Search

The aim of this paper is to estimate households’ willingness to pay (WTP) for the development of community based tourism (CBT) around Alelo Bad hot spring water. To achieve the stated objective, relevant data was collected from a total of 157 sample respondents through questionnaires, interviews and field observation techniques. In this study, both descriptive and econometric models (Seemingly Unrelated Bivariate Probit and Probit models) were used to analyze the collected data. The descriptive statistics clearly shows that 66.24% of the respondents were willing to pay for the existence of the proposed project while 33.76% were not willing to pay. The seemingly unrelated bivariate probit model output revealed that the mean WTP of the sample household heads per year for the proposed project was birr 468.75 ($16.401) as well as the total sample respondents has estimated to pay birr 73,593.75 ($2,575.045) per year per household head. Gender, age, family size, off-farm income, education status, social responsibility and initial bid values were statistically significant variables which affect the WTP decision of household heads in the study area. The government should create a conducive environment for different stakeholders to actively engage in boosting the returns of the tourism sector and fulfillment of the proposed project in the study area. The tourism policy should be amended in the form of allocating higher proportion of the revenue obtained from the tourism sector to the local communities for the development of social infrastructure, improving the living standard of the local communities and sustaining resource conservation. Key words: Alelo bad hot spring water, WTP, seemingly unrelated bivariate probit and probit models, Ethiopia.

Purpose This study aims to combine two fraud-related streams of the literature on guanxi and overconfidence into an integrated framework, which is the fraud triangle, to interpret the mechanism of fraud commission and detection. Design/methodology/approach A bivariate probit model with Partial Observability (POBi Probit) is applied. Moreover, the POBi Probit model is adjusted to the Chinese context. The China-specific POBi Probit model is constructed using data of Chinese A-share listed companies from 2008 to 2014, with a total of 15,109 firm-year observations. Findings Overconfidence induces fraud commission and worsens fraud detection; overconfidence mediates the relationship between fraud and guanxi; the “white side” of guanxi comes from alumni networks, while the “dark side” is derived from relatives-based networks; overconfidence induces fraud commission in accounting and disclosure and benefits the detection of disclosure frauds. Guanxi suppresses fraud commission in management and disclosure, however, it worsens fraud detection given fraud in management and disclosure; overconfidence induces fraud commission in both state-owned enterprises (SOE) and non-SOEs, and benefits fraud detection in SOEs. Guanxi suppresses fraud commission and worsens fraud detection in SOEs and city-owned firms. Research limitations/implications There are two drawbacks of the partial observable bivariate probit (POBi-Probit) method that must be mentioned here. On one hand, the ex ante variable selection is one of the most difficult parts of applying the POBi-Probit model and different variables are included in different studies. On the other hand, the POBi-Probit model might not converge if too many variables are included. Thus, many widely accepted factors can be included in the model. Thus, this study initially sets the POBi-Probit model based mainly on Khanna et al. (2015) and then adjusts the model for the Chinese context (e. g. considering government ownership) according to Yiu et al. (2018) and Zhang (2018) and the local study of Meng et al. (2019). Considering the observability of fraud, on one hand, the observability of fraud commission is a widely accepted limitation, especially when accounting opacity comes across with regulatory efficiency (Yiu et al. (2018). On the other hand, the observability of relationships is another obstacle to this study. Future studies can go further by revealing the presently unobservable relationships using Big Data technology. Originality/value This paper theoretically and practically contributes to the literature on both corporate fraud and corporate governance. Theoretically, by introducing integrated principal-agent resource-reliance theory (IPRT) and upper echelon theory (UET), this paper broadens the framework of fraud triangle theory (FTT) and testifies the availability of the broaden FTT in the transitional and emerging-market context of China. Practically, this paper provides evidence that guanxi and overconfidence are two of the factors affecting corporate fraud. Thus, this paper provides a governance approach opposing corporate fraud in China, which may help the other emerging economies in transition.

The increased population aging has resulted in a growing need for longitudinal studies about the quality of life among older people. Nevertheless, the results of these investigations could be biased because more disadvantaged people leave the original sample. The purpose of this study is to examine how the selective attrition observed in a panel survey affect multivariate models of subjective well-being (SWB). The question is if we could do reliable longitudinal investigations concerning the predictors of SWB in old age. This paper examines attrition in a panel of older people in Chile. Attrition was evaluated in the variables that affect elderly SWB. Probit models were fitted to compare dropouts with nondropouts. Then, multivariate probit models were estimated on satisfaction and depressive symptoms, comparing dropouts and nondropouts. Finally, we compared weighted and unweighted multivariate probit models on SWB. The attrition rate in 2 years was 38.8%, including deaths and 32.9%, excluding them. Survey dropouts had lower satisfaction but not higher depressive symptoms. Among SWB predictors, people without a partner and with lower self-efficacy abandoned more the study. When applying the Becketti, Gould, Lillard, and Welch test, the probit coefficients of the predictor variables on SWB outcome variables were similar for dropouts and nondropouts. Finally, the comparison of multivariate models on SWB with weighting methods did not find substantial differences in the explanatory coefficients. Although some predictors of attrition were associated with SWB, attrition did not produce biased estimates in multivariate models of life satisfaction life or depressive symptoms in old age.

