Binomial Estimation Research Articles

Community College Pathways for Disadvantaged Students

Objective: We estimated the correlations between the “pathways” chosen by community college students—in terms of desired credentials and fields of study, as well as other choices and outcomes along the paths—and the attainment of credentials with labor market value. We focused on the extent to which there were recorded changes in students’ choices over time, whether students made choices informed by their chances of success and by labor market value of credentials, and the impacts of choices on outcomes. Method: Using micro-longitudinal administrative data on a full cohort of Kentucky community college students, we provide summary data on a range of pathway characteristics and outcomes, as well as binomial and multinomial logit estimates of how pathway characteristics affect the odds of completing different kinds of credentials. Some of the logit estimates were based on random or fixed effects models. Results: We found that several characteristics of chosen pathways, such as field of study and desired credential as well as early “momentum,” affected outcomes. Student choices of pathways—and especially differences by gender and academic readiness—sometimes ran strongly counter to information about later chances of success in terms of probabilities of completing programs and attaining strong earnings. Students also changed pathways quite frequently, making it harder to accumulate the credits needed in their fields. Contributions: Attainment of credentials with greater market value by community college students could likely be improved by appropriate guidance and supports for them along the way and perhaps by broader institutional changes as well.

Identifying Stabilising Effects on Survey Based Life Satisfaction Using Quasi-maximum Likelihood Estimation

To which extent do happiness correlates contribute to the stability of life satisfaction? Which method is appropriate to provide a conclusive answer to this question? Based on life satisfaction data of the German SOEP, we show that by Negative Binomial quasi-maximum likelihood estimation statements can be made as to how far correlates of happiness contribute to the stabilisation of life satisfaction. The results show that happiness correlates which are generally associated with a positive change in life satisfaction, also stabilise life satisfaction and destabilise dissatisfaction with life. In such as they lower the probability of leaving positive states of life satisfaction and increase the probability of leaving dissatisfied states. This in particular applies to regular exercise, volunteering and living in a marriage. We further conclude that both patterns in response behaviour and the quality of the measurement instrument, the life satisfaction scale, have a significant effect on the variation and stability of reported life satisfaction.

Exponential family QMLE-based CUSUM test for integer-valued time series

This study considers testing for parameter changes in integer-valued time series models based on one parameter exponential family quasi-maximum likelihood estimates. We employ the cumulative sum (CUSUM) test as a change point test, based on score vectors, residuals, standardized residuals, and squares of residuals, focusing on performance comparison of negative binomial (NB) quasi-maximum likelihood estimate (QMLE)-based tests. Monte Carlo simulations are conducted with Poisson, NB, zero-inflated Poisson and NB, generalized Poisson INGARCH(1,1) models and Poisson and NB INAR(1) models. Real data analysis using the Korean stock price index (KOSPI) 200 is also included for illustration. The findings validate QMLE-based CUSUM tests using standardized residuals for INGARCH models and residuals for INAR models. Zero proportional change is well detected by the test using squares of residuals.

A New Method for Estimating the Incidence of Infectious Diseases

Ambitious World Health Organization targets for disease elimination require monitoring of epidemics using routine health data in settings of decreasing and low incidence. We evaluated two methods commonly applied to routine testing results to estimate incidence rates that assume uniform probability of infection between consecutive negative and positive tests based on: 1. the midpoint of this interval; and 2. a randomly selected point on this interval. We compared these with an approximation to the Poisson-binomial distribution which assigns partial incidence to time-periods based on the uniform probability of occurrence in these intervals. We assessed bias, variance and convergence of estimates using simulations of Weibull distributed failure times with systematically varied baseline incidence, and varying trend. We considered results for quarterly, half-yearly and yearly incidence estimation frequencies. We applied methods to assess human immunodeficiency virus (HIV) incidence in HIV-negative patients from the Treatment with Antiretrovirals and their Impact on Positive And Negative men study between 2012 and 2018. The Poisson-binomial method had reduced bias and variance at low levels of incidence and for increased estimation frequency, with increased consistency of estimation. Application of methods to real-world assessment of HIV incidence found decreased variance in Poisson-binomial model estimates, with observed incidence declining to levels where simulation results had indicated bias in midpoint and random-point methods.

