Bivariate Probit Estimation Research Articles

Locus of control and performance pay: Evidence from US survey data

AbstractThis work examines the influence of locus of control on sorting into performance pay jobs. It uniquely examines different types of performance pay schemes, demonstrating sharp differences between them. Bivariate probit estimates indicate workers with an internal locus of control sort into individual schemes but not joint schemes. Wage equations reveal that adding locus of control modestly reduces the return to individual performance pay but that in more complete specifications, the return to an internal locus of control becomes vanishingly small, which suggests that its primary importance is in sorting (not only into performance pay but into education and occupation).

Travel Cost on Election Day and Voter-Turnout in Chile: Exploring University Students’ Willingness to Cast a Hypothetical Online Vote

An i-voting system may promote electoral participation by reducing travel cost and time to polling places, especially among youth who are more accustomed to technological changes. We study the linkage between travel costs on election day and voter turnout by comparing past electoral participation with stated voting behavior in a hypothetical i-voting system. We believe that the link between transportation costs, i-voting, and voter-turnout emerges as an interesting opportunity to disentangle the mechanism behind the expected increase in political participation after diversifying voting channels. Data were collected using an online questionnaire that was disseminated among Chilean university students. Binary and bivariate probit estimates show that conventional turnout probability among university students is negatively affected by travel costs on election day. Interestingly, whereas political interest and democracy valuation still augment the probability of voter turnout with i-voting, travel-to-polling-station costs are not statistically relevant.

Households’ health insurance status and COVID-19 vaccination in Nigeria: A recursive bivariate probit and decomposition estimation

Health insurance remains a viable option for the promotion of healthcare service utilization and efficiency. Very few studies have analyzed the linkages between health insurance uptake and COVID-19 vaccination decisions. This paper contributes to existing literature by recursively analyzing the effect of health insurance uptake on COVID-19 vaccination status in Nigeria. The data were the second wave of the National Longitudinal Phone Survey (NLPS), comprising 2750 respondents. The data were analyzed with the recently developed Recursive Bivariate Probit and Decomposition Estimation approach. The results showed that 31.50% and 7.78% were vaccinated and health insured, respectively. Health insurance was positively and significantly influenced (p<0.05) by being from the North West zone, urban residence, needing non-COVID maternal health, and adults or households’ heads as the major vaccination decision makers. In addition, being vaccinated or having a vaccinated households’ member was negatively and significantly influenced by three zonal variables (North East, North West, and South East) and urban residence, but positively influenced by age, needing COVID-19 related health services, concurring with making the vaccines mandatory and adults being the major vaccination decision makers. Health insurance recursively influenced being vaccinated or having a vaccinated households’ member with significant positive treatment effects (p<0.05). It was concluded that efforts to promote health insurance will facilitate acceptability of COVID-19 vaccines. In addition, uptake of health insurance and COVID-19 vaccination can be enhanced with proper focus on some peculiar zonal and sectoral factors through initiatives that target adult households’ members.

A matter of time: The influence of underperformance duration on corporate misconduct

AbstractResearch Question/IssueThis study examines firms' reactions to the duration of underperformance. We posit that firms are more likely to engage in misconduct to solve the problem of underperformance as the length of time a firm has been underperforming prolongs. Further, we investigate how divergent external governance actors shape underperforming firms' motivation for misconduct and consequently affect their responses to underperformance duration.Research Findings/InsightsUsing bivariate probit estimations for panel data of 2662 Chinese publicly listed firms during 2007–2018, we uncover that underperformance duration is positively associated with the likelihood of a corporate misconduct commission. In addition, the positive relationship between the duration of firm underperformance and corporate misconduct is mitigated by the level of state ownership but reinforced by the number of analysts covering the firm.Theoretical/Academic ImplicationsThis study extends the behavioral theory of the firm by incorporating the construct of underperformance duration from a time perspective, which is a proactive signal of firms' illicit decisions. We show that the duration of underperformance is positively associated with the likelihood of corporate misconduct, which is moderated by the firms' external governance actors who have different time pressures to solve financial problems.Practitioner/Policy ImplicationsThis study offers insights for regulators interested in the prevention of ex‐ant misconduct. Identifying underperformance duration as a critical predictor of illegal activities helps to improve regulators' vigilance. Moreover, a holistic executive evaluation system that shows more tolerance for short‐term underperformance is needed.

