Tobit Maximum Likelihood Estimation Research Articles

A New Tobit Ridge-Type Estimator of the Censored Regression Model With Multicollinearity Problem

In the censored regression model, the Tobit maximum likelihood estimator is unstable and inefficient in the occurrence of the multicollinearity problem. To reduce this problem's effects, the Tobit ridge and the Tobit Liu estimators are proposed. Therefore, this study proposes a new kind of the Tobit estimation called the Tobit new ridge-type (TNRT) estimator. Also, the TNRT estimator was theoretically compared with the Tobit maximum likelihood, the Tobit ridge, and the Tobit Liu estimators via the mean squared error criterion. Moreover, we performed a Monte Carlo simulation to study the performance of the TNRT estimator compared with the previously defined estimators. Also, we used the Mroz dataset to confirm the theoretical and the simulation study results.

Two‐parameter estimation for Tobit model: An application to national health and nutrition examination survey dataset

AbstractFixed censorship is usually encountered in medical fields, as well as biological, econometric, and engineering researches. It is quite possible to come across censored data with multicollinearity in real‐life studies. The multicollinearity affects traditional Tobit maximum likelihood estimation, which is often used in presence of censored data. Biased estimators such as Tobit Liu estimator with one biasing parameter can be used for solving the multicollinearity. In this study, Tobit two‐parameter estimator with two biasing parameters is proposed as an alternative to the classical Tobit maximum likelihood and Tobit Liu estimators for the censored data. This new estimator provides advantages from two different aspects thanks to having two biasing parameters. With a simulation study consisting of several scenarios where various levels of factors like the number of independent variables, sample size, correlation degree, variance, and censorship are examined, an in‐depth experimental analysis is conducted. In these scenarios, two different biasing parameters' selection methods where one of the biasing parameters is fixed to determine the other one are used and their corresponding outputs are obtained. In addition, a real‐life application is carried out with the National Health and Nutrition Examination Survey public‐use dataset which includes some demographic and health‐related laboratory measurements. The simulation study and data analysis results show that the proposed estimator is more advantageous to its competitors.

Tobit Liu estimation of censored regression model: an application to Mroz data and a Monte Carlo simulation study

Multicollinearity is often ignored in censored regression model. In this respect, Tobit Liu estimation is proposed as an alternative in order to dispel the adverse effects of multicollinearity on the maximum likelihood estimation. Tobit Liu estimator is compared with Tobit ridge estimator and Tobit maximum likelihood estimator, theoretically via mean square error. For empirical analysis, we prefer Mroz dataset which is a phenomenon in the context of censored regression. Since many studies have investigated Mroz dataset by neglecting multicollinearity, we handle this dataset in the context of multicollinearity in this paper. Moreover, it is seen that multicollinearity is not included in pioneer studies' simulation designs. Therefore, we conduct a Monte Carlo simulation study where we take account of different levels of multicollinearity while generating data. Briefly, this study contributes to filling an important gap in the literature and proposes to investigate other econometrically censored data in the context of multicollinearity.

Revenue Structure and Spending Behavior in Nonprofit Organizations

Nonprofit organizations (NPOs) rely on multiple funding sources to meet organizational needs; and, heavy reliance on any one revenue source can limit an NPO’s ability to allocate funding. As such, in this study, we examine the association between funding source and spending behavior in a national sample of NPOs from 2008 to 2012. Our sample consists of 51,812 observations from 16,035 unique NPOs. Using Tobit maximum likelihood estimation, we find that NPOs that rely on, both, restricted and nonrestricted revenue sources are more limited in their ability to spend on administrative needs, whereas donation income restricts personnel spending of compensation. Revenue diversification, though, can help NPOs overcome this limitation and can provide NPOs with greater spending flexibility. Our findings also show, however, that these results differ for NPO hospitals and universities.

센서링과 절단 환경에서의 경로 손실 추정 방법에 대한 비교 연구

밀리미터파 대역은 주파수가 30GHz-300GHz이고, 파장이 10mm-1mm인 EHF (Extremely High Frequency) 대역이다. 밀리미터파 대역에서는 장애물이 있는 경우 전파 감쇠가 심하기 때문에 Line-of-Sight (LoS)가 아닌 경우 신호가 잘 잡히지 않는다. 그렇기 때문에 밀리미터파 대역에서 신호 감쇠 측정을 할 경우에 측정 장비가 noise와 구별할 수 없는 신호들이 관찰된다. 이와 같이 감쇠가 심한 환경에서 신호 감쇠 data를 보면 특정한 값에서 제한을 받는 것이 관찰된다. 특정한 값에서 제한 받는 것을 그대로 두고 일반적인 Least square로 추정을 하는 경우에는 감쇠 exponent를 과소평가 할 수도 있다. 본 논문에서는 특정한 값에서 제한을 받아도 정확한 추정이 가능한 Tobit Maximum Likelihood Estimation, Heckman Two-stage Model 그리고 Truncation Regression model의 성능 비교를 하였다. The millimeter wave band is in the extremely high frequency band whose frequency and wavelength are 30-300GHz and 10-1mm respectively. When the obstacles block the propagation path which is not Line-of-Sight (LoS), due to a high propagation loss, it is hard to receive a signal in the millimeter wave band. Therefore When the path loss is measured in the millimeter wave band, the signal which is not distinguished from the noise is observed. Consequently, the path loss data which is limited in certain value is observed in the high propagation loss environment. If the original least square is implemented without taking the limitation of certain value into account, the path loss exponent may be underestimated. In this paper, the performance of Tobit Maximum Likelihood Estimation, Heckman Two-stage Model and Truncation Regression Model which can estimate properly in the censoring or truncated environments are compared.

