Key determinants of daily cigarette consumption included gender, age, education, and Body Mass Index (BMI). Men consumed 3.24 times more cigarettes per day than women. Higher education levels were inversely related to smoking intensity, with MSc/PhD holders having significantly lower smoking rates. Age and BMI also significantly influenced smoking behavior, with younger and obese individuals showing lower smoking rates. The use of advanced count models capable of handling numerous zeros and overdispersion is crucial for accurately analyzing trends in cigarette consumption across different population groups. The results indicate that factors such as older age, lower education levels, and gender differences influence smoking behavior. Therefore, prevention strategies aimed at delaying the onset of smoking, particularly among men, and promoting education among adolescents can effectively reduce smoking rates. However, further research should consider additional socioeconomic variables and encompass a broader age range to enhance the understanding of smoking behavior.

The two most popular models inwell-known count regression models are Poisson and negative binomial regression models. Poisson regression is a generalized linear model form of regression analysis used to model count data and contingency tables. Poisson regression assumes the response variable Y has a Poisson distribution, and assumes the logarithm of its expected value can be modeled by a linear combination of unknown parameters. Negative binomial regression is similar to regular multiple regression except that the dependent (Y) variables an observed count that follows the negative binomial distribution. This research studies some factors affecting divorce using Poisson and negative binomial regression models. The factors are unemployment rate, inflation and Gini coefficient. The data were taken from the website of the Statistics Center for the years 2002 to 2023.Under the Poisson regression model, each factor has been reported to have an effect on the divorce rate. The two factors of inflation and unemployment had a direct effect and income inequality factors had an inverse effect on the divorce rate. But, under the negative binomial regression model, only inflation has an effect on the number of divorces. It is worth noting that according to the AIC values, the negative binomial regression model has a better fit than the Poisson regression model because its AIC value is lower.

Background: Under-five mortality rate, often known by its acronym U5MR, indicates the probability of dying between birth and five years of age, expressed per 1,000 live births. Globally, 16,000 children under-five still die every day. Especially in Sub-Saharan Africa every 1 child in 12, dying before his or her fifth birthday. This study aims to identify the determinants of under-five mortality among women in child bearing age group of Tach-Armachiho district using count regression models. Methods: For achieving the objective, a two-stage random sampling technique (simple random sampling and systematic random sampling techniques in the first and second stages respectively) was used to select women respondents. The sample survey conducted in Tach-Armachiho district considered a total of 3815 households of women aged 15 to 49 years out of which the information was collected from 446 selected women through interviewer administrated questionnaire. Results: The descriptive statistics result showed that in the district 16.6% of mothers have faced the problem of at least one under-five death. In this study, Poisson regression, negative binomial, zero-inflated Poisson and zero-inflated negative binomial regression models were applied for data analysis. Each of these count models were compared by different statistical tests. So that, zero-inflated poisson regression model was found to be the best fit for the collected data. Results of the zero-inflated Poisson regression model showed that education of husband, source of water, mother occupation, kebele of mother, prenatal care, place of delivery, place of residence, wealth of house hold, average birth interval and average breast feeding were found to be statistically significant determinants of under-five mortality. Conclusions: In this study, it was found that the factors like average birth interval and average breast feeding were found to be statistically significant factors in both groups (not always zero category and always zero category) with under-five child deathwhereas education of husband, source of water, place of delivery, mother occupation and wealth index of the household have significant effect on under-five mortality under not always zero group. Place of residence, kebele of mother and prenatal care have a significant effect on under-five mortality in TachArmachiho district on inflated group

Atkins, D

Processes that occasionally, but not always, produce extreme values are notoriously difficult to model, as a small number of extreme observations may have a large impact on the results. Existing methods for handling extreme values are often arbitrary and leave researchers without guidance regarding this problem. In this paper, we propose an extreme value and zero-inflated negative binomial (EVZINB) regression model, which allows for separate modeling of extreme and nonextreme observations to solve this problem. The EVZINB model offers an elegant solution to modeling data with extreme values and allows researchers to draw additional inferences about both extreme and nonextreme observations. We illustrate the usefulness of the EVZINB model by replicating a study on the effects of the deployment of UN peacekeepers on one-sided violence against civilians.

PurposeThe purpose of this paper is to present a multichannel segmentation approach to identifying customer segments based on actual customer channel usage in the post-purchase phase in the health insurance industry.Design/methodology/approachA multinomial regression model and count regression models were estimated to describe the profiles of customer segments and the frequency of channel usage based on generations and sociodemographic variables.FindingsThis study identified generational differences in channel usage. Single female customers from the Pre-Boomer or Baby Boomer generation and customers living in states with lower incomes are more likely to use call centres. Website users tend to live in regions with higher per capita income. Multichannel users are, on average, more frequent users of both the website and call centres. In terms of sociodemographics, they display a more heterogeneous profile.Research limitations/implicationsThe proposed segmentation needs to be enriched with additional variables such as customers’ health status or channel usage motivations.Practical implicationsCustomers, who are male, married and from Generations Y and X, are more likely to use the website. Their propensity to switch to a digital channel could be investigated further to develop targeted migration strategies. Multichannel users are, on average, more frequent users of all channels. To avoid increased channel costs, segments should be analysed in terms of their size and profit potential to help allocate marketing investment more efficiently.Originality/valueAs opposed to existing research, the proposed segmentation approach is based on transactional data of channel usage from a real company, combined with analyses using generations and sociodemographic variables.