We illustrate the estimation and identification of multi-step sequential probit models with and without stepwise sample separation information. The likelihood functions are explicitly derived to ease experimentation with such models. We used data on health, activity limitations, demographic traits and work from the Survey of Income and Program Participation (SIPP) and exactly matched them with Social Security administrative records to showcase our theoretical points. Using a Monte Carlo simulation technique, our results suggest that the correlations in errors across equations may arise due to unobserved individual heterogeneity. Using a novel marginal likelihood approach, we also estimated the above sequential probit model without the sample separation information for the purpose of direct comparison. In terms of both in-sample and jackknife-type out-of-sample predictive analysis, the value of modelling the underlying sequential structure of the determination process in generating correct membership probabilities of belonging to a particular group is confirmed. JEL: C31, C34, C 35, I12, I18

This study was conducted to understand fishers’ climate change adaptation decisions in order to move climate informed policy for artisanal fisheries in developing economies forward. Data were collected from a random sample of 220 fishers in Mangochi District in Malawi. A binary probit model and a multivariate probit model were used to assess factors that affect fishers’ decision to adapt to climate change and their choice of adaptation strategies respectively. The study found that factors such as sex, education level, fishing experience, household size, fishing income, perception of catch rate trend, social capital and access to extension service corresponded in an increase in the probability of fishers adapting to impacts of climate change by increasing fishing effort, engaging in migratory fishing, investing in improved gear and livelihood diversification. The study recommends strengthening the education system in riparian communities to equip fishers with skills employable outside fishing and at the same time relive pressure off aquatic ecosystems.

We propose a simple procedure based on an existing “debiased” l1-regularized method for inference of the average partial effects (APEs) in approximately sparse probit and fractional probit models w...

This paper investigated the effect of maternal employment on childhood overweight in the United States using a sample of school-age children. We used data from the spring 2013 cohort of the Early Childhood Longitudinal Study, Kindergarten Class of 2010–2011 (ECLS-K: 2011). We estimated a recursive bivariate probit model using exogenous variation in the youngest sibling’s eligibility for kindergarten as an instrument for maternal employment. As a robustness check, instrumental variable regression using 2SLS estimation technique and IV probit regression were also used. The findings suggest that the effect of maternal employment on child overweight is not significant. The results showed that rather than maternal employment, socioeconomic status, schooling environment, life style behaviors including physical exercise and sedentary behavior were significant factors contributing to child overweight. More specifically, higher socioeconomic status and doing physical exercise more frequently were negatively related to child overweight, while sedentary behavior and free/reduced price school meals were positively related to child overweight.

In the early days of the COVID-19 pandemic, an area could only report its first positive cases if the infection had spread into the area and if the infection was subsequently detected. A standard probit model does not correctly account for these two distinct latent processes but assumes there is a single underlying process for an observed outcome. A similar issue confounds research on other binary outcomes such as corporate wrongdoing, acquisitions, hiring, and new venture establishments. The bivariate probit model enables empirical analysis of two distinct latent binary processes that jointly produce a single observed binary outcome. One common challenge of applying the bivariate probit model is that it may not converge, especially with smaller sample sizes. We use Monte Carlo simulations to give guidance on the sample characteristics needed to accurately estimate a bivariate probit model. We then demonstrate the use of the bivariate probit to model infection and detection as two distinct processes behind county-level COVID-19 reports in the United States. Finally, we discuss several organizational outcomes that strategy scholars might analyze using the bivariate probit model in future research.

This study examines smallholder farmers’ adoption of both a full set of and multiple bundles of integrated soil fertility management technologies, and estimates the determinants of and assesses the relationship among adoption practices using the logistic model and multivariate probit model respectively. A cross-sectional survey was used to collect data from 300 smallholder farmers who benefitted from a sustainable food security and environmental health project in three districts in Ghana. Four ISFM technologies (zero or minimal tillage, inorganic fertilizer, leguminous crop, and crop rotation) serve as outcome variables. The result revealed that only 26.7% of the respondents adopted the full set of the ISFM technologies. Agroecological zone, a spatial variable has been found to significantly influence smallholder farmers adoption of the full ISFM technologies. One or more of the predictor variables, purpose of farming, land ownership, distance from house to the nearest input shop, access credit and agroecological zone, have been found to significantly influence the adoption of the multiple ISFM technologies. However, the computed correlation coefficients of the independent determinants show inconsistent significant values. The implication of this finding is that the adoption of multiple ISFM technologies cannot be estimated utilizing common determinants. Therefore, extension service in the region should focus on crucial factors that influence adoption of specific multiple ISFM technologies to maximize adoption options., Adoption; Integrated soil fertility management; Technology; Multivariate; probit model; Land degradation

Keçi sütünün günlük gıda tüketimindeki önemi her geçengün artmaktadır. Bu çalışma keçi sütü tüketimine etki eden faktörleribelirlemeyi amaçlamaktadır. Araştırmanın materyalini Adana ve Mersin illerindeuygulanan yüz yüze tüketici anketleri oluşturmuştur. Anketin örneklembüyüklüğü, sınırsız popülasyon koşulları altında 518 tüketici olarak (kolaydaörnekleme yöntemi kullanılarak) belirlenmiştir. Bu bağlamda, keçi sütü tüketimive satın alma niyetlerini test etmek için çok değişkenli bir probit modelitasarlanmıştır. Çalışmanın sonuçları, satınalma yeri, şişe tipi, koku, marka,peynir tüketimi ve memleket faktörlerinin keçi sütü tüketimi ve satın almafaaliyetleri ile ilişkili olduğunu göstermektedir. Bu sonuçlar, tüketicininkeçi sütündeki tutumunu anlamak ve gelecekteki ticari hedefleri ve üretimstratejilerini belirlemek için yararlı olabililecektir., Goat milk hasincreasing importance in daily food consumption of individuals. This study aimsto determine the factors that have influence on goat milk consumption. Theresearch was conducted based on a face to face consumer survey which wasapplied in the two cities of the south-east part of Turkey, Adana and Mersin.The sample size of the survey was determined as 518 consumers depend onconvenience sampling in case of unlimited population size. In this regard, amultivariate probit model was designed to test the intentions for goat milkconsumption and purchase. The result of the study shows that place of purchase,bottle type, odour, brand, cheese consumption and homeland are the relatedfactors with goat milk consumption and purchase activities. These results couldbe useful for understanding consumer attitude towards goat milk and to identifycommercial targets and production strategies in future.