Estimating and interpreting secondary attack risk: Binomial considered biased

The household secondary attack risk (SAR), often called the secondary attack rate or secondary infection risk, is the probability of infectious contact from an infectious household member A to a given household member B, where we define infectious contact to be a contact sufficient to infect B if he or she is susceptible. Estimation of the SAR is an important part of understanding and controlling the transmission of infectious diseases. In practice, it is most often estimated using binomial models such as logistic regression, which implicitly attribute all secondary infections in a household to the primary case. In the simplest case, the number of secondary infections in a household with m susceptibles and a single primary case is modeled as a binomial(m, p) random variable where p is the SAR. Although it has long been understood that transmission within households is not binomial, it is thought that multiple generations of transmission can be neglected safely when p is small. We use probability generating functions and simulations to show that this is a mistake. The proportion of susceptible household members infected can be substantially larger than the SAR even when p is small. As a result, binomial estimates of the SAR are biased upward and their confidence intervals have poor coverage probabilities even if adjusted for clustering. Accurate point and interval estimates of the SAR can be obtained using longitudinal chain binomial models or pairwise survival analysis, which account for multiple generations of transmission within households, the ongoing risk of infection from outside the household, and incomplete follow-up. We illustrate the practical implications of these results in an analysis of household surveillance data collected by the Los Angeles County Department of Public Health during the 2009 influenza A (H1N1) pandemic.

Income inequality, human capital and terrorism in Africa: Beyond exploratory analytics

This study uncovers the effect of income inequality on terrorism, delineated with four distinct markers: domestic, transnational, uncertain, and total, respectively, intermediated with the role of human capital, on a panel of 34 African countries, over the period 1980–2012. Thus, rather than presenting correlation analyses implied by exploratory analytics among these key variables of interest, this study further employs a zero-inflated negative binomial regression estimator due to the preponderance of zero values of the terrorism data. The following findings are consistently established. First, income inequality remains a substantive predictor of terrorism across the model specifications, with the exception of transnational terrorism. Second, human capital variables exert a positive first-order effect on both domestic and total terrorism. Third, the marginal impacts of interactions between human capital measures and income inequality indicators are negative at the higher levels of educational attainment. These findings remain robust in the presence of endogeneity concerns, time and country-specific effects, alternative estimators, and regional effects, respectively. On the policy front, eliminating the gaps in income inequality remains an effective policy antidote to quell the ember of angers and frustration that may aggravate into arm taking by the aggrieved.

Data science and GIS-based system analysis of transit passenger complaints to improve operations and planning

Transit user complaints support system resilience by serving as a data source for service improvements. This study shows how geographic information system (GIS)-based analysis, econometric models, and latent class analysis can improve system-wide understanding of passenger complaints. The analyzed dataset consists of 718 passenger complaints concerning the operation of municipal lines in Jerusalem as the study region. The analytical methods consists of GIS-based analysis and statistical modeling: mapping, recursive bivariate probit estimation, negative binomial model estimation, and latent class analysis. The GIS-based analysis showed that the spatial distribution of complaints changes over time as a function of service disruption type and geographical area. The recursive bivariate probit model results indicated that the most acute sources of frustration are service problem recurrence and monetary loss, with the former caused by overcrowding, delays and line cancellations. The negative binomial model results shows that the number of complaints increases with an increase in the passenger boarding to bus arrivals ratio. Latent class analysis reveals that, in terms of both prevalence and customer frustration, overcrowding delays and line cancellations are the most acute problems in the study region. The proposed interface between transit complaints and GIS databases can readily be implemented by transport operators and authorities.

Evaluation of Two-Leaf Sampling Units to Estimate Sugarcane Aphid (Hemiptera: Aphididae) Economic Thresholds in Commercial Grain Sorghum.

Sugarcane aphid Melanaphis sacchari Zehntner is a significant economic pest of grain sorghum in the United States. Effective monitoring and early detection are cornerstones for managing invasive pests. The recently developed binomial sequential sampling plan estimates sugarcane aphid economic thresholds (ETs) based on classification whether a 2-leaf sample unit has ≤ or ≥ 50 M. sacchari. In this study, we evaluated eight 2-leaf sampling units for potential use in the sequential sampling plan. From 2016 through 2017, whole plant counts of M. sacchari were recorded non-destructively in situ on sorghum plants from 140 fields located in five states. Plant canopies were stratified into three categories. Two leaves from each stratum were used to compare linear relationships between M. sacchari numbers per two-leaf sample unit and total M. sacchari density per plant. Analysis revealed that two randomly selected leaves from the middle stratum accounted more variation for estimating M. sacchari density when compared to two leaves from the other strata. Comparison of eight two-leaf sampling units within plant growth stages were variable in quantifying variation of M. sacchari densities. When growth stages were combined, the standard uppermost + lowermost leaf sample unit and a unit consisting of two randomly selected leaves from the middle stratum revealed little difference in their enumeration of variation in M. sacchari density. Because other sample units were either less predictive and/or more variable in estimating M. sacchari density, we suggest that the (L1+U1) sample unit remain the preferred method for appraising M. sacchari ETs.

