Modeling unobserved heterogeneity using finite mixture random parameters for spatially correlated discrete count data

2016 ◽  
Vol 91 ◽  
pp. 492-510 ◽  
Author(s):  
Prasad Buddhavarapu ◽  
James G. Scott ◽  
Jorge A. Prozzi
Keyword(s):  
Count Data ◽  
Unobserved Heterogeneity ◽  
Finite Mixture ◽  
Random Parameters ◽  
Spatially Correlated

Modeling Safety Effects of Horizontal Curve Design on Injury Severity of Single-Motorcycle Crashes with Mixed-Effects Logistic Model

2017 ◽  
Vol 2637 (1) ◽  
pp. 38-46 ◽  
Author(s):  
Chunfu Xin ◽  
Zhenyu Wang ◽  
Chanyoung Lee ◽  
Pei-Sung Lin
Keyword(s):  
Logistic Model ◽  
Injury Severity ◽  
Unobserved Heterogeneity ◽  
Mixed Effects ◽  
Severe Injury ◽  
Horizontal Curve ◽  
Random Parameters ◽  
Horizontal Curves ◽  
Curve Design ◽  
Motorcycle Crashes

Horizontal curves have been of great interest to transportation researchers because of expected safety hazards for motorcyclists. The impacts of horizontal curve design on motorcycle crash injuries are not well documented in previous studies. The current study aimed to investigate and to quantify the effects of horizontal curve design and associated factors on the injury severity of single-motorcycle crashes with consideration of the issue of unobserved heterogeneity. A mixed-effects logistic model was developed on the basis of 2,168 single-motorcycle crashes, which were collected on 8,597 horizontal curves in Florida for a period of 11 years (2005 to 2015). Four normally distributed random parameters (moderate curves, reverse curves, older riders, and male riders) were identified. The modeling results showed that sharp curves (radius <1,500 ft) compared with flat curves (radius ≥4,000 ft) tended to increase significantly the probability of severe injury (fatal or incapacitating injury) by 7.7%. In total, 63.8% of single-motorcycle crashes occurring on reverse curves are more likely to result in severe injury, and the remaining 26.2% are less likely to result in severe injury. Motorcyclist safety compensation behaviors (psychologically feeling safe, and then riding aggressively, or vice versa) may result in counterintuitive effects (e.g., vegetation and paved medians, full-access-controlled roads, and pavement conditions) or random parameters (e.g., moderate curve and reverse curve). Other significant factors include lighting conditions (darkness and darkness with lights), weekends, speed or speeding, collision type, alcohol or drug impairment, rider age, and helmet use.

scholarly journals Determining the Key Capacities of Effective Leaders in Malaysian Public and Private Focused Universities

SAGE Open ◽  
2018 ◽  
Vol 8 (4) ◽  
pp. 215824401880762 ◽  
Author(s):  
Majid Ghasemy ◽  
Sufean Bin Hussin ◽  
Ahmad Zabidi Bin Abdul Razak ◽  
Mohd Jamil Bin Maah ◽  
Simin Ghavifekr
Keyword(s):  
Unobserved Heterogeneity ◽  
Finite Mixture ◽  
Future Directions ◽  
Public And Private ◽  
Leadership Performance ◽  
Managerial Competencies ◽  
Effective Leaders ◽  
Performance Map ◽  
Performance Drivers ◽  
Map Analysis

The study was undertaken to identify the essential leadership capabilities and managerial competencies as the key leadership performance drivers in Malaysian focused universities. To collect data, the previously developed scales of capabilities, competencies, and leadership performance in the context of Malaysian Higher Education (HE) were distributed among the leaders in seven public focused and 12 private focused universities. In total, 172 completed surveys were collected among which 94 had been filled out by the leaders in Malaysian public focused and 78 had been completed by leaders in private focused universities. The data were screened and SmartPLS 3 was employed to analyze the data. Also, Finite Mixture Partial Least Squares (FIMIX-PLS) segmentation and Importance–Performance Map Analysis (IPMA) were run to extend the results. The outcome of FIMIX-PLS didn’t reveal unobserved heterogeneity within the data and, through IPMA, change-oriented capability was identified as the main improvement area to be addressed by management activities. Moreover, the implications of the findings were discussed and future directions were recommended.

scholarly journals Analysis of Severe Injury Accident Rates on Interstate Highways Using a Random Parameter Tobit Model

2017 ◽  
Vol 2017 ◽  
pp. 1-6 ◽  
Author(s):  
Minho Park ◽  
Dongmin Lee
Keyword(s):  
Regression Model ◽  
Unobserved Heterogeneity ◽  
Random Parameter ◽  
Tobit Model ◽  
Severe Injury ◽  
Parameter Estimates ◽  
Random Parameters ◽  
Tobit Regression ◽  
Accident Rates ◽  
Tobit Regression Model