Effect of Health Insurance Uptake on Hesitancy toward COVID-19 Vaccines in Nigeria: A Recursive Bivariate Probit and Decomposition Estimation.

Moral hazard remains one of the major challenges of health insurance administration. This paper recursively analyzed the effect of health insurance on the willingness to take COVID-19 vaccines in Nigeria. The data comprised 1892 unvaccinated respondents in the 2021/2022 National Longitudinal Phone Survey (NLPS). The data were analyzed with Coban's recursive probit regression and decomposition approaches. The results revealed that 5.87% were health insured, and 7.93% were willing to take COVID-19 vaccines. Health insurance uptake significantly increased (p < 0.05) with an adult being the decision-maker on vaccination, requiring family planning, and urban residence, while it reduced with loss of jobs and residence in the southeast and southwest zones. In addition, health insurance significantly (p < 0.01) increased the willingness to take COVID-19 vaccines, along with each adult, all adults, and households' heads being the major vaccination decision-makers, loss of jobs, and support for making COVID-19 vaccines compulsory. The average treatment effects (ATEs) and average treatment effect on the treated (ATET) of health insurance were significant (p < 0.01), with positive impacts on willingness to be vaccinated. It was concluded that policy reforms to promote access to health insurance would enhance COVID-19 vaccination in Nigeria. In addition, hesitancy toward COVID-19 vaccines can be reduced by targeting adults and household heads with adequate information, while health insurance uptake should target southern states and rural areas.

International, national and sectoral determinants of innovation: evolutionary perspective from the Czech, German, Hungarian and Slovak community innovation survey data

This paper studies the determinants of innovation activities in Central European economies at the firm, sectoral, country and international levels. It focuses on innovation activities in four countries, the Czech Republic, Germany, Hungary, and Slovakia. Our dataset includes data from the three waves (2010, 2012, 2014) of the Community Innovation Survey (CIS), in a total of 58,880 observations, which we combined with 2-digit NACE rev. 2 sectoral variables (Herfindahl index, average values of age, profits, intangible assets, shares of large and medium-sized enterprises). These variables were calculated from 910,731 observations originating from the Amadeus database. We used Heckman and Bivariate Probit estimation procedures to observe the dynamics of new-to-the-market product and process innovation over time and at different levels of the innovation ecosystem. We focused on sectoral variables and found that determinants of innovation activity differed substantially. Our analysis documented the fluctuation of sectoral variables over time, which aligns with evolutionary theories. At the international level, the results suggest a disequilibrium effect of some sectoral variables over time. National innovation systems differ, and individual coefficients are hardly comparable without an innovation input-output context. We provided several recommendations for future research, such as the issue of non-linearity in some identified determinants.

Father Parental Leave Use in Spain: The Role of the Female Partner Labour Situation

This article presents novel empirical evidence of fathers’ parental leave usage by introducing a family dimension in Spain. To test this hypothesis, a bivariate probit estimation was used to analyse the effect of the mother’s labour force participation on the father’s decision to take parental leave. This procedure allowed us to address the issue of simultaneous factors affecting the decisions of both the man and the woman, which were relevant to interpreting for the phenomenon. The results suggested that successfully using fathers’ paternity leave as a tool to promote gender equality depends on the family household’s characteristics and the woman’s connection to the job market. The bivariate probit estimation revealed that the effect of the woman’s decision on the man’s choice is much stronger than a naive regression would suggest.

Employment effects of language training for unemployed immigrants

Proficiency in the host country’s language is an important factor for the successful labor market integration of immigrants. In this study, I analyze the effects of a language training program for professional purposes on the employment opportunities of participants in Germany. I apply an instrumental variable approach and exploit differences in lagged local training intensities. Bivariate probit estimates show that 2 years after the program started, the employment probability of immigrants who were unemployed in 2014 and participated in the program had increased by more than nine percentage points as a result of language training.