Photovoltaic (PV) units and electric vehicles (EVs) are two household goods that are the focus of much research, and many policy initiatives attempting to promote a more sustainable, low-carbon energy system. Despite both academic and practical interest in household adoption of PV units and EVs, potential linkages in these household decisions have only just begun to be explored. This paper presents q-complementarity between the goods as one possible form of a linkage between PV and EV purchases that is based on economic utility theory. We posit the goods could be q-complements due to a PV-owning household's ability to offset and shift their electricity load from EV charging to increase the self-consumption of `home-made' electricity, thereby increasing the positive feelings of environmental efficacy and monetary returns from the PV unit. We use data from 2,541 internet surveys of Austrian residential electricity customers collected in 2018 to explore these hypotheses. Probit models of household EV and PV adoption choice are estimated, including a recursive bivariate probit model of households who plan to purchase an EV in the future, with PV ownership endogenously determined. Controlling for household income, characteristics, environmental attitudes, and neighborhood characteristics, we find that EV and PV adoption are positively correlated, and that current PV unit owners are 18\% more likely to plan an EV purchase in the next 5 years compared to non-PV owners. We interpret these results as evidence in support of our hypothesis of q-complementarity between PV units and EVs, and note the potential for added benefits from incentive policies promoting adoption of one good or the other that this linkage suggests.

Probit and logit models typically require a normalization on the error variance for model identification. This paper shows that in the context of sample mean probability decompositions, error variance normalizations preclude estimation of the effects of group differences in the latent variable model parameters. An empirical example is provided for a model in which the error variances are identified. This identification allows the effects of group differences in the latent variable model parameters to be estimated.

This paper examines the notion of “identification by functional form” for two equation triangular systems for binary endogenous variables by providing a bridge between the literature on the recursive bivariate probit model and that on partial identification. We evaluate the impact of functional form on the performance of (quasi) maximum likelihood estimators, and investigate the practical importance of available instruments in both cases of correct and incorrect distributional specification. Finally, we calculate average treatment effect bounds and demonstrate how properties of the estimators are explicable via a link between the notion of pseudo-true parameters and the concepts of partial identification.

The attraction eect and other decoy eects are often understood as anomalies and modeled as departures from rational inference. We show how these decoy eects may arise from simple Bayesian updating. Our new model, the Bayesian probit, has the same parameters as the standard multinomial probit model: each choice alternative is associated with a Gaussian random variable. We show how, unlike any random utility model, the Bayesian probit can jointly accommodate similarity eects, the attraction eect and the compromise eect. We also provide a new denition of revealed similarity based only on the choice rule and show that in the Bayesian probit (i) signal averages capture revealed preference; (ii) signal precision captures the decision maker’s familiarity with the options; and (iii) signal correlation captures our new denition of revealed similarity. This link of parameters to observable choice

The purpose of my paper is to describe and explain the probability of staying in temporary work for young people (age 16-27) in Sweden between 1992 and 2011 and its relation to socioeconomic outcomes (low socioeconomic classification and wage). I used panel data from the Swedish Labour Force Survey (LFS) and the longitudinal integration database for health insurance and labour market studies (LISA). To analyse the data, I used a dynamic probit model, unconditional quantile regression, and a pooled bivariate probit model. My results suggest that young people who have a low education have lower probabilities of receiving temporary employment in younger cohorts. However, younger cohorts with a lower education have a substantive wage disadvantage, specifically in younger cohorts compared to older cohorts. Low-educated cohorts also have a higher probability of obtaining low socioeconomic classification (SEC) employment, which is conditional on holding temporary employment in older cohorts compared to other educational groupings.

Risk management is an essential way for farmers to reduce uncertainty. In this research, a stratified random sampling method was used to survey 350 maize farmers in four different agro-ecological regions in Bangladesh. Using the multivariate probit model, this study explored the possible correlation between farmers&rsquo, perceptions of catastrophic risks and their attitudes towards risk sources&mdash, as well as the possible correlation between contract farming, diversification and precautionary savings as risk management strategies. The results confirm the relevance of risk management adoption decisions and reveal that the use of one risk management tool may simultaneously influence the use of another risk management tool. In addition, the research results also show that age, education level, extension experience, monthly household income, farming areas, land ownership and risk aversion nature are the most important factors that affect the adoption of risk management strategies. The research results provide further explanation and information and provide a platform for decision-makers to predict appropriate risk management strategies.