In this study, a random parameter Tobit regression model approach was used to account for the distinct censoring problem and unobserved heterogeneity in accident data. We used accident rate data (continuous data) instead of accident frequency data (discrete count data) to address the zero cell problems from data where roadway segments do not have any recorded accidents over the observed time period. The unobserved heterogeneity problem is also considered by using random parameters, which are parameter estimates that vary across observations instead of fixed parameters, which are parameter estimates that are fixed/constant over observations. Nine years (1999–2007) of panel data related to severe injury accidents in Washington State, USA, were used to develop the random parameter Tobit model. The results showed that the Tobit regression model with random parameters is a better approach to explore factors influencing severe injury accident rates on roadway segments under consideration of unobserved heterogeneity problems.

Modelling Museum Visitors’ Perception and Experience of Authenticity: Examining Heterogeneity with a Finite Mixture Model

2021 ◽  
Vol 56 ◽  
pp. 0-0
Author(s):  
Claudia Bauer-Krösbacher ◽  
Josef Mazanec
Keyword(s):  
Latent Variable ◽  
Structural Equation ◽  
Latent Class ◽  
Structural Model ◽  
Unobserved Heterogeneity ◽  
Model Fitting ◽  
Equation Model ◽  
Finite Mixture ◽  
Museum Visitors ◽  
Specific Strength

Purpose. In this study, the authors explore the role of museum visitors’ perceptions and experiences of authenticity. They introduce several variants of authenticity experience and analyse how they are intertwined and feed visitor satisfaction. Method. The authors apply a multi-step model fitting and validation procedure including inferred causation methods and finite mixture modelling to verify whether the visitors’ perceptions of authenticity are subject to unobserved heterogeneity. They elaborate an Authenticity Model that demonstrates out-of-sample validity and generalisability by being exposed to new data for another cultural attraction in another city. Then, they address the heterogeneity hypothesis and evaluate it for the case study with the larger sample. Findings. In both application cases, the Sisi museum in Vienna and the Guinness Storehouse in Dublin, the empirical results support the assumed cause-effect sequence, translating high quality information display—from traditional and multimedia sources—into Perceived Authenticity and its experiential consequences such as Depth and Satisfaction. Accounting for unobserved heterogeneity detects three latent classes with segment-specific strength of relationships within the structural model. Research and conclusions limitations. The combined latent-class, structural-equation model needs validation with another sample that would have to be larger than the available Guinness database. Future studies will have to complement the purely data-driven search for heterogeneity with theory-guided reasoning about potential causes of diversity in the strength of the structural relationships. Practical implications. Cultural heritage sites are among the attractions most typical of city tourism. History tends to materialise in the artefacts accumulated by the population among the urban agglomerations, and museums are the natural places for preserving exhibits of cultural value. Authenticity must be considered an important quality assessment criterion for many visitors, whereby, the distinction between object authenticity and existential authenticity is crucial. Originality. In addition to making substantive contributions to authenticity theory, the authors also extend previous research in terms of methodological effort. Authenticity research, so far, has neither exploited inferred causation methods nor combined latent variable modelling with detecting unobserved heterogeneity. Type of paper: Research article.

scholarly journals Modelling Unobserved Heterogeneity in Claim Counts Using Finite Mixture Models

Risks ◽  
2020 ◽  
Vol 8 (1) ◽  
pp. 10 ◽  
Author(s):  
Lluís Bermúdez ◽  
Dimitris Karlis ◽  
Isabel Morillo
Keyword(s):  
Mixture Models ◽  
Finite Mixture Models ◽  
Unobserved Heterogeneity ◽  
Finite Mixture ◽  
Insurance Claim ◽  
Poisson Models ◽  
Excess Of Zeros ◽  
Car Insurance ◽  
Insurance Data ◽  
Natural Way

When modelling insurance claim count data, the actuary often observes overdispersion and an excess of zeros that may be caused by unobserved heterogeneity. A common approach to accounting for overdispersion is to consider models with some overdispersed distribution as opposed to Poisson models. Zero-inflated, hurdle and compound frequency models are typically applied to insurance data to account for such a feature of the data. However, a natural way to deal with unobserved heterogeneity is to consider mixtures of a simpler models. In this paper, we consider k-finite mixtures of some typical regression models. This approach has interesting features: first, it allows for overdispersion and the zero-inflated model represents a special case, and second, it allows for an elegant interpretation based on the typical clustering application of finite mixture models. k-finite mixture models are applied to a car insurance claim dataset in order to analyse whether the problem of unobserved heterogeneity requires a richer structure for risk classification. Our results show that the data consist of two subpopulations for which the regression structure is different.

Sign in / Sign up

Export Citation Format

Share Document