Random Effects Tobit Model Research Articles

Efficiency and productivity assessment of public hospitals in Greece during the crisis period 2009\u20132012

BackgroundThis study is an initial effort to examine the dynamics of efficiency and productivity in Greek public hospitals during the first phase of the crisis 2009–2012. Data were collected by the Ministry of Health after several quality controls ensuring comparability and validity of hospital inputs and outputs. Productivity is estimated using the Malmquist Indicator, decomposing the estimated values into efficiency and technological change.MethodsHospital efficiency and productivity growth are calculated by bootstrapping the non-parametric Malmquist analysis. The advantage of this method is the estimation efficiency and productivity through the corresponding confidence intervals. Additionally, a Random-effects Tobit model is explored to investigate the impact of contextual factors on the magnitude of efficiency.ResultsFindings reveal substantial variations in hospital productivity over the period from 2009 to 2012. The economic crisis of 2009 had a negative impact in productivity. The average Malmquist Productivity Indicator (MPI) score is 0.72 with unity signifying stable production. Approximately 91% of the hospitals score lower than unity. Substantial increase is observed between 2010 and 2011, as indicated by the average MPI score which fluctuates to 1.52. Moreover, technology change scored more than unity in more than 75% of hospitals. The last period (2011–2012) has shown stabilization in the expansionary process of productivity. The main factors contributing to overall productivity gains are increases in occupancy rates, type and size of the hospital.ConclusionsThis paper attempts to offer insights in efficiency and productivity growth for public hospitals in Greece. The results suggest that the average hospital experienced substantial productivity growth between 2009 and 2012 as indicated by variations in MPI. Almost all of the productivity increase was due to technology change which could be explained by the concurrent managerial and financing healthcare reforms. Hospitals operating under decreasing returns to scale could achieve higher efficiency rates by reducing their capacity. However, certain social objectives should also be considered. Emphasis perhaps should be placed in utilizing and advancing managerial and organizational reforms, so that the benefits of technological improvements will have a continuing positive impact in the future.

Analýza faktorů selekce a alokace české rozvojové pomoci s využitím panelových dat a metod Probit a Tobit

The aim of our paper is to identify factors that influence the territorial selection and allocation of development aid of the Czech Republic. We applied random-effects probit and tobit models in our regression analysis which revealed that flows of Czech aid to individual developing countries are determined by variety of factors. Czech interests and mutual relations were mostly identified as statistically significant determinants, namely export volumes, closer historical relations and geographical proximity. The presence of Czech embassy in a country was not confirmed as a significant factor. The reflection of recipients' needs in Czech aid selection and allocation is rather ambiguous. While Czech aid flows depend positively on total population and negatively on per capita income of recipient countries, they are positively influenced by the recipients' level of social development. Similarly, the Czech Republic tends to give (more) aid to more democratic and freer countries with lower institutional quality.

“Why some consumers don't care”: Heterogeneity in household responses to a food scandal

In the aftermath of food scandals, household perceptions about the health risks posed by failures in food safety play a central role in determining their mitigating behavior. A stream of literature has shown that factors including media coverage of a scandal, risk perceptions, trust in food safety information, and consumption habits matter. This paper deviates from the standard assumption of a homogeneous response to media information across all households exposed to a food scandal. Instead, we present an innovative multi-method approach to investigate the impacts of household heterogeneity in underlying psychological and behavioral, media usage patterns and consumption habits on poultry demand in the aftermath of the 2011 German dioxin scandal. The analysis employs weekly retail purchase and matching survey data for 6133 households covering pre and post scandal periods. The supplementary survey data elicits household respondent's risk perceptions and risk attitudes, product label and media information behavior. Initial factor and cluster analysis identify household segments based on psychographic and behavioral indicators. We then estimate a correlated random effect Tobit model to account for clustered household responses to quantify the influence of media effects distinguishing between short-term risk mitigation behavior and longer-term habit persistence. Our results confirm significant heterogeneity in household's media-induced risk-mitigation responses to the dioxin scandal across three clusters. However, we find that habit persistence in the form of consumption preferences for the affected products were able to largely compensate for demand-reducing media effects across household clusters. Considering heterogeneity in household's risk mitigation behaviors to food scandals holds implications for policy makers and food industry alike.