Brexit and the location of Japanese direct investment in European regions

This paper investigates how the Brexit announcement affects Japanese direct investment into Europe at the regional NUTS-2 level. Political and economic uncertainty is an important factor affecting the economic performance of a country and its regions. In this study, Japanese annual firm-level data between the years 2000 and 2018 for 31 European countries is used. Negative binomial estimations indicate a significant negative relationship between uncertainty associated with the Brexit announcement and Japanese foreign direct investment (FDI) in the UK regions. Strong FDI path dependence currently acts to dampen this effect. However, depending upon future European Union Single Market access rules, such path dependence could act to magnify Brexit’s effect on inward-UK FDI. JEL Classification Codes: F23, R12.

Estimating the impacts of lockdown on Covid-19 cases in Nigeria

The study examines the extent to which lockdown measures impact on COVID-19 confirmed cases in Nigeria. Six indicators of lockdown entailing retail and recreation, grocery and pharmacy, parks, transit stations, workplaces, and residential, are considered. The empirical evidence is anchored on the negative binomial regression estimator, due to the count nature of the dataset on the daily cases of the virus. The study established the key following findings: First, retail and recreation, grocery and pharmacy, parks, transit stations, and workplaces are statistically significant and negatively signed as relevant predictors of the virus. Second, the impact of residential is positive and statistically significant at the conventional level. Lastly, the results are robust to an alternative estimator of Poisson Regression. The emanated policy message centres on the need to direct efforts toward ensuring total compliance to the lockdown rules as it holds the key to keeping the virus under check.

Temporal Analysis of Predictors of Pedestrian Crashes

This study investigates the relationship between pedestrian crashes and various socio-demographic, built environment, traffic exposure, and roadway characteristics across different times of day for both weekdays and weekends. Using the street segment as the unit of analysis, multilevel generalized linear mixed models with negative binomial estimators are applied to examine predictors of pedestrian crashes, including those resulting in severe injuries and fatalities, that occurred in Philadelphia, U.S., between 2010 and 2017. It is found that most of the relationships between the predictor variables and pedestrian crashes are consistent throughout the day for both weekdays and weekends. Although traffic volumes and pedestrian trips fluctuate throughout the day, average daily measures of traffic and pedestrian exposure have consistent relationships with pedestrian crashes throughout the day for both weekdays and weekends. Certain roadway characteristics, such as the amount of secondary highways and major arterials, have stronger relationships with pedestrian crashes than others at certain times of day. Results indicate that authorities should pay particular attention to pedestrian safety at night, as well as in lower-income neighborhoods throughout the day when designing interventions to improve the walking environment. Modeling pedestrian crashes by time of day provides additional information that might not be captured by temporally aggregate analyses. Scholars should consider incorporating time of day into future traffic crash analyses.

Development of a method to model the mixing energy of solutions using COSMO molecular descriptors linked with a semi-empirical model using a combined ANN-QSPR methodology

A methodology linking the interaction parameters of a semi-empirical model to COSMO molecular descriptors to represent the hE(x) is presented. A database of 4395 values of ester-alkane is used to check the procedure. Relationships are established for the model coefficients, ai1,i2,…ip, although only for a12 and for a second parameter k21, which governs the asymmetry of the representation of the mixing process. A discretization of the σ-profile and its statistical moments constitute two descriptors, as a vector, Sσ-profilej and Sσ-momentp, for a12. A third molecular descriptor/vector, is described for k21, based on the divergence of Kullback-Leibler and the molecules size, which is presented for the first time as:SRσ-profile=A1,A2,DKL[p1(σ)||p2(σ)],DKL[p2(σ)||p1(σ)]The clustering of systems in a a12/k21-space is predictable with molecular descriptors in relation to their main interactions. An ANN-QSPR binomial estimates the parameters a12 and k21 from molecular descriptors. The methodology generalizes the procedure, acceptably representing the energetic effects of solutions (R2 > 0.9).