Statistical Modeling and Estimation of Censored Pathloss Data

Pathloss is typically modeled using a log-distance power law with a large-scale fading term that is log-normal. However, the received signal is affected by the dynamic range and noise floor of the measurement system used to sound the channel, which can cause measurement samples to be truncated or censored. If the information about the censored samples are not included in the estimation method, as in ordinary least squares estimation, it can result in biased estimation of both the pathloss exponent and the large scale fading. This can be solved by applying a Tobit maximum-likelihood estimator, which provides consistent estimates for the pathloss parameters. This letter provides information about the Tobit maximum-likelihood estimator and its asymptotic variance under certain conditions.

The Impact of Employee Compensation and Financial Performance on Nonprofit Organization Donations

This study focuses on the complex interaction between employee compensation and organizational financial performance. In particular, we investigate the impact of higher than median employee compensation on nonprofit donations and whether such impact is conditional on the financial performance of the organization. Using recent panel data from 10,206 nonprofit organizations across multiple tax designations, we test the hypotheses with Tobit maximum likelihood estimation that incorporates measures of employee compensation, financial performance, financial capacity, and controls for state factors and nonprofit type. Findings demonstrate that employee compensation above the median is unfavorable for donations overall; however, the negative effect is mitigated by sound financial performance. This study highlights the collective impact that exists between financial performance and employee compensation on organizational donative resources, directly speaks to an organization’s internal capacity to raise private revenue, and adds subtlety to the ongoing discussions of how much is enough compensation for high-quality nonprofit leadership.

Remedies for information asymmetry in online transaction

PurposeThis study seeks to investigate the signals on which consumers may rely to reduce the problems of information asymmetry on an online auction site. The research aims to develop and test based on information signaling theory. It classifies signals from auction web pages into three types: seller reputation, product condition, and argument quality. To understand how the signals affect consumers' online buying decisions, the study intends to test the impacts of these signals on the auction outcome variables: number of bids, auction success, and willingness to pay.Design/methodology/approachThe paper employs an empirical test with real observation data comprised of 5,013 samples coded from the eBay auction site in the USA. Ordinary least squares (OLS) regression is used to predict the effect of web page signals on the number of bids, logistic regression to determine which web page signals contribute to auction success, and Tobit maximum likelihood estimation to estimate the impact of web page signals on willingness to pay.FindingsResults show that, in addition to the seller's reputation, signals like product condition and the quality of the sellers' arguments on the web page are significantly related to the three auction outcomes. Buyers tend to rely on these signals to resolve information asymmetry in online auction transactions.Originality/valuePast studies have found that the seller's feedback score is central to a positive online auction outcome. This paper is the first to classify web page signals comprehensively and to investigate their impacts on online auction outcomes using real transaction data. The findings provide substantial evidence and implications for both academic research and practitioners in online auctions. A dynamic strategy for success in online auctions is offered in the conclusion section.

Determinants of Food Industry Performance: Survey Data and Regressions for Denmark

AbstractThis paper investigates empirically the determinants of firms’ performance in the agri‐food sector by using recent survey data for Denmark. Treating sales per employee as a proxy for value added, we estimate several bootstrapped regression models to draw conclusions on the marginal effects of potential performance determinants such as the form and nature of ownership, stage of the food chain and commodity sector, new product development, staff quality, firms’ competitive stance, and elements of firms’ strategy. To draw robust inferences we apply, besides the ordinary heteroscedasticity‐corrected Tobit maximum likelihood estimator, a non‐parametric least absolute deviations estimator (LAD/CLAD) based on a quantile regression procedure. The results indicate that we cannot reject the hypothesis of no influence of dominant orientation on value added. Rather, firms’ focus on human capital, stage and commodity sector better explains their value addition. We reject the hypothesis that regional networks have no influence on value added. Location in Århus, emphasis on human capital and the negative influence of outsourcing on value added all provide supporting evidence. We reject the hypothesis of no influence of foreign direct investment (FDI), and moreover propose that FDI has targeted the Danish domestic market as a source of value added.

The Tobit model with a non‐zero threshold

The standard Tobit maximum likelihood estimator under zero censoring threshold produces inconsistent parameter estimates, when the constant censoring threshold γ is non‐zero and unknown. Unfortunately, the recording of a zero rather than the actual censoring threshold value is typical of economic data. Non‐trivial minimum purchase prices for most goods, fixed cost for doing business or trading, social customs such as those involving charitable donations, and informal administrative recording practices represent common examples of non‐zero constant censoring threshold where the constant threshold is not readily available to the econometrician. Monte Carlo results show that this bias can be extremely large in practice. A new estimator is proposed to estimate the unknown censoring threshold. It is shown that the estimator is superconsistent and follows an exponential distribution in large samples. Due to the superconsistency, the asymptotic distribution of the maximum likelihood estimator of other parameters is not affected by the estimation uncertainty of the censoring threshold.