Share of irrigated land and farm size in rainwater harvesting irrigation in Ethiopia

Rainfall shortages constrain small-holders' agricultural production in developing countries and with ongoing climate change these shortages may increase in volume and frequency. Rainwater harvesting irrigation is an interesting technology that decreases this risk. Therefore, one would expect an increasing use of this technology in drought-prone areas, particularly for large and wealthy farms. This study investigated the relation between farm size and share of irrigated land among smallholders from two regions in Ethiopia. It also analyzed which factors explain the share of irrigated land using panel data collected in 2005 and 2010. A random effects tobit model was estimated for the share of irrigated land as a function of variables affecting returns, market prices, source of finance, and expectation formation. The findings show that the share of irrigated land declines with farm size. Moreover, the share of irrigated land depends on distance to market, ease of selling output, age, aridity, distance from natural water sources, credit access, and regional differences. These results question the relevance of water harvesting for farm enlargement. However, they also show that by safeguarding the availability of credit and improving local infrastructure farmers may extend the share of land irrigated by harvested water.

An analysis of country medal shares in individual sports at the Olympics

ABSTRACTResearch question: Several studies report modelling relating countries’ medal shares at the Olympics to population and per capita income (host status and political system are typically included as controls). This paper uses a similar model but disaggregates to the level of the individual sport to ask questions such as whether some sports have a less steep relationship with income levels than others and whether hosting effects are more pronounced in some sports than others. Research methods: Employing a random effects tobit model, data on medal shares are modelled across 15 sports at six editions of the Games (1992–2012). Marginal effects, calculated for the case of cycling, illustrate how far many poor countries are from reasonable expectation of achieving medals. Results and findings: Income is influential on outcomes in all sports, its effects most pronounced in sports with substantial requirements for specific capital equipment; the distribution of medals is less unequal in sports practised in multi-sports venues. Gains from hosting vary in magnitude, performance tending to be elevated most in sports with outcomes strongly influenced by judges. Implications: For poorer countries, the paper identifies a small group of sports on which it would be most realistic to focus resources. For Games organisers, who must decide which sports to include, it provides information relevant to the goal of spreading success more evenly across countries. For example, proposals to exclude wrestling are shown to have been potentially harmful to medal prospects of poorer countries.

Predictors of surgeons' efficiency in the operating rooms.

The sustainability of the Japanese healthcare system is questionable because of a huge fiscal debt. One of the solutions is to improve the efficiency of healthcare. The purpose of this study is to determine what factors are predictive of surgeons' efficiency scores. The authors collected data from all the surgical procedures performed at Teikyo University Hospital from April 1 through September 30 in 2013-2015. Output-oriented Charnes-Cooper-Rhodes model of data envelopment analysis was employed to calculate each surgeon's efficiency score. Seven independent variables that may predict their efficiency scores were selected: experience, medical school, surgical volume, gender, academic rank, surgical specialty, and the surgical fee schedule. Multiple regression analysis using random-effects Tobit model was used for our panel data. The data from total 8722 surgical cases were obtained in 18-month study period. The authors analyzed 134 surgeons. The only statistically significant coefficients were surgical specialty and surgical fee schedule (p = 0.000 and p = 0.016, respectively). Experience had some positive association with efficiency scores but did not reach statistical significance (p = 0.062). The other coefficients were not statistically significant. These results demonstrated that the surgical reimbursement system, not surgeons' personal characteristics, is a significant predictor of surgeons' efficiency.

Firm level R&D intensity: evidence from Indian drugs and pharmaceutical industry

This paper analyzes the R&D profile of Indian drug and pharmaceutical industry during the period 2000–2013, and the factors that influence a pharmaceutical firm’s decision to undertake R&D activities. The study period from 2000 to 2013 has been characterized by a rapid growth in industry’s R&D expenditures, as part of the strategic shift, induced by the Patents (Amendment) Act, 2005. Using the real financial data for the top 91 publicly listed Indian domestic pharmaceutical companies, the study provides new evidence on drivers of R&D intensity in Indian Drugs and Pharmaceutical industry. A panel data random effects Tobit model along with OLS model using firm fixed effects are applied to identify the factors affecting the RD past cash flow; export and import intensities of the firm tend to significantly impact the R&D intensity. While firm size exhibits a non-linear relationship, cash flow, past innovative output shows a positive and significant relationship with R&D intensity. Further, patent count and firm’s overseas presence, considered as additional important determinants of firm-level R&D intensity, influences R&D positively. Lastly, global orientation of Indian pharmaceutical firms has been found to impact R&D activities considerably.