Identifying the determinants of firms’ investment in knowledge, this study first explores the heterogeneous impacts of research and development (R&D) on product, process, organization, and marketing innovation. Second, it examines if there exists a complementary (substitute) relation in terms of firms’ preference between four types of innovation. Studying 1500 firms of seven developing economies of the Association of Southeast Asian Nations (ASEAN), we applied the least absolute shrinkage and selection operator (LASSO), a machine learning-based regression, to identify key predictors likely to influence firms’ R&D propensity and intensity. Estimating the knowledge function, we found—in line with LASSO—that medium-sized firms, human capital (training) and credit facilities favorably affect firms’ decision to invest in R&D. Contrarily, the impact is adverse if the first or main product generates firms’ large share of revenue, a unique finding not captured by previous studies. The marginal effects of four univariate probit models indicate that firms’ investment in R&D translates into innovation. However, the application of the Geweke−Hajivassiliour−Keane (GHK)-simulator based multivariate probit, which considers simultaneity of firms’ innovation decisions that univariate probit ignores, suggests that the relationship between different types of innovation is complementary. Firms’ strategy to adopt a particular type of innovation is influenced by other types. This led to the estimation of R&D’s impact on technological and nontechnological innovation, which shows that while firms innovate both types, there is a skewed link between nontechnological innovation and the services sector.

This study examines the factors affecting obesity prevalence among adult individuals in Turkey using data obtained from the National Health Survey of the Turkish Statistical Institute (TSI). Nowadays obesity is one of the world’s major health problems. Although the proportion of young people remains very high in Turkey, the prevalence of obesity is increasing daily. In this study, we used the National Health Survey data collected by the TSI in 2012. The research was carried out on 14,400 households in 12 regions of Turkey. The study covered socio-demographic characteristics of families and household heads, but included only observations made by household heads. We tested a bivariate probit model with sample selection, which was compatible with the data-generating process to exclude the inherent selection problem. We then applied a simple binary probit model to assess the likelihood of being obese among those who reported their body measures (height and weight). The results indicated that living in a city, getting married, being female, being middle-aged, being depressed and having lower education levels increased the probability of obesity prevalence among Turkish subjects, while less obesity prevalence was associated with being male, being well educated, being a regular walker, being a smoker and living in a rural area. When combating obesity in Turkey, social risk groups that are more likely to be obese should be identified and awareness training should be carried out for each group with suitable objectives and programs. The aim of such programs should be to encourage adequate and balanced nutrition and regular physical activity and to teach individuals about the adverse effects of obesity on health (cardiovascular disease, diabetes, some types of cancer, hypertension, etc.).

This note shows that, if a Bivariate Probit (BP) model is estimated on data arising from a Recursive Bivariate Probit (RBP) process, the resulting BP correlation parameter is a weighted average of the RBP correlation parameter and the parameter associated to the endogenous binary variable. Two corollaries follow this proposition: i) the interpretation of the correlation parameter in the RBP is not the same as in the BP —i.e. the RBP correlation parameter does not necessarily reflect the correlation between the binary variables under study; and ii) a zero correlation parameter in a BP model, usually interpreted as evidence of independence between the binary variables under study, may actually mask the presence of an RBP process.

This study investigates the key factors that elicit financial reporting fraud among companies in Malaysia. Using enforcement action releases issued by the Security Commission of Malaysia (SC) and Bursa Malaysia, we identify a sample of 76 firms that had committed financial reporting fraud during the period of 1996–2016. We use the fraud triangle framework and the Malaysian International Standards on Auditing 240 to identify the factors. Since the simple probit model fails to address the identification problem (partial observability), we estimate our results using a bivariate probit model. The new model estimates the effects of pressure, opportunity, and rationalization on the probability of fraud likelihood by disentangling the detection probability of fraud. Among several proxies used for pressure, our results suggest that aggressive tax reporting and financial difficulties increase the likelihood of fraud commission. In regard to opportunity, we find that dedicated institutional investors, independence of the board, effective audit committee, and the presence of a female on the board provide active monitoring and oversight in reducing fraud occurrence. Results for rationalization suggest that prior violations and frequent changes of external auditors increase the chances of fraud occurrence. This research offers possible insights to auditors, managers, and regulators to prevent, detect, and react to fraud. Specifically, it highlights the specific factors that may exacerbate the fraudulent intentions of firms.

Weak identification is a well known topic for linear multiple equation models. However, little is known whether this problem also matters for probit models with endogenous covariates. Therefore, the behaviour of the usual z-statistic in case of weak identification is analysed in a simulation study. It shows large size distortions. However, a new puzzle is found: The magnitude of the size distortion depends heavily on the parameter value that is tested. Alternatively the LR-statistic was calculated which is known to be more robust against weak identification in case of linear multiple equation models. The same seems to be true for probit equations. No size distortions are found. However, medium undersizing is observed.

Combining the multivariate probit models with the multivariate partially linear single-index models, we propose new semiparametric latent variable models for multivariate ordinal response data. Bas...

This study uses highway accident data collected in the State of Washington, between 2011 and 2013, to study the factors that affect accident injury-severities. To account for the fixed thresholds limitation of the traditional ordered probability models – which typically leads to incorrect estimation of outcome probabilities for the intermediate categories – and for the possibility of unobserved factors systematically varying across the observations, a random thresholds hierarchical ordered probit model with random parameters is estimated. This approach simultaneously allows the explanatory parameters to vary across roadway segments, and the thresholds to vary both as a function of explanatory parameters and across the observations, thus accounting for unobserved and threshold heterogeneity, respectively. Using goodness-of-fit measures, likelihood ratio tests and forecasting accuracy measures, the model estimation results are compared with the hierarchical and fixed thresholds ordered probit model counterparts, with fixed and random parameters. The comparative assessment among the ordered probit modeling approaches reveals the relative benefits and the overall statistical superiority of the random thresholds random parameters hierarchical ordered probit model.