Background: It may take a long time to diagnose multiple sclerosis (MS) since the emergence of primary symptoms. This study aimed to use count regression models to compare their fit and to identify factors affecting delay in the diagnosis of MS. Methods: Data were collected from the Nationwide MS Registry of Iran (NMSRI) for Mazandaran Province, Iran, using census sampling until April 2022. The four models of Poisson regression, negative binomial (NB) regression, zero-inflated Poisson (ZIP) regression, and zero-inflated negative binomial (ZINB) regression were used in this study. Results: In this study on 2894 patients, 74.0% were women, and 8.5% had a family history of MS. The mean ± standard deviation (SD) of the patients' age was 34.96 ± 9.41 years, and the mean delay in diagnosis was 12.32 ± 33.26 months, with a median of 0 (Q1-Q3: 0-9). The NB regression model showed the best performance, and factors, including a history of hospitalization and the year of symptom onset, had significant effects on a delayed diagnosis. Besides, the Expanded Disability Status Scale (EDSS) score was significantly different before and after 2017; it was also associated with sex, type of MS, and history of hospitalization. Conclusion: The mean diagnostic delay and the mean age of MS diagnosis are critical in Mazandaran Province. Patients with MS develop the disease at an early age and are diagnosed with a long delay. The time of symptom onset is a significant factor in the diagnosis of MS, and in recent years, there have been improvements in the diagnostic process.

Background Antenatal care visit is the service given to pregnant women to have a safe pregnancy and a healthy baby. The main objective of this study was to identify potential factors for the barriers in the number of antenatal care visits. Methods Data for this study was taken from the 2016 Ethiopian demographic health survey. All childbearing women from rural parts of Ethiopia were considered in this study, and the count regression model was used to explore the major risk factors for the barriers in the number of antenatal care service visits. Results Nearly 42% of pregnant mothers did not visit antenatal care services, and only 1% of the mothers attended antenatal care service visits eight times and above. From hurdle Poisson regression model results, women having previous pregnancy complication (AOR = 1.16; P ≤ 0.001); husbands with primary education (AOR = 1.02; P=0.004), secondary education (AOR = 1.117; P ≤ 0.0001), and higher education (AOR = 1.191; P ≤ 0.001); middle wealth index (AOR = 1.08; P=0.006); richer wealth index (AOR = 1.10; P ≤ 0.001); maternal age 35–49 (AOR = 0.690; P ≤ 0.001); being exposed to media access (AOR = 1.745; P=0.019); having distance problem (AOR = 0.75; P=0.013); planned pregnancy (AOR = 1.42; P=0.002); and mothers with primary education (AOR = 1.85; P ≤ 0.001) and secondary (AOR = 2.387; P ≤ 0.001) were statistically associated with barriers in the number of ANC service visits. Conclusion As indicated in the findings, there is underutilization of the antenatal care service visits regarding rural women in Ethiopia. Having a low education level, no media access, distance problem from the health facility, and not planned pregnancy decrease the rate of antenatal care service visits. To fill this discrepancy, the concerned bodies including government and nongovernmental organizations should work on the identified factors in the rural parts of the country to save children and mothers.

Estimating the influence of inspection violations on large-truck crashes using count regression models

Police agencies are considering various de-escalation curricula and training to aid in safer outcomes for both officers and civilians. Psychological reactance, a defensive response triggered when individuals perceive that their freedom or autonomy is being threatened, has been extensively studied across various disciplines, including health communications, marketing, and education, since the 1960s. However, formal training programs focused on teaching these techniques remain limited, and to date, no such training has been empirically tested with law enforcement in a health care setting. As the first known study in a law enforcement context, this pilot study implemented a randomized controlled trial in a hospital setting, coupled with pre- and post-test surveys to evaluate the impact of reactance-mitigating linguistic de-escalation training on physical interventions and de-escalation. Two of the four patrol blocks were randomized to receive the training, in which pre-test and post-test surveys were administered to the treatment personnel. Findings revealed successful training effectiveness, improved knowledge of reactance-mitigating concepts, and overall high support of the training. Count regression models indicated that treatment security staff reported fewer de-escalations than control security staff; however, treatment police officers reported significantly higher de-escalations than control police officers. This pilot study provides great promise for law enforcement officers, particularly when de-escalating more common, low-level encounters with hostile civilians. Other implications and future directions are discussed.

Roles of locational factors in the rise and fall of restaurants: A case study of Beijing with POI data