Natural resource rents, political regimes and terrorism in Africa

The study adds to the stock of existing literature on the supposed crises-inducing role of natural resource rents, by specifically linking same to political regime and growth of terrorist attacks for a panel of forty-nine (49) African economies for the period, 1980–2012. To avail room for more policy implications, four terrorism indicators, namely: domestic, international, uncertain, and total, are used on a negative binomial regression estimator due to the count nature of terrorism data. Our findings reveal the following: first, natural resource rents have unconditional effects on transnational and total terrorism. Second, political regimes equally exert unconditional impacts on domestic and total terrorism, with both democracy and autocracy mitigating the terror-inducing effects on the one hand, with anocracy acting as a magnifying apparatus on the other hand. Third, the interaction between natural resource rents and anocracy has negative marginal effects on both domestic and total terrorism measures. Fourth, the corresponding effects of interaction, however, turned positive for both domestic and total terrorism. Lastly, the considered conditioning variables equally received extensive empirical backings but not on an equal basis. Thus, understanding the terror context of natural resource rents and the dynamics of political regimes represent formidable counterterrorist measures.

Does Democracy Really Fuel Terrorism in Africa?

ABSTRACTThis article complements the extant literature on terrorism by paying particular attention to the influence of democracy on a panel of 49 African countries, over the period 1980–2012. For this broad objective to be achieved, terrorism is decomposed into four main categories, namely domestic, transnational, uncertain and total. Due to the count nature of terrorism data, the study employs a negative binomial regression estimator, in which the following key findings are established: (i) there is a mitigating role of democracy on measures of terrorism, with the exemption of transnational terrorism; (ii) there is existence of threshold values of democracy which must be attained in order to ascertain its mitigating role on terrorism; (iii) the importance of other covariates such as conflicts, population, surface areas and physical integrity rights are no less significant across the model specifications. These results have important policy implications. We also offer suggestions for future research.

ОЦЕНКИ БИНОМИАЛЬНОЙ ВЕРОЯТНОСТИ С ОГРАНИЧЕНИЯМИ НА ИХ d-РИСКИ

ОЦЕНКИ БИНОМИАЛЬНОЙ ВЕРОЯТНОСТИ С ОГРАНИЧЕНИЯМИ НА ИХ d-РИСКИ

Democracy, Regime Durability and Terrorism in Africa

ABSTRACT This study investigated the causal linkages among democracy, regime durability and terrorism for a panel of 53 African countries over the period 1980-2012. Due to the count nature of terrorism data, the study employs a negative binomial regression estimator. The empirical analysis is based on four terrorism types namely: domestic, transnational, uncertain and total terrorism respectively. The following are the key findings: First, with the exception of the specification relating to uncertain terrorism, the unconditional effect of democracy was found to be negative on the other three dimensions of terrorism. Second, the unconditional impact of regime durability was also positive on terrorism with the exception of uncertain terrorism but in a rather inconsistent manner. Third, the interactions between democracy and regime durability are found to have positive marginal effects on all the terrorism types except uncertain terrorism. Fourth, the net effects of interaction between democracy and regime durability are positive across various models of these terrorism measures. Lastly, the theoretical priors of other covariates are equally validated across different measures of terrorism. On the policy arena, mitigating terrorism would require embracing democratic regime and mainstreaming the concomitant doctrines into the politico-institutional architecture but not without moderation in regime elongation..

Identifying obesity-related multimorbidity combinations in the United States.

Interest in understanding the effects of multimorbidity on outcomes has increased in recent years. This paper presents the most common obesity-related groupings of multimorbidity in the United States. Using Cerner HealthFacts data, we applied the frequent pattern growth algorithm to identify prevalent multimorbidity groupings of 3 or more diseases (one being obesity) by race using a dataset of 574 172 patients with obesity from all over the United States. We set the minimum prevalence to 10% and identified groupings of ICD10-CM diagnoses that occur in our dataset at or above the minimum prevalence level. We provide binomial proportion confidence interval estimates to demonstrate the validity of the proportions. We performed g-test for independence to validate differences in prevalence by race. We found 18 multimorbidity combinations with prevalence higher than or equal to 10%. Our results indicate that there are multiple common multimorbidities groupings for patients with obesity. Each multimorbidity combination is composed of diseases from the following clinical categories: endocrine, nutritional and metabolic diseases; diseases of the circulatory system; diseases of the digestive system; diseases of the nervous system; and diseases of the musculoskeletal system and connective tissue. For each multimorbidity pattern, the prevalence was found to be significantly different by race according to the g-test with P-value < .001. Most frequent patterns include essential hypertension or disorder of lipid metabolism. This study identifies common groupings of multimorbidity. We believe our data can be useful for those developing integrated care plans, particularly for those serving diverse communities.