This paper provides identification results for a class of models specified by a triangular system of two equations with binary endogenous variables. The joint distribution of the latent error terms is specified through a parametric copula structure that satisfies a particular dependence ordering, while the marginal distributions are allowed to be arbitrary but known. This class of models is broad and includes bivariate probit models as a special case. The paper demonstrates that having an exclusion restriction is necessary and sufficient for global identification in a model without common exogenous covariates, where the excluded variable is allowed to be binary. Having an exclusion restriction is sufficient in models with common exogenous covariates that are present in both equations. The paper then extends the identification analyses to a model where the marginal distributions of the error terms are unknown.

Arts audiences in Finland A survey conducted in 2013 by the Finnish Cultural Foundation studied Finnish views on and thoughts about culture and its consumption. About 30 % in the sample had not visited any cultural attractions or events. The main cultural activities visited or attended were theatre, museum, art exhibitions, pop music concerts and movies at a cinema. In addition to these consumers seem to favour classical music. Opera, folk music and dance events had the lowest attendance figure. Our study contributes to the literature by identifying the determinants of participation level and of each category in arts consumption in Finland. First the overall participation level is studied by employing multiple choice and ordered logit and probit models as well as a bivariate probit model. We show how different socio-economic variables explain cultural consumption in Finland. Some insights into the distribution of state subsidises is discussed. We examine to what extent standard socio-economic variables influence attendance at different cultural events. How these variables are related to the number of cultural events participated and what are the main differences between univore and omnivore consumers? A standard economic theory assumes that the marginal utility of any consumption diminishes. Is this valid in the case of cultural events consumption? Does the assumption reflect the idea that even if the consumers’ incomes increase, still they do not participate all cultural events? Incomes, education and learning experiences accumulated and associated with age are important factors in the demand for arts, however, there are exceptions in Finland. The demand for folk music cannot be explained by differences in household’s incomes. Folk music category is more separated and not very popular among Finnish consumers. Dance events and folk music seem to have the smallest distance and all other categories are more far away Keywords: Finland, cultural consumption, participation, logit, probit, art audiences

In this paper, a large set of macroeconomic and financial predictors is used to forecast U.S. recession periods. We propose a sparse Bayesian variable selection in probit model for predicting U.S. recessions. The correlation prior is assigned for the binary vector to distinguish models with the same size, and the sparse prior is specified for the coefficient parameters for the purpose of predicting accurately using fewer parameters. In terms of the quadratic probability score and the log probability score, we demonstrate that the proposed method performs better than other three methods.

Selecting a small number of relevant genes for cancer classification has received a great deal of attention in microarray data analysis. In this paper, a sparse Bayesian multinomial probit regression model with correlation prior is proposed. Based on simulated and real datasets, we demonstrate that the proposed method performs better than five other competing methods in terms of variable selection and classification.

OBJECTIVES Probit has not been applied to ancestry estimation in forensic anthropology. The goals of this study were to: (1) evaluate the performance of probit analysis as a classification tool for ancestry estimation using ordinal data and (2) expand our current understanding of human cranial variation for an understudied population. METHODS Multivariate probit models were used to classify the ancestral affiliation of Filipino crania using morphoscopic traits. Ancestral reference populations represented Africa, Asia, and Europe in a three-group model, with the addition of Hispanics in a four-group model. Posterior probabilities across these groups were interpreted as admixture proportions of an individual. Model performance was also evaluated for individuals with missing data. RESULTS The overall correct classification rates for the three-group and four-group models were 72.1% and 68.6%, respectively. Filipinos classified as Asian 52.9% of the time using three ancestral reference groups and 48.6% using four groups. A large portion of Filipinos also classified as African. There were no significant differences in classification trends or accuracy rates between complete crania and crania with at least one missing variable. CONCLUSIONS Multivariate probit models using morphoscopic traits perform well when populations are represented in both training and test samples. Probit can also accommodate individuals with missing data. Classifying Filipinos showed only moderate success. Filipinos are more phenotypically similar to Africans than the other Asian samples used here, but still affiliate most closely as Asian. Ancestry methods would benefit from including Filipinos as a reference sample given the additional variation they provide to the continental category of Asian.

Objective Side crashes between vehicles which usually lead to high casualties and property loss, rank first among total crashes in China. This paper aims to identify the factors associated with injury severity of side crashes at intersections and to provide suggestions for developing countermeasures to mitigate the levels of injuries. Method In order to investigate the role of striking and struck vehicles in side crashes simultaneously, bivariate probit model was proposed and Bayesian approach was employed to evaluate the model, compared to the corresponding univariate probit model. Data Crash data from Beijing, China for the period 2009–2012 were used to carry out the statistical analysis. Based on the investigation with vehicles and data analysis on events, 130 intersection side crash cases were selected to form a specific dataset. Then, the influence of human, vehicles, roadway and environmental variables on crash severity was examined by means of bivariate probit regression within Bayesian framework. Results The effects of the factors on striking vehicle drivers and struck vehicle drivers were considered separately and simultaneously to find more targeted conclusions. The statistical analysis revealed vehicle type, lane number, no non-motorized lane and speeding have the corresponding influence on the injury severity of striking vehicles, while time of day and vehicle type of struck vehicles increased the likelihood of being injured. Conclusions From the results it can be concluded that there indeed exists correlation between striking and struck vehicles in side crashes, although the correlation is not so strong. Importantly, Bayesian bivariate probit model can address the role of striking and struck vehicles in side crashes simultaneously and can accommodate the correlation clearly, which extends the range of univariate probit analysis. The general and empirical countermeasures are presented to improve the safety at intersections.

