Tobit Type Research Articles

Nonlinear distributed filtering subject to censoring measurements under dynamic event-triggered communication mechanism: The state-saturated case

This paper studies the nonlinear distributed filtering problem for a class of discrete state-saturated systems with censoring measurements and multiplicative noises under the dynamic event-triggered communication mechanism (DETCM). The censoring measurements, which are characterized by the Tobit type I model, unavoidably arise in the measurement signals resulted from the sudden changes of circumstances or the repairs of components. Meanwhile, for the sake of reducing the communication cost and improving the data transmission efficiency, the DETCM is used to determine when the sensor has an opportunity to transmit the information to its adjacent nodes according to the fixed communication topology. The main purpose of the paper is to design a novel distributed filter under the DETCM for the underlying sensor networks, where a particular upper bound of the filtering error covariance is obtained by means of the mathematical induction approach and the matrix theory. Then, the proposed upper bound can be minimized via designing the suitable filter gain. Further, the boundedness of filtering error dynamics is proved based on some pre-set conditions. Finally, illustrative simulation experiments are provided to illustrate the effectiveness of the presented distributed filtering algorithm.

COVID-19 and the efficiency of health systems in Europe

BackgroundThis study aims at analyzing the efficiency of the health systems of 31 European countries in treating COVID-19, for the period January 1, 2020 – January 1, 2021, by incorporating some factors from a multidimensional perspective.MethodsThe methodology used in the research was Data Envelopment Analysis (DEA), through which efficiency scores for health systems have been calculated. The research was performed considering three stages: the first wave (January 1–June 15), the relaxation period (June 15–October 1) and the second wave (October 1–December 31). In evaluating the determinants of the efficiency of health systems, six major fields of influence were taken into account: health care, health status, population, economic, cultural/societal and governmental issues, all covering 15 indicators. After measuring the efficiency, we used the Tobit type regression to establish the influencing elements on it.ResultsThe results for the public health systems of European states were determined for each country and period. We evaluated the efficiency of health systems in Europe against COVID-19, starting from health inputs (COVID-19 cases, physicians, nurses, hospital beds, health expenditure) and output (COVID-19 deaths). The obtained outputs show that, especially in the first phase of the pandemic, the inefficiency of the health systems was quite high, mainly in Western countries (Italy, Belgium, Spain, UK). In the relaxation phase and in the second wave, the Western states, severely affected at the beginning of the pandemic, began to take adequate measures and improve the efficiency of their sanitary systems. Instead, Eastern European countries were hit hard by the inefficiency of health systems (Bulgaria, Greece, Hungary, Romania). After Tobit regression, results of the study show that the influencing elements are different for the three stages: concerning the first wave, comobirdities, population age, and population density are important; for relaxation period a great influence have government effectiveness and power distance; with respect to second wave, the relevant factors are education and population density.ConclusionsThe results obtained could serve as starting points for health policymakers to perform comparative analyzes in terms of good practices in the health system and to develop national plans to better deal with health crises. At the same time, they can be used internationally to achieve a coherent and effective community response to the pandemic.

Set-membership filtering for discrete time-varying nonlinear systems with censored measurements under Round-Robin protocol

Abstract This paper addresses the set-membership filtering problem for a class of discrete time-varying nonlinear systems with censored measurements and time-delay under the Round-Robin protocol. The censored measurements resulting from occlusion region, limit-of-detection or sensor faults are modeled by the Tobit Type I model, in which the given threshold governs whether or not the measurement information is directly utilized. A periodic protocol named Round-Robin protocol is employed to reduce the communication burden. Subsequently, a novel periodical model is given to describe censored measurement and the Round-Robin protocol in a uniform framework. In the light of such a model, the existence condition of the set-membership filter is described by a series of periodic threshold-dependent recursive linear matrix inequalities (RLMIs). As a consequence, the desired filter parameters can be obtained by the existence conditions and optimizing the corresponding ellipsoid parameters with the help of the convex optimization approach. Finally, a simulation is provided to illustrate the effectiveness of the proposed estimation approach.

Acceptability and willingness to pay for telemedicine services in Enugu state, southeast Nigeria.

BackgroundThis study examines the level of awareness, acceptability and consumers’ willingness to pay (WTP) for telemedicine services using the contingent valuation method (CVM). This work is important as it elicits the value that consumers attach to telemedicine given there is a gap in this knowledge in many sub-Saharan countries such as in Nigeria.MethodsThe study was based on primary data obtained through an interviewer-administered questionnaire of 370 individuals including both males and females from 25 years and over, to collect data on respondents’ awareness of, acceptability of, and WTP for telemedicine, using the bidding game question format. A socioeconomic status (SES) index was created, based on information on household assets, and was used to categorize respondents into SES quartiles. The data were analyzed using a combination of descriptive techniques, logistics and the Tobit regression model (Tobit Type 1) methods.ResultsThe study found that majority of the people (58.9%) had no knowledge of telemedicine. However, 48.7% of the respondents were willing to pay for telemedicine. The mean WTP for a telemedicine was US$2.04 for each visit. Tobit regression analysis showed that respondents’ socioeconomic status (SES) was the main statistically significant variable that explained their WTP for telemedicine.ConclusionThe study has shown that there is a low-level awareness of and WTP for telemedicine services in Enugu State, South East of Nigeria. The finding of a positive relationship between SES and WTP implies that the poor may not be able to pay for telemedicine and may need government subsidies to be able to benefit from such service. Also, government and their partners need to undertake wide scale campaign before the introduction of telemedicine.