Estimating overall exposure effects for the clustered and censored outcome using random effect Tobit regression models.

The random effect Tobit model is a regression model that accommodates both left- and/or right-censoring and within-cluster dependence of the outcome variable. Regression coefficients of random effect Tobit models have conditional interpretations on a constructed latent dependent variable and do not provide inference of overall exposure effects on the original outcome scale. Marginalized random effects model (MREM) permits likelihood-based estimation of marginal mean parameters for the clustered data. For random effect Tobit models, we extend the MREM to marginalize over both the random effects and the normal space and boundary components of the censored response to estimate overall exposure effects at population level. We also extend the 'Average Predicted Value' method to estimate the model-predicted marginal means for each person under different exposure status in a designated reference group by integrating over the random effects and then use the calculated difference to assess the overall exposure effect. The maximum likelihood estimation is proposed utilizing a quasi-Newton optimization algorithm with Gauss-Hermite quadrature to approximate the integration of the random effects. We use these methods to carefully analyze two real datasets. Copyright © 2016 John Wiley & Sons, Ltd.

Aporte del empleo fuera de finca a los ingresos de hogares indígenas y mestizos de la Amazonía ecuatoriana

<p>This study examines the process of income diversification among indigenous and mestizo households settled in one of the world’s biodiversity hotspots. The results of a random-effect tobit model show that agricultural wage work is the principal income source for homes with scarce or no land. Self-employment employs households with low endowments of education but high endowments of capital. Non-agricultural wage income absorbs educated individuals either indigenous or mestizo. <em></em></p>

Aporte del empleo fuera de finca a los ingresos de hogares indígenas y mestizos de la Amazonía ecuatoriana

<p>This study examines the process of income diversification among indigenous and mestizo households settled in one of the world’s biodiversity hotspots. The results of a random-effect tobit model show that agricultural wage work is the principal income source for homes with scarce or no land. Self-employment employs households with low endowments of education but high endowments of capital. Non-agricultural wage income absorbs educated individuals either indigenous or mestizo. <em></em></p>

Some like it organic, some like it purple and some like it ancient: Consumer preferences and WTP for value-added attributes in whole grain bread

The German bread market is considered one of the most developed and diverse bread markets worldwide. However, until so far no empirical evidence exists with respect to consumers liking and willingness to pay for different value-added attributes in whole grain bread. Thus, our study is the first one providing empirical evidence on how German consumers perceive different value-added attributes in whole grain bread, how much they are willing to pay for these attributes and to which extent liking scores and willingness to pay (WTP) estimates are influenced by extrinsic information. Our analysis is based on a combination of hedonic evaluations with experimental auctions under three different information scenarios. The attributes considered in our study are: (i) organic, (ii) functional, and (iii) ancient grain variety. The collected data are analyzed via cluster analysis and random effects Tobit models. The results indicate the following. First, significant heterogeneity exists across consumer clusters with respect to the responsiveness to extrinsic information. Second, results differ depending on the hedonic measure chosen, i.e. whether a taste or an overall liking score is employed. Third, the chosen functional bread, purple wheat bread would be accepted as long as taste expectations are met. Put differently, consumers would not comprise on taste for health. However, at the same time our results highlight that expecting that a bread has “natural” health-enhancing properties significantly increases the sensory evaluation and thus product liking. Consequently, bread with functional properties will be only successful on the market if consumers are satisfied with the taste experience, whereas extrinsic information might increase the perceived taste experience.

Has the global financial crisis had different effects on innovation performance in the agri-food sector by comparison to the rest of the economy?