Estimation of marginal or partial effects of covariates x on various conditional parameters or functionals is often a main target of applied microeconometric analysis. In the specific context of probit models, estimation of partial effects involving outcome probabilities will often be of interest. Such estimation is straightforward in univariate models, and results covering the case of quadrant probability marginal effects in bivariate probit models for jointly distributed outcomes y have previously been described in the literature. This paper's goals are to extend Greene's results to encompass the general M≥2 multivariate probit (MVP) context for arbitrary orthant probabilities and to extended these results to models that condition on subvectors of y and to multivariate ordered probit data structures. It is suggested that such partial effects are broadly useful in situations wherein multivariate outcomes are of concern.

Inferring concerted changes among biological traits along an evolutionary history remains an important yet challenging problem. Besides adjusting for spurious correlation induced from the shared history, the task also requires sufficient flexibility and computational efficiency to incorporate multiple continuous and discrete traits as data size increases. To accomplish this, we jointly model mixed-type traits by assuming latent parameters for binary outcome dimensions at the tips of an unknown tree informed by molecular sequences. This gives rise to a phylogenetic multivariate probit model. With large sample sizes, posterior computation under this model is problematic, as it requires repeated sampling from a high-dimensional truncated normal distribution. Current best practices employ multiple-try rejection sampling that suffers from slow-mixing and a computational cost that scales quadratically in sample size. We develop a new inference approach that exploits 1) the bouncy particle sampler (BPS) based on piecewise deterministic Markov processes to simultaneously sample all truncated normal dimensions, and 2) novel dynamic programming that reduces the cost of likelihood and gradient evaluations for BPS to linear in sample size. In an application with 535 HIV viruses and 24 traits that necessitates sampling from a 12,840-dimensional truncated normal, our method makes it possible to estimate the across-trait correlation and detect factors that affect the pathogen's capacity to cause disease. This inference framework is also applicable to a broader class of covariance structures beyond comparative biology., Comment: 24 pages, 6 figures, 2 tables. Version accepted by Annals of Applied Statistics

The purpose of this study is to introduce a more flexible joint distribution for a probit model with more than two equations, or a so-called SUR probit model. The main idea of the suggested method ...

We study the directional predictability of monthly excess stock market returns in the U.S. and ten other markets using univariate and bivariate binary response models. We introduce a new bivariate (two-equation) probit model that allows us to examine the benefits of predicting the signs of returns jointly, focusing on the predictive power originating from the U.S. to foreign markets. Our in-sample and out-of-sample forecasting results indicate superior predictive performance of the new model over competing univariate binary response models, and conventional predictive regressions, by statistical measures and market timing performance. This highlights the importance of predictive information from the U.S. to the other markets providing also practical improvement in investors' market timing decisions.

The study investigated what drives farmers’ decision not to utilise their land for cultivation. The study utilised data from Statistical Office of Kosovo (SOK) with sample size of 4187 agricultural households. To achieve the objective, distance and transaction costs were examined, controlling for socioeconomic characteristics. The dichotomous dependent variable, dummy=1 if land fallow otherwise=0 was regressed over a set of explanatory variables. The model was estimated using both probit regression and linear probability model (LPM). Diagnostics test were performed after estimation. From the results, probit model passed almost all the tests. The results from both probit and LPM have low R2= 0.093. However, most of the explanatory variables showed a consistent sign and significance with useful insights into the determinants of land fallow decisions. The log likelihood ratio (LR) significance test from probit model confirmed the variables of interest are statistically jointly significant at 99% confidence level (p-value

Integrated models for multiple decision variables, not necessarily from the same family, are becoming possible thanks to the advances in econometrics and in the estimation techniques. Recently, probit type models have been proposed to model joint decisions for the flexibility offered by the multivariate normal to capture correlations across the different dependent variables. Ordered probit models are in general preferred to unordered probit for the saving in computational costs deriving from the closed mathematical form of the choice probabilities. In this study, we compare results obtained from unordered probit models estimated with simulation and numerical computation to those obtained from ordered discrete–continuous probit. The analysis is performed on household decisions concerning vehicle holding and mileage travelled and using data extracted from the 2009 National Household Travel Survey. Estimation results show that discrete–continuous unordered probit are superior to ordered structures in terms of goodness of fit, but produce comparable results when applied to predict behavioral changes. Model applications for policy analysis also reveal that income and density only affects marginally vehicle holding decisions and annual miles driven, while driving cost has a more significant effect on annual household mileage.

The study used contingent valuation to solicit monetary values from researchers and farmers on how much they were willing to sell and buy agricultural innovations from research respectively. A probit model was then employed to identify the determinants of researchers’ willingness to sell innovations from research. Furthermore, a multivariate (MV) probit model was estimated to explain key determinants of farmers’ willingness to pay (WTP) for such innovations (technologies). Multi-stage sampling methods were used to obtain data from 360 farmers and 51 research scientists for the study. Though majority of farmers were willing to pay for agricultural innovations, the amounts they were prepared to pay (average of GH₵6.00), were far less than what the researchers wanted them to pay (average of GH₵50.00). The probability of a researcher accepting payment for innovations from research was high for the following categories of researchers: younger researchers; researchers who were members of professional bodies; and researchers with a high number of publications. The following categories of farmers also had a higher probability of paying for research output: younger farmers; farmers with high level of formal education; native farmers; farmers who had contacts with extension staff; and farmers with high income from their previous farming and non-farming activities. Considering the wide disparity between researchers’ WTA payment for innovations and farmers’ WTP, commercialization of research is possible but cannot be run on full cost-recovery. Government should therefore set up a statutory fund dedicated to agricultural research as a way of subsidizing agricultural innovations. Key words: Agricultural innovations, contingent valuation, multivariate probit model, willingness to pay, willingness to accept, probit model.