Abuse is not a zero-sum game! The case for zero tolerance of match official physical and verbal abuse

ABSTRACT Emergent research has investigated the impact of abuse on the decision of match officials to leave their sport. The existing literature is largely descriptive and qualitative. Based on large surveys of football referees in France and the Netherlands, this paper investigates the factors that are associated with the verbal and physical abuse of the referees and also the association of this abuse with the intentions of referees to quit officiating. The associations are investigated by estimating the marginal effects from bivariate probit and probit models respectively. Bivariate probit estimation reveals a strong correlation between each form of abuse. Both, unsurprisingly, are also positively associated with years of experience of referees. Probit estimation reveals that both forms of abuse, as well as intimidation from refereeing certain teams, are associated with an increased consideration of referees to quit. As increased intention to quit is also associated with the experience of the referee it is likely that the effect of abuse on referee considerations of quitting increase through time. The main conclusions are that the alternative forms of abuse are not zero-sum and both should be targeted by governing bodies to reduce the decline in the number of football referees. The data show that support of referees, for example through mentoring, can offset stated intentions to quit. Highlights This study looks at the factors that are associated with verbal and physical abuse of football referees and the association of this abuse with the intentions to quit. The alternative forms of abuse are not zero-sum and both should be targeted to reduce the decline in referees. Support of referees, for example through mentoring, can offset stated intentions to quit.

Data science and GIS-based system analysis of transit passenger complaints to improve operations and planning

Transit user complaints support system resilience by serving as a data source for service improvements. This study shows how geographic information system (GIS)-based analysis, econometric models, and latent class analysis can improve system-wide understanding of passenger complaints. The analyzed dataset consists of 718 passenger complaints concerning the operation of municipal lines in Jerusalem as the study region. The analytical methods consists of GIS-based analysis and statistical modeling: mapping, recursive bivariate probit estimation, negative binomial model estimation, and latent class analysis. The GIS-based analysis showed that the spatial distribution of complaints changes over time as a function of service disruption type and geographical area. The recursive bivariate probit model results indicated that the most acute sources of frustration are service problem recurrence and monetary loss, with the former caused by overcrowding, delays and line cancellations. The negative binomial model results shows that the number of complaints increases with an increase in the passenger boarding to bus arrivals ratio. Latent class analysis reveals that, in terms of both prevalence and customer frustration, overcrowding delays and line cancellations are the most acute problems in the study region. The proposed interface between transit complaints and GIS databases can readily be implemented by transport operators and authorities.

Information acquisition and adoption of conservation agriculture by smallholder farmers in South-West Nigeria: Recursive bivariate probit estimation

The persistent use of traditional farming practices and cultivation of low yielding variety of crops on scattered small farmland holdings by agrarian farming households in Nigeria has put pressure on land and water resources, consequently leading to depletion of soil productivity with spill-over effects on the environment, crop-output and farm-income. Addressing this requires a holistic approach, especially in light of farmers’ apathy towards transitioning from traditional farming practices to more sustainable ones, and motivated this research. This research used cross-sectional survey data obtained from 350 farmers randomly chosen from South-West Nigeria. This study applied a descriptive statistical technique to present the mean statistics of sampled farmers’ characteristics. Similarly, the study applied a bivariate probit model to examine the influences on farmers’ decisions about conservation agriculture (CA) adoption, as well as to isolate the factors driving farmers’ choices on acquisition of information decision and the use of CA practices. The results revealed that decisions to acquire information and adopt CA were jointly determined by farmers, owing to the positive and strong correlation parameter-rho in the estimated model. More so, the post-estimation Murphy test score apparently revealed no significant departure from the normal and jointly distributed error terms.

The impact of parental labour migration on left‐behind children's educational and psychosocial outcomes: Evidence from Romania

AbstractMany children grow up with parents working abroad. Social scientists are interested in the scholastic achievement and health of these left‐behind children, in order to better understand the positive and negative aspects of migration for the families in the sending countries. This paper examines the causal effects of parents' migration on the education, physical, and mental health of left‐behind children aged 11 to 15 years in Romania, a country where increasingly more children have parents working abroad. Using data from a unique representative survey carried out in 2007, instrumental variable and bivariate probit estimates have been performed. The paper finds evidence for a significant positive effect of parental migration on children's school performance (reflected in higher grades) and a higher probability of suffering from depression and having health problems more frequently. The study furthermore demonstrates that living in transnational families is more harmful for girls and for those from rural areas.