BackgroundThe globalization and expansion of financial markets and the current economic crisis are changing the rules. Innovation has ceased to be part of the business strategy in many companies. However, in other companies innovation still plays a fundamental role in the improvement of performance and in maintaining competitive advantages in today's global markets. This is particularly the case in the agri-food industry; we will see here how innovations have become an important instrument for companies in this sector. Scope and approachThe main purpose is to determine the impact of this global financial crisis on the probability of firms introducing technological and non-technological innovations as well as on radical and incremental innovations and the use of innovation inputs. The analysis is based on panel data from the Technological Innovation Panel (PITEC) for Spanish firms between 2008 and 2012. We estimated random-effects Logit and Tobit models. Key findings and conclusionsThis manuscript explores that the economic crisis has had a significant and negative impact on firms' innovative performance and on the effort made by the firms in assigning resources for R&D. A crisis affects technological innovations to a greater extent, as well as small companies, those which carry out less internal R&D and cooperation efforts. However, innovating firms are proved to obtain better results both in economic and productive terms. Further to that, the agri-food sector innovative behavior has been less affected by the crisis than the rest of the economic sectors.

Asian emerging-market currencies in the international debt market (1994–2014)

This paper investigates the increasing presence of Asian emerging-market currencies in the international debt market over the last two decades. I use the “original sin” index developed by Eichengreen et al. (The pain of original sin. 〈http://elsa.berkeley.edu/~;;eichengr/research/ospainaug21-03.pdf〉 (August, 2003) to measure the use of an economy's home currency in international debt relative to the total international debt of its residents. The relative reliance on home currency debt is seen to have increased markedly in a number of economies. Using a random effects Tobit model, I examine factors underlying recent changes for a sample of nine Asian emerging market economies. The results suggest the importance of economic size, strength of institutions, and financial market development.

What Drives Security Issuance Decisions Of Firms Listed On The Johannesburg Stock Exchange: Market Timing Or Dynamic Trade-Off Theory Or Both?

This study used the random effects Tobit model to investigate the validity of the market timing, trade-off and pecking order hypotheses of capital structure in 143 non-financial firms listed on the Johannesburg Stock Exchange. The results show that leverage is positively correlated to the modified external finance weighted average market-to-book ratio (EFWAMB). Firm profitability and growth rate are negatively correlated to leverage whilst firm size and asset tangibility are positively correlated to leverage. The firms also have target leverage ratios towards which they actively adjust at an unbiased speed of 41.80% for the market-to-debt ratio and 52.82% for the book-to-debt ratio. EFWAMB has a negligible effect on the firms’ speeds of adjustment towards target leverage. The results are robust. These results reject the market timing hypothesis in support of the dynamic trade-off and pecking order hypotheses. They further confirm the fact that these two theories of capital structure are not mutual exclusive.

The Effects of Hartz IV Reform on Precautionary Savings

Using the reform on unemployment benefit II system in 2005 in Germany this paper verifies precautionary saving motives of German households. Based on first difference and random effects Tobit model using two years of GSOEP panel data, this paper found an increase in benefit amount by one unit (1,000 Euro) decreases household’s saving rates from 1.2 to 2 percent point depending on applied specifications. Though the magnitude of estimated results is quite moderate compared to the results from previous researches, through consistent findings which show negative relation between simulated benefit amounts and household saving rate, this paper concludes that there exists a moderate precautionary motive in savings for German households. It gives an important policy implication in a sense that unfavorable benefit cut makes individual take more financial responsibility at household level.

The Great Recession’s Impact on Credible Commitment

This study explores the Great Recession’s effect on the commitment by the city of Dallas, Texas, to its private partners in seventeen tax increment financing (TIF) districts. What effect did the recession have on private investment in public–private partnerships? Did the recession cause a loss of credibility in the city’s commitment, resulting in lower levels of private investment? Was there a lasting structural change in the determinants of private participation stemming from the recession? Results from a random effects Tobit model show that the city’s proposed budget for each TIF district was a significant determinant of the level of private investment. However, during the recession, the actual amount of investment by the city was essential to reassuring private investors of the city’s commitment.