Thirty years and 1663 consecutive Norwood procedures: Has survival plateaued?

ObjectiveHypoplastic left heart syndrome is one of the most common and challenging lesions requiring surgical intervention in the neonatal period. The Norwood procedure for hypoplastic left heart syndrome was first reported in 1983. The objective of this study was to describe early outcomes after the Norwood procedure at a single institution over 30 years. MethodsThis retrospective cohort study included all patients with hypoplastic left heart syndrome (and variants) who underwent the Norwood procedure between January 1984 and May 2014 at a single institution. The study period was divided into 6 eras: era 1, 1984 to 1988; era 2, 1989 to 1993; era 3, 1994 to 1998; era 4, 1999 to 2003; era 5, 2004 to 2008; and era 6, 2009 to 2014. The primary outcome was in-hospital mortality after the Norwood procedure. Binomial point estimates complete with 95% confidence intervals (CL0.95) were computed for the entire cohort and by era. ResultsDuring the study period, 1663 infants underwent the Norwood procedure. Overall in-hospital mortality was 25.9% (CL0.95, 23.8-28.0). Mortality by chronologic era was 40.4% (CL0.95, 34.9-45.9), 33.6% (CL0.95, 29.2-37.9), 28.7% (CL0.95, 22.8-34.6), 14.9% (CL0.95, 10.4-19.3), 11.2% (CL0.95, 7.4-15.0), and 15.7% (CL0.95, 10.3-21.1). Survival was improved in eras 4 to 6 compared with eras 1 to 3 (P all < .03). Anomalous pulmonary drainage, moderate to severe atrioventricular valve regurgitation, lower birth weight, earlier era, younger gestational age, genetic anomaly, preterm birth, race other than white or African-American, and lower weight at the Norwood procedure were associated with increased mortality. Mortality was greatest in patients with 3 or more risk factors. In the best-fitting multiple covariate model, anomalous pulmonary venous drainage, gestational age in weeks, genetic anomaly, and race other than white and African American were statistically significant contributors, after adjusting for era. ConclusionsSurvival after the Norwood procedure has plateaued despite improvements in diagnosis, perioperative care, and surgical techniques. Nonmodifiable patient characteristics are important determinants of the risk of mortality.

The Impact of Ritual Bathing in a Holy Hindu River on Waterborne Diseases

In this paper, we identify the role of religious practices on individual outcomes by examining if bathing in polluted river water for religious reasons affects the likelihood of missing days at work. To exploit the relationship, we use a primary survey (N = 1,200) of the residents of Kathmandu Valley, Nepal on their Bagmati River water usage. Probit and negative binomial estimation strategies reveal that bathing in river water, driven by traditional and cultural norms, is significantly associated with a higher probability of missing work. Among other factors, accessibility to personal sanitation facilities have a negative and significant correlation with the likelihood of missing work due to health reasons.

Of bats and livestock: The epidemiology of rabies in Trinidad, West Indies

Vampire bat-transmitted human rabies was first recognized in Trinidad during a major outbreak during the first half of the 20th century. To date, Trinidad is the only Caribbean island with vampire bat-transmitted rabies. Herein, we summarized the epidemiological situation of rabies in Trinidad during the period 1971–2015 through the analysis of field and laboratory records. During the study period, 259 domestic and wild animal rabies cases were laboratory confirmed with an annual median of 2 animal rabies cases. Over the 45 years, five significant epizootic events occurred (in 1974, 1997–1998, 2000, 2010 and 2012–2013) over which there was a significant increasing trend for the occurrence of rabies cases. The highest number of cases (87 cases) occurred during the 1997–1998 event, and the rabies positive proportion, was highest (0.7, 95% CI 0.52-0.84) for the year 2000. Rabies risk was highest for cattle (negative binomial parameter estimate 4.84, 95% CI 3.45–6.76), although numerous rabies cases were seen in the caprine population during the study period. In light of this finding, consideration should be given to including the small ruminant population in the national rabies vaccination program. Outbreaks affected mainly the counties of St. Patrick and St. George East, with epidemic progression outwards, and these areas should be prioritized for prevention and control efforts.