LRMoE.jl: a software package for insurance loss modelling using mixture of experts regression model

2021 ◽  
pp. 1-22
Author(s):  
Spark C. Tseung ◽  
Andrei L. Badescu ◽  
Tsz Chai Fung ◽  
X. Sheldon Lin
Keyword(s):  
Parameter Estimation ◽  
Mixture Models ◽  
Model Evaluation ◽  
Software Package ◽  
Mixture Of Experts ◽  
Statistical Software ◽  
Distinctive Features ◽  
Key Features ◽  
Loss Modelling ◽  
Data Censoring

Abstract This paper introduces a new julia package, LRMoE, a statistical software tailor-made for actuarial applications, which allows actuarial researchers and practitioners to model and analyse insurance loss frequencies and severities using the Logit-weighted Reduced Mixture-of-Experts (LRMoE) model. LRMoE offers several new distinctive features which are motivated by various actuarial applications and mostly cannot be achieved using existing packages for mixture models. Key features include a wider coverage on frequency and severity distributions and their zero inflation, the flexibility to vary classes of distributions across components, parameter estimation under data censoring and truncation and a collection of insurance ratemaking and reserving functions. The package also provides several model evaluation and visualisation functions to help users easily analyse the performance of the fitted model and interpret the model in insurance contexts.

Assessment of serum interleukin-6 with a rapid test. The diagnosis of neonatal sepsis can be established or ruled out

2007 ◽  
Vol 148 (34) ◽  
pp. 1609-1614 ◽  
Author(s):  
Éva Görbe ◽  
Judit Jeager ◽  
Bálint Nagy ◽  
Ágnes Harmath ◽  
Erik Hauzman ◽  
...  
Keyword(s):  
Interleukin 6 ◽  
Neonatal Sepsis ◽  
Software Package ◽  
Rapid Test ◽  
Statistical Software

Bevezetés: A neonatális szepszis mortalitása magas, és koraszülöttek esetén a szepszis rizikója emelkedik a születési súly csökkenésével. Anyag és módszer: A szerzők gyorsteszt segítségével 12 érett újszülött és 60 igen kis súlyú (VLBW) koraszülött interleukin-6-vérszintjét határozták meg a C-reaktív protein vizsgálatával egyidejűleg, akiket a Semmelweis Egyetem I. Számú Szülészeti és Nőgyógyászati Klinikájának Neonatális Intenzív Centrumában kezeltek 2005-ben és 2006-ban. A szérum-IL-6 meghatározása gyorsteszt segítségével történt (Milenia Quickline IL-6, PicoScan system). Eredmények: Vizsgálataikban a szérum-interleukin-6- és CRP-meghatározás korrelált. A szérum-IL-6-meghatározás szenzitivitása a CRP-értékkel együtt az általuk vizsgált betegcsoportban 100% volt, álnegatív eset nem fordult elő. A vizsgálat pozitív prediktív értéke 93%. Adataikat Mann–Whitney-teszt segítségével analizálták (SPSS Statistical Software Package, Chicago, IL, USA). Szignifikáns különbség volt az igazolt szepszis és az infekciós betegcsoport IL-6-értékei között ( p = 0,048), valamint az infekciós és nem infekciós csoport interleukin-6-értékei között ( p < 0,005). Következtetések: Az igen kis súlyúak nem specifikus infekciós tünetekhez hasonló reakcióit értékelve, a szeptikus és nem infekciós esetek elkülönítése a neonatális morbiditás és mortalitás csökkentése érdekében is fontos szempont, a költségek csökkentésével egyidejűleg.

LRMoE: An R Package for Flexible Actuarial Loss Modelling Using Mixture of Experts Regression Model

2020 ◽  
Author(s):  
Spark C. Tseung ◽  
Andrei Badescu ◽  
Tsz Chai Fung ◽  
Xiaodong Sheldon Lin
Keyword(s):  
Regression Model ◽  
R Package ◽  
Mixture Of Experts ◽  
Loss Modelling

scholarly journals Why Socially Responsible? Determinant Factors of Organizational Performance: Case of Dangote Cement Factory in Ethiopia

2021 ◽  
Vol 13 (9) ◽  
pp. 4783
Author(s):  
Anna Dunay ◽  
Abebe Ayalew ◽  
Gemechu Abdissa
Keyword(s):  
Corporate Social Responsibility ◽  
Organizational Performance ◽  
Software Package ◽  
Positive Relationship ◽  
Multiple Linear Regression Model ◽  
Sampling Technique ◽  
Socially Responsible ◽  
Statistical Software ◽  
Cement Factory ◽  
Corporate Social