The purpose of this letter is to show the equivalence of three latent class models; the switching regression model with endogenous switching and a latent outcome (the binary Roy model), the probit model with a systematically misclassified dependent variable, and a trivariate probit model with partial observability. The probit model with measurement error is an enhanced version of existing models which allows for the potential correlation between error terms. Establishing this connection, we hope, will help a researcher working on one of these classes of estimators to benefit from the literature and software related to other families.

I present the bireprob command, which fits a bivariate random-effects probit model. bireprob enables a researcher to estimate two (seemingly unrelated) nonlinear processes and to control for interrelations between their unobservables. The estimator uses quasirandom numbers (Halton draws) and maximum simulated likelihood to estimate the correlation between the error terms of both processes. The application of bireprob is illustrated in two examples: the first one uses artificial data, and the second one uses real data. Finally, in a simulation, the performance of the estimator is tested and compared with the official Stata command xtprobit.

Improved drinking-water sources need not be microbiologically safe. Hence, households usually boil their water prior to drinking. However, this practice can potentially harm health when households rely on unsafe cooking fuels. In Indonesia, little is known about the association of use of unsafe fuels with boiling practice. Hence, an analysis was carried out to elicit information regarding boiling practice using unsafe fuels. Such information would be useful in determining appropriate household water treatments. Data from the 2012 Indonesia Demographic and Health Survey (IDHS) were analysed to examine the relationship between the use of unsafe cooking fuel and choosing boiling as household water treatment. Bivariate and multivariate probit regression models (PRM) were fitted and compared using average marginal effects (AME) and its respective 95 per cent confidence interval (95% CI) as measures of association. The results suggest that using kerosene as cooking fuel is positively significantly associated with higher probability of practicing boiling (p = 0.006; AME: 0.019; 95% CI: 0.0056, 0.0333). This is also true for use of solid fuel (p< 0.001; AME: 0.3115; 95% CI: 0.3026, 0.3203). These association holds, albeit attenuated (Kerosene, p< 0.001; AME: 0.02706; 95% CI: 0.0186, 0.0355; Solid fuel, p< 0.001; AME: 0.0373; 95% CI: 0.02839, 0.0463), after the control variables are included. The authors suggest that stakeholders should promote the use of other household water treatment technologies to reduce the boiling practice using unsafe cooking fuels as to minimize the risk of smoke related infections. Moreover, universal access and equity to safe drinking water and sanitation facility in Indonesia should be realised to reduce demand of boiling water using unsafe cooking fuels.

In this paper, I use a large set of macroeconomic and financial predictors to forecast U.S. recession periods. I adopt Bayesian methodology with shrinkage in the parameters of the probit model for the binary time series tracking the state of the economy. The in-sample and out-of-sample results show that utilizing a large cross-section of indicators yields superior U.S. recession forecasts in comparison to a number of parsimonious benchmark models. Moreover, data rich models with shrinkage manage to beat the forecasts obtained with the factor-augmented probit model employed in past research

Iran’s banking industry as a developing country is comparatively very new to risk management practices. An inevitable predictive implication of this rapid growth is the growing concerns with regard to credit risk management which is the motivation of conducting this research. The paper focuses on the credit scoring aspect of credit risk management using both logit and probit regression approaches. Real data on corporate customers are available for conducting this research which is also a contribution to this area for all other developing countries. Our questions focus on how future customers can be classified in terms of credibility, which models and methods are more effective in better capturing risks. Findings suggest that probit approaches are more effective in capturing the significance of variables and goodness-of-fitness tests. Seven variables of the Ohlson O-Score model are used: CL_CA , INTWO , OENEG , TA_TL , SIZE , WCAP_TA , and ROA ; two were found to be statistically significant in logit ( ROA , TL_TA ) and three were statistically significant in probit ( ROA , TL_TA, SIZE ). Also, CL_CA , ROA , and WCAP_TA were the three variables with an unexpected correlation to the probability of default. The prediction power with the cut-off point is set equal to 26% and 56.91% for defaulted customers in both logit and probit models. However, logit achieved 54.85% correct estimation of defaulted assets, 0.37% more than what probit estimated.

Two convenient classifications for variables which are not amenable to treatment by the principal tool of econometrics, regression analysis, are quantal responses and limited responses. In the quantal response (all or nothing) category are dichotomous, qualitative and categorical outcomes, and the methods of analysis identified as probit and logit are appropriate for these variables. Illustrative applications include decisions to own or rent, choice of travel mode, and choice of professions. The limited response category covers variables which take on mixtures of discrete and continuous outcomes, and the prototypical model and analysis technique is identified as tobit. Examples are samples with both zero and positive expenditures on durable goods, and models of markets with price ceilings including data with both limit and non-limit prices. While the tobit model evolved out of the probit model and the limited and quantal response methods share many properties and characteristics, they are sufficiently different to make separate treatment more convenient.