Individual characteristics, behavioral biases, and attitudes toward foreign workers: Evidence from a survey in Japan

This study examines individual attitudes toward foreign workers jointly with their trade policy preferences based on a survey of more than 10,000 respondents in Japan. Our bivariate probit estimation results show that people influenced by status-quo bias or risk aversion tend to have significantly lower probability of supporting both foreign workers and imports. Individuals opposing foreign workers tend to have pessimistic views of the national economy's prospects and no personal acquaintance with foreigners. We also confirm the effects of standard variables, such as education and occupation. These findings suggest that wide-ranging measures are required for expanding support for foreign workers.

The double trap: Institutions and economic development

The empirical growth literature has established that institutional quality is a deep determinant of economic growth. We examine whether institutional quality in low income countries converges to the level witnessed in high income countries, or whether they are trapped in convergence clubs that stagnate or even deteriorate over time. Using the log-t-test suggested by Phillips and Sul (2007), we find evidence of multiple equilibria in institutional quality, with several countries stuck in poor quality institutions traps. We further find that per capita incomes of some of the developing countries are also stuck in low-level traps. Finally, using bivariate probit estimations, we establish that poor institutional traps are major determinants of low income traps. These results indicate that these countries are caught in a double trap where their incomes are stuck in low-level traps from which it is difficult to escape, because the institutions that enable growth are also stuck in low-quality traps.

Effect of Boarding on Mortality in ICUs.

Hospitals use a variety of strategies to maximize the availability of limited ICU beds. Boarding, which involves assigning patients to an open bed in a different subspecialty ICU, is one such practice employed when ICU occupancy levels are high, and beds in a particular unit are unavailable. Boarding disrupts the normal geographic colocation of patients and care teams, exposing patients to nursing staff with different training and expertise to those caring for nonboarders. We analyzed whether medical ICU patients boarding in alternative specialty ICUs are at increased risk of mortality. Retrospective cohort study using an instrumental variable analysis to control for unmeasured confounding. A semiparametric bivariate probit estimation strategy was employed for the instrumental model. Propensity score matching and standard logistic regression (generalized linear modeling) were used as robustness checks. The medical ICU of a tertiary care nonprofit hospital in the United States between 2002 and 2012. All medical ICU admissions during the specified time period. None. The study population consisted of 8,429 patients of whom 1,871 were boarders. The instrumental variable model demonstrated a relative risk of 1.18 (95% CI, 1.01-1.38) for ICU stay mortality for boarders. The relative risk of in-hospital mortality among boarders was 1.22 (95% CI, 1.00-1.49). GLM and propensity score matching without use of the instrument yielded similar estimates. Instrumental variable estimates are for marginal patients, whereas generalized linear modeling and propensity score matching yield population average effects. Mortality increased with boarding of critically ill patients. Further research is needed to identify safer practices for managing patients during periods of high ICU occupancy.

Source and Use of Insecticide Treated Net and Malaria Prevalence in Ghana

This study contends that the achievement of the Global objective of reducing malaria prevalence through the scaling up of Insecticide Treated Nets (ITNs) is largely dependent on the extent of education incorporated into its distribution by the sources (distributors). The study categorises the sources into those that include some sort of education about how to use the nets and those that do not and examines the effect of these sources on the relationship between ITN use and malaria prevalence in Ghana. A recursive bivariate probit estimation technique that addresses endogeneity between ITN use and malaria prevalence was used to analyse data on 2,908 under-five children from the 2011 Multiple Indicator Cluster Survey (MICS). The descriptive results revealed that the proportion of ITN usage among children in households who acquired their ITNs from government, NGOs and Community Based Agents (CBAs) was higher than the proportion of usage among those who acquired their ITNs from private health centres, market, shops and street vendors that do not include education. The estimation shows that controlling for other socio-demographic factors, sleeping under ITN reduces the likelihood of experiencing malaria by 22 percent. Conclusion: Scaling up ITN distribution is not enough to ensure utilisation and the expected reduction in malaria prevalence unless the source includes education.