The main purpose of this study is to examine the effect of corporate social responsibility on the organizational performance of the Dangote cement factory in Ethiopia. In order to achieve the research objectives, the authors adopted both a descriptive and explanatory research design. Structured questionnaires were used to gather data from the targeted group of the study, where the probability and non-probability sampling technique was employed to draw a sample of 179. The collected data were presented and analyzed using the SPSS (version 20) statistical software package. A multiple linear regression model was applied to see the effect of CSR on organizational performance. The study showed that philanthropic activities, ethical activities, and legal activities affect organizational performance, have a positive relationship, and are statistically significant at a 1% confidence interval. It was concluded that for the existence of business industries, the community relation is key to ensuring a conducive atmosphere for the business to succeed.

scholarly journals The results of a subjective assessment of the organization of inpatient care for newborn parents and neonatologists

2020 ◽  
Vol 101 (3) ◽  
pp. 412-417
Author(s):  
K E Moiseeva ◽  
E N Berezkina ◽  
V V Kirilenko
Keyword(s):  
Software Package ◽  
Inpatient Care ◽  
Medical Personnel ◽  
Subjective Assessment ◽  
Technical Equipment ◽  
Medical Organization ◽  
Statistical Software ◽  
Financial Costs ◽  
Individual Laboratory ◽  
Mathematical Processing

Aim. To study the opinion of mothers of newborns and neonatologists about the organization of inpatient care for newborns in St. Petersburg. Methods. An anonymous survey of 2123 mothers of newborns and 172 neonatologists of St. Petersburg was conducted. The representativeness of the sample was checked by using the method of Professor A.M. Merkov, with the errors do not exceed 4 and 3%, respectively. Mathematical processing and data analysis were carried out by using the statistical software package PASW STATISTICS. Results. 28.9% of mothers were partially or completely unsatisfied with the organization of inpatient care for newborns, in most cases due to the unfriendly and inattentive attitude by the medical staff (22.4%), the unsatisfactory provision by child care products (12.8%) and poor material and technical equipment of a medical organization (12.5%). On average, the human qualities of neonatologists were rated quite high by mothers at 4.630.09 (out of 5) points, and in mid-level practitioners were significantly lower 3.910.08 points (p 0.05). In general, staying a newborn in a medical organization required financial costs for 37.3% of women, and 13.9% of respondents who received help through compulsory medical insurance paid for individual laboratory and other tests on their own. Mothers rated the organization of inpatient care for newborns on average 4.010.09 points. Compared to mothers, neonatologists rated it higher in the medical organization they work for and lower overall in St. Petersburg (M=4.110.10 points and M=3.780.12 points; p 0.05). According to the doctors, the main disadvantages of organizing inpatient care for newborns are poor material and technical equipment and problems associated with the staffing and qualifications of medical personnel. Conclusion. There is a need to improve the process of providing inpatient care to newborns.

scholarly journals Regularized Parameter Estimation in High-Dimensional Gaussian Mixture Models

2011 ◽  
Vol 23 (6) ◽  
pp. 1605-1622 ◽  
Author(s):  
Lingyan Ruan ◽  
Ming Yuan ◽  
Hui Zou
Keyword(s):  
Parameter Estimation ◽  
Mixture Models ◽  
Gaussian Mixture Models ◽  
Expectation Maximization Algorithm ◽  
Real Data ◽  
Gaussian Mixture ◽  
High Dimensional ◽  
Model Based Clustering ◽  
Text Type ◽  
Effective Dimensionality

Finite gaussian mixture models are widely used in statistics thanks to their great flexibility. However, parameter estimation for gaussian mixture models with high dimensionality can be challenging because of the large number of parameters that need to be estimated. In this letter, we propose a penalized likelihood estimator to address this difficulty. The [Formula: see text]-type penalty we impose on the inverse covariance matrices encourages sparsity on its entries and therefore helps to reduce the effective dimensionality of the problem. We show that the proposed estimate can be efficiently computed using an expectation-maximization algorithm. To illustrate the practical merits of the proposed method, we consider its applications in model-based clustering and mixture discriminant analysis. Numerical experiments with both simulated and real data show that the new method is a valuable tool for high-dimensional data analysis.

On the Number and Nature of Common Factors Extracted by the Eigenvalue-One Rule Using BMDP VS SPSSX

1989 ◽  
Vol 65 (1) ◽  
pp. 155-160 ◽  
Author(s):  
Raymond Hubbard ◽  
Stuart J. Allen
Keyword(s):  
Factor Analysis ◽  
Empirical Data ◽  
Software Package ◽  
Common Factor ◽  
Common Factors ◽  
Computer Programs ◽  
Data Sets ◽  
Statistical Software ◽  
Common Factor Analysis ◽  
Psychology Literature

Given nuances in the computer programs, unwary researchers performing a common factor analysis on the same set of data can be expected to arrive at very different conclusions regarding the number and nature of extracted factors if they use the BMDP, as opposed to the SPSSx (or SAS), statistical software package. This is illustrated using six well-known empirical data sets from the psychology literature.

Sign in / Sign up

Export Citation Format

Share Document