The Tobit Kalman Filter: An Estimator for Censored Measurements

Tobit model censored data arise in multiple engineering applications through saturating sensors, limit-of-detection effects, and image frame effects. In this brief, we introduce a novel formulation of the Kalman filter for Tobit Type 1 censored measurements. Our proposed formulation, called the Tobit Kalman filter, is identical to the standard Kalman filter in the no-censoring case. At or near the censored region, the Tobit Kalman filter utilizes a local approximation of the probability of censoring in order to provide a fully recursive estimate of the state and state error covariance. The additional computational burden of the method compared with the standard Kalman filter is limited to the calculation of $m$ normal probability density functions and $m$ normal cumulative density functions per update, where $m$ is the number of measurements.

SCORING MODELLING OF COLLECTION FINANCIAL FLOWS

Nowadays, an expansive growth of past due debts in retail crediting is one of the most important problems of financial-credit system of Russia as well as of other countries. Collection activity may be optimized by implementing collection scoring systems. The paper regards one of the main problems of collection scoring – evaluating of collection financial flows and collection probability. The solution with the use of Tobit Type II model is offered, which allows determining the probability that debtor will make payments, dividing debtors to the groups of payers and defaulters and estimating the probable sum of payment for each debtor. Factors that have the most influence on the probability of payment (surety amount, loan duration, residence region etc.) are detected. As a classification result, the category of debtors who will not return the debt is defined. For other debtors on the basis of linear model the probable monthly sum of payment is calculated. The results of this research may serve as a foundation for planning work with the debtor, will allow identifying hopeless debts and in accordance with that effectively allocating collection resources and reducing transaction costs.

El alcohol en el presupuesto familiar: incidencia del poder adquisitivo y de la composición demográfica de los hogares

Among the problems associated with family alcohol consumption is the effect on household resource distribution, with a larger incidence in those households that are socially more vulnerable. This study examines the influence that household socioeconomic and demographic characteristics have on the share of alcoholic beverages in the household budget, using data from Santa Fe, Argentina for the period 2004-2005. Engel parametric curves are estimated using a sample selection model (Tobit type II). The sample is subdivided using the poverty line as the criterion. The results show that the most relevant characteristics differ depending on whether the household is poor or not. In non-poor households, variables such as the age of the household head, the share of women and the number of minors have a statistically significant effect on alcohol’s share of expenditures. In contrast, only characteristics related to purchasing power are relevant in poor households.

Finding Donors by Relationship Fundraising

Our research utilizes revenue–business-based relationships and data to expand the donor bases of non-profit organizations. Fundraisers desire to predict who will donate and how much to allocate their marketing resources effectively. To answer both questions, we develop the Spatial Tobit Type 2 (ST2) model that integrates the auto-Logistic (AL) and auto-Gaussian (AG) models into the Tobit type 2 framework. The AL component is used to predict who is likely to donate by inferring inter-client similarities based on the clients' transaction information from the revenue businesses. Similarly, the AG component is used to predict how much based on a similar measure of inter-client similarities. The Tobit type 2 framework combines both components into the single framework of ST2. Our empirical application linking a veterinary school's medical treatment records to its donation records demonstrates that clients' relationships built through their medical treatments at the school hospital positively contribute to their donation decisions.

Likelihood Estimation for Censored Random Vectors

ABSTRACT This article shows how to construct a likelihood for a general class of censoring problems. This likelihood is proven to be valid, i.e. its maximizer is consistent and the respective root-n estimator is asymptotically efficient and normally distributed under regularity conditions. The method generalizes ordinary maximum likelihood estimation as well as several standard estimators for censoring problems (e.g. tobit type I–tobit type V).

First-difference estimator for panel censored-selection models

We propose a semiparametric first-difference estimator for panel censored-selection models where the selection equation is of tobit type. The estimator allows the unit-specific term to be arbitrarily related to regressors. The estimator minimizes a convex function and does not require any smoothing. A simulation study is provided comparing our proposal with the estimators of Wooldridge (Journal of Econometrics 68 (1995) 115) and Honoré and Kyriazidou (Econometric Reviews (2000)).

Asymptotic Covariance Matrices of Two-Stage Probit and Two-Stage Tobit Methods for Simultaneous Equations Models with Selectivity

The paper discusses the two-stage estimation method for switching simultaneous equations models where the criterion function determining the switching is of the probit type and the tobit type. It derives the asymptotic covariance matrices of these estimators and shows that when the criterion function is of the probit type the correct covariance matrix is underestimated when the heteroscedasticity introduced in the first step is ignored, whereas the same is not necessarily the case for one of the regimes when the criterion function is of the tobit type.