Intermediation in Peer-to-Peer Markets: Evidence from Auctions for Personal Loans

I examine the role of intermediaries on the world's largest peer-to-peer online lending platform. This marketplace as well as other recently opened lending websites allow people to auction microcredit over the internet and are in line with the disintermediation in financial transactions through the power of enabling technologies. On the online market, the screening of potential borrowers and the monitoring of loan repayment can be delegated to designated group leaders. I find that, despite superior private information, these financial intermediaries perform worse than the average lender with respect to borrower selection. I attribute this to deliberately sending wrong signals. Bivariate probit estimates of the effect of group membership on loan default indicate positive self selection into group loans. That is borrowers with worse observed and unobserved characteristics select into this contract form. I provide evidence that this is due to a missleading group reputation system that is driven by a short term incentive design, which was introduced by the platform to expand the market and has been discontinued. I further find that, after controlling for this group growth driven selection effect, group affliation per se significantly reduces the probability of loan default.

Does Internal and External Research and Development Affect Innovation of Small and Medium-Sized Enterprises? Evidence from India and Pakistan

This study investigates the impact of internal and external research and development (R&D) on the innovation performance of small and medium-sized enterprises (SMEs) in India and Pakistan. Micro-level data was obtained for 3,492 Indian and 696 Pakistani SMEs from the World Bank’s Enterprise Survey, and bivariate probit estimation techniques were used. The results show that internal and external R&D positively affects product and process innovations. However, this effect is stronger for Indian SMEs. The negative relationship between firm size and innovation output implies that SMEs in both countries face resource constraints. Further, Indian SMEs are dominant in terms of undertaking internal R&D and generating product and process innovations relative to those in Pakistan. The complementary relationship between internal and external R&D has been examined for both countries. The study is unique in comparing Indian and Pakistani SMEs innovation activities using micro-level data. The results suggest that business managers can utilize a balanced combination of internal and external R&D to accelerate innovation output and increase absorptive capacity. Specifically, public support for innovation, such as R&D grants, subsidies, and tax credits, could encourage SMEs to undertake more radical innovations.

Innovation performance of Chilean firms, a bivariate probit analysis

Purpose The purpose of this paper is to investigate the innovation activities of Chilean firms by using micro-level data. Design/methodology/approach Micro-level data have been obtained from the World Bank, Enterprise Survey on 696 Chilean small and medium enterprises (SMEs). Bivariate probit estimation method has been used. Findings The results showed that SMEs are less likely to apply for patents and introduce product innovations. This outcome indicates that Chilean SMEs face resource constraint in terms of introducing product innovations and applying for patents. In addition, SMEs undertaking research and development (R&amp;D) and making network ties with other research institutions are more likely to introduce patents and product innovations. Similarly, SMEs that are engaged in quality programs are more likely to spend on patents. Lastly, SMEs with public support for innovation activities positively influence the patent application. Research limitations/implications Findings imply that SMEs investment in knowledge-based assets (e.g. R&amp;D, networks and quality methods) accelerate their innovation output. Policy makers should not only provide financial incentives (R&amp;D subsidies) to SMEs but also encourage their strong ties with research institutions for higher innovation output. Originality/value Previous studies showed research gap related to micro-level analysis of the Chilean SMEs. For the first time, multiple proxies have been used as dependent variables (product/process innovations and patent application/spending), which is neglected by the past studies.

THE DETERMINANTS OF ORGANISATIONAL CREATIVITY METHODS: AN EMPIRICAL STUDY BASED ON A FRENCH SURVEY

This paper analyses the determinants of different organisational techniques dedicated to creativity by stressing the crucial role played by the dynamic innovative capacities of firms in this process. In particular, we show that the impact of creativity methods varies with the type of innovator (product versus process; single versus complex). We use a bivariate probit estimation on a sample of 4,570 manufacturing firms drawn from the 2010 French Community Innovation Surveys (CIS 2010) to study how the innovation profiles of firms impact the propensity to use organisational creativity methods. The estimation results show a strong but differentiated impact of the innovation profiles of firms (products/process, single/complex) on the use of different creativity methods. These empirical results display the accuracy of modern research on the determinants of intra-firm organisation of creativity.