Factors associated with abuse in the workplace in Bangladesh: An empirical investigation

Workplace abuse is a much-discussed global phenomenon in the world of work. Bangladesh, being a developing country that relies heavily on its labor resource, should have definite methods to protect the workers' rights and safety. Unfortunately, weak frameworks are in place to prevent it, and the lack of awareness among the workers is helping the problem to establish its roots more firmly. Despite the gravity of workplace abuse and its consequences, comprehensive studies for addressing or understanding the problem at a national level is difficult to find in the context of Bangladesh. Using the latest nationally representative survey namely the Quarterly Labour Force Survey (QLFS) 2016-17, this study attempts to bridge the existing gaps through an empirical investigation of the factors associated with workplace abuse in Bangladesh. A total of 16,646 participants with males of 75.9% and females of 24.1% are used for the analysis. A probit model analysis has been applied in this paper to explore how the workers' demographic and socioeconomic characteristics, as well as workplace features, may be associated with experiencing abuse in the workplace. The study finds that younger, less educated, females, elementary job-holders, non-governmental organization workers or those who work in the manufacturing, or services sector are more likely to be abused in the workplace. The study also concludes that the number of workers employed, and the hazardous workplace environment may be related to the probability of being abused. Furthermore, this study shows that full-time workers, workers who are employed temporarily or have an oral contract may face abuse in the workplace more.

Implications of an exogenous shock (COVID-19) on wine tourism business: A Portuguese winery perspective

This study investigates the impact of an exogenous and unexpected shock (COVID-19) on the wine tourism business from the winery's perspective. A sample of 146 Portuguese wineries was surveyed. The econometric results show that the share of wine tourism sales, the amount of dependence on exports and the assertiveness of brand recognition have a structural effect on direct-to-consumer tasting room wine sales, even when the winery's business is disrupted by a shock that degrades the dynamics and flows of international trade. The research establishes a starting point that allows to understand the implications of an exogenous shock on the structure of the winery's business, calling for further research on the firm's economic performance as well as on the consumer's behaviour in a post