Examining post-wildfire reseeding on arid rangeland: A multivariate tobit modelling approach

Despite fire cycles of increasing severity and frequency in the arid western U.S., very little empirical analysis has examined the success of plant seeding on arid rangeland following fire. This manuscript uses a unique dataset to assess causal factors underlying the measured densities, several years after fires, of: (1) unwanted invasive grasses, (2) seeded grasses, and (3) sagebrush, on rangeland in a western U.S. state. To accommodate various characteristics of the data, we employ trivariate tobit maximum likelihood estimation. Results indicate that the success of reseeding efforts is sensitive to the timing of and techniques used in reseeding, as well as whether grazing is allowed on the land. Our findings have broad implications for emergency fire rehabilitation management and policy for rangelands in the western U.S., as well as arid and semiarid rangelands elsewhere.

The Tobit Model with a Non-zero Threshold

Contrary to accepted belief, the standard Tobit maximum likelihood estimator produces inconsistent parameter estimates, when the constant censoring threshold c is non-zero and unknown. Unfortunately the recording of a zero rather than the actual censoring threshold value is typical of economic data. Non-trivial minimum purchase prices for most goods, fixed cost for doing business or trading, social customs such as those involving charitable donations, and informal administrative recording practices represent common examples of non-zero censoring threshold where the threshold is not readily available to the econometrician. Monte Carlo results show that this bias can be extremely large in practice. A new estimator is proposed to estimate the unknown censoring threshold. It is shown that the estimator is superconsistent and follows an exponential distribution in large samples. Statistical tests for the censoring threshold are introduced. A simulation study shows that the finite sample size and power properties of the proposed tests are encouraging.

The Relationship Between the Liberal Ethos and Quality of Life

This research examines the positive influence of democracy and economic liberalism on citizens' quality of life (QOL). The statistical analysis relies on extreme-bounds analysis, the Tobit-maximum likelihood estimator, and robust two-stage least squares to test this hypothesis. The relationship between democracy and QOL is a parabolic inverted U-shaped curve, so that democracy first enhances QOL and over time it hampers it. On the other hand, QOL strengthens democracy. QOL suffers from a market economy in middle-income countries. Openness to trade enhances QOL everywhere but sub-Saharan Africa and the Middle East. A market economy consolidates democracy everywhere else but sub-Saharan Africa. Openness enhances democracy around the globe, except in Latin America and the Middle East. Economic development and QOL exhibit a reciprocal normal U-shaped curve, whereas democracy and economic development are linearly dependent. These contradictory results cast some doubt on the pursuit of both democracy and a liberal economy in fostering development. The current pursuit of the liberal ethos can be destructive, and it is time to modify our vision of the future.

Assessing the correlates of desired family size in Shaanxi, China.

This exploratory analysis of factors associated with Chinese women's fertility desires uses data on married women between the ages of 18 and 35 who live in Shaanxi Province, China. Analyses using an economic framework found that both rural and urban couples who intended to sign, or who had already signed, the one-child certificate reported wanting significantly fewer children. However, in rural areas (where 80 per cent of the provincial population lives), education level, living arrangements, participation in an arranged marriage, attitudes regarding the ideal age for marriage, and knowledge of the reasons for the government's fertility policies appear to play a relatively larger role in shaping fertility preferences.

Tobit maximum-likelihood estimation for stochastic time series affected by receiver saturation

The Tobit (Tobin Probit) model is adapted from the field of econometrics as a maximum likelihood estimator of PDF (probability density function) parameters for data that have been censored and truncated. A general expression for the Tobit estimator is presented. It is shown that when the (standard) maximum likelihood estimator is efficient for the random variable with unlimited dynamic range, the unbiased Tobit estimator is efficient for the censored/truncated random variable. The model is presented in detail for the Rayleigh PDF; its efficiency is confirmed, independent of the degree of truncation/censoring. Results from the application of Tobit estimation to simulated data with Rayleigh, log-normal, Rice-Nakagami, and Nagakami-M PDFs are shown to exhibit very low mean-squared error as well. The limitations and computational complexities of the Tobit estimator are discussed. >

Asymptotic misspecification biases for heckman's two step estimator

Asymptotic bias formulae are obtained for Heckman's two step estimator under misspecification of the single equation Tobit modelj and the two equation sample selection model. Asymptotic biases are also obtained for the ordinary least squares estimator based on uncensored observations only. Omitted variables, errors in variables, and heteroskedasticity are considered as sources of misspecification. The biases are illustrated by numerical examples, in which the Tobit maximum likelihood estimator is also included. Severe consequences for the two step estimator are indicated.

Tobit maximum likelihood estimation for probability densities stemming from the 2-dimensional random walk, and its application to ultrasonic imaging

Tobit maximum likelihood estimation for probability densities stemming from the 2-dimensional random walk, and its application to ultrasonic imaging