Refined-scale panel data crash rate analysis using random-effects tobit model

Random effects tobit models are developed in predicting hourly crash rates with refined-scale panel data structure in both temporal and spatial domains. The proposed models address left-censoring effects of crash rates data while accounting for unobserved heterogeneity across groups and serial correlations within group in the meantime. The utilization of panel data in both refined temporal and spatial scales (hourly record and 1-mile roadway segments on average) exhibits strong potential on capturing the nature of time-varying and spatially varying contributing variables that is usually ignored in traditional aggregated traffic accident modeling. 1-year accident data and detailed traffic, environment, road geometry and surface condition data from a segment of I-25 in Colorado are adopted to demonstrate the proposed methodology. To better understand significantly different characteristics of crashes, two separate models, one for daytime and another for nighttime, have been developed. The results show major difference in contributing factors towards crash rate between daytime and nighttime models, implying considerable needs to investigate daytime and nighttime crashes separately using refined-scale data. After the models are developed, a comprehensive review of various contributing factors is made, followed by discussions on some interesting findings.

Examining the relationship between the physical availability of medical marijuana and marijuana use across fifty California cities

BackgroundThe purpose of the current study is to assess statistical associations between individual demographic and personality characteristics, the city-level physical availability of medical marijuana (as measured through densities per roadway mile of storefront dispensaries and delivery services), and the incidence and prevalence of marijuana use. MethodIndividual level data on marijuana use were collected during a telephone survey of 8853 respondents living in 50 mid-size cities in California. Data on medical marijuana dispensaries and delivery services were obtained via six different websites and official city lists. Three outcome variables pertaining to lifetime, past year use, and frequency of past year use were analyzed using random effects logistic models (for lifetime and past year use) and random effects tobit models (for frequency of past 365-day use). ResultsThe current study finds that the total physical availability of medical marijuana through dispensaries and delivery services per roadway mile at the city-level is positively related to current marijuana use and greater frequency of use, controlling for a variety of demographic and personality characteristics. As expected, current physical availability of medical marijuana was unrelated to lifetime use. ConclusionsRegulations on the number and densities of marijuana outlets may be a sufficient means to restrain overall levels of marijuana use within cities. However, alternative use of delivery services may also provide easy access to marijuana and mitigate these effects.

Bayesian Two-Part Tobit Models with Left-Censoring, Skewness, and Nonignorable Missingness

In a longitudinal HIV/AIDS study with response data, observations may be missing because of patient dropouts due to drug intolerance or other problems, resulting in nonignorable missing data. In addition to nonignorable missingness, there are also problems of skewness and left-censoring in the response variable because of a lower limit of detection (LOD). There has been relatively little work published simultaneously dealing with these features of longitudinal data. In particular, one of the features may sometimes be the existence of a larger proportion of left-censored data falling below LOD than expected under a usually assumed log-normal distribution. When this happens, an alternative model that can account for a high proportion of censored data should be considered. We present an extension of the random effects Tobit model that incorporates a mixture of true undetectable observations and the values from a skew-normal distribution for an outcome with left-censoring, skewness, and nonignorable missingness. A unifying modeling approach is used to assess the impact of left-censoring, skewness, nonignorable missingness and measurement error in covariates on a Bayesian inference. The proposed methods are illustrated using real data from an AIDS clinical study.

Rehospitalization risk of former voluntary and involuntary patients with schizophrenia.

The aim of the study was to examine the differences between former involuntary and voluntary patients with a schizophrenic disorder with regard to time to and frequency of rehospitalization. In this prospective observational study, 374 patients with a diagnosis of schizophrenia or schizoaffective disorder were included. At the time of inclusion, 290 (77.5 %) were hospitalized voluntarily and 84 (22.5 %) involuntarily. Follow-up assessments were conducted half-yearly over a 2-year period with measures of PANSS, GAF, sociodemographic data and cognitive functioning. These data served as covariates for adjustment in statistical models that included a Cox regression model, a random-effect logit model and a random-effect tobit model. After adjustment for other relevant covariates, the Cox regression showed that involuntary treatment is a significant risk factor of subsequent rehospitalization (HR = 1.53; CI = 1.06, 2.19; p = 0.02). The involuntary group had higher half-year incidence rates of rehospitalization, and in case of rehospitalization the duration of hospital stay was longer. Involuntary hospitalization seems to be associated with a higher risk of rehospitalization and longer subsequent hospital stays in patients with schizophrenia and schizoaffective disorders. Further studies are needed to examine in detail the processes and interventions that are suitable for interrupting circles of repeated hospitalizations, especially in former involuntary patients.