Land fragmentation is high and increasing in the Gamo Highlands of southwest Ethiopia. We postulate that this substantial land fragmentation is obstructing the adoption of sustainable land management practices as climate adaptation measures. To explore this, a mixed method study was conducted with emphasis on a multivariate probit model. The results indicate that farmers adapt to climate change and variability they perceive. According to the probit model, there is no clear answer to the question whether land fragmentation facilitates or obstructs adoption of sustainable land management practices. Yet, a qualitative analysis found that farmers perceive land fragmentation as an obstacle to land improvement as adaptation strategy. Moreover, farmers invest more in land improvement on plots close to their homestead than in remote plots. However, the higher land fragmentation also promoted crop diversification, manure application and terracing. Although exogenous to farmers, we therefore suggest that land fragmentation can be deployed in climate change adaptation planning. This can be done through voluntary assembling of small neighboring plots in clusters of different microclimates to encourage investment in remote fields and to collectively optimize the benefits of fragmentation to adaptation.

We propose a two-stage probit model (TPM) to predict recovery rates. By the ordinal nature of the three categories of recovery rates: total loss, total recovery, and lying between the two extremes, we first use the ordered probit model to predict the category that a given debt belongs to among the three ones. Then, for the debt that is classified as lying between the two extremes, we use the probit transformation regression to predict its recovery rate. We use real data sets to support TPM. Our empirical results show that macroeconomic-, debt-, firm-, and industry-specific variables are all important in determining recovery rates. Using an expanding rolling window approach, our empirical results confirm that TPM has better and more robust out-of-sample performance than its alternatives, in the sense of yielding more accurate predicted recovery rates.

Spatial/spatiotemporal interdependence—that is, that outcomes, actions or choices of some unit-times depend on those of other unit-times—is substantively important and empirically ubiquitous in binary outcomes of interest across the social sciences. Estimating and interpreting binary-outcome models that incorporate such spatial/spatiotemporal dynamics directly is difficult and rarely attempted, however. This article explains the inferential challenges posed by spatiotemporal interdependence in binary-outcome models and recent advances in their estimation. Monte Carlo simulations compare the performance of one of these consistent and asymptotically efficient methods (maximum simulated likelihood, using recursive importance sampling) to estimation strategies naïve about (inter-) dependence. Finally, it shows how to calculate, in terms of probabilities of outcomes, the estimated spatial/spatiotemporal effects of (and response paths to) hypotheticals of substantive interest. It illustrates with an application to civil war in Sub-Saharan Africa.

Despite considerable protections provided by the patent system, a surprisingly small number of firms use patents. This study focuses on examining empirically Henry and Ponce (2011)’s theoretical finding that firms’ preference of secrecy over patents rise with knowledge tradeability using the Innovation in Australian Business survey data. Besides, other determinants of firms’ choices of patenting versus secrecy are explored. We constructed a trivariate probit model to correct for the endogeneity of the key explanatory dummy variable in the basic bivariate probit model of patents and secrecy. As robustness check, we attempted to correct for the potential sample selection bias caused by using only the innovator subsample. Our key findings are that firms engaged in knowledge trading or those among the largest R&D investors, are more likely to use secrecy than patents. Other findings are consistent with the existing literature, which are large or manufacturing firms and those involving R&D joint-ventures are more likely to use patents, while firms obtaining information from internal and non-market sources are more inclined to use secrecy.

Bivariate probit models can deal with a problem usually known as endogeneity. This issue is likely to arise in observational studies when confounders are unobserved. We are concerned with testing the hypothesis of exogeneity (or absence of endogeneity) when using regression spline recursive and sample selection bivariate probit models. Likelihood ratio and gradient tests are discussed in this context and their empirical properties investigated and compared with those of the Lagrange multiplier and Wald tests through a Monte Carlo study. The tests are illustrated using two datasets in which the hypothesis of exogeneity needs to be tested.

The pregibit binary choice model is built on a distribution that allows symmetry or asymmetry and thick tails, thin tails, or no tails. Thus, the model is much more flexible than the traditional binary choice models: pregibit nests logit, approximately nests probit, loglog, cloglog, and gosset models and incorporates the linear probability model. Greater flexibility allows a more accurate estimation of the data-generating process, including asymmetric and thick/thin tails. We prove that the maximum likelihood estimator of the pregibit model is consistent and asymptotically normally distributed. A Monte Carlo analysis and two real-world examples show that probit and logit estimates may show misleading evidence in cases where a pregibit model is statistically preferred. One example concerns enrollment in post-secondary education in Belgium: The pregibit estimate of the enrollment gap between Belgian natives and foreign students is 50 % larger, and the type of high school (general, technical, catholic) is more influential. The second example examines the outcome of mortgage applications in the USA. Here, pregibit estimates assign a stronger role to variables that measure the financial strength of mortgage applicants and a weaker role to demographic characteristics including minority status. More importantly, the distribution of the disturbances proves to be seriously skewed: Pregibit indicates that even high-risk applicants (with a probit acceptance probability of nearly 0) have a positive probability of getting their mortgage application approved. Apparently, mortgage officers are more inclined to uncover reasons to make a mortgage deal than to send clients away empty-handed.

Often in data arising out of epidemiologic studies, covariates are subject to measurement error. In addition ordinal responses may be misclassified into a category that does not reflect the true state of the respondents. The goal of the present work is to develop an ordered probit model that corrects for the classification errors in ordinal responses and/or measurement error in covariates. Maximum likelihood method of estimation is used. Simulation study reveals the effect of ignoring measurement error and/or classification errors on the estimates of the regression coefficients. The methodology developed is illustrated through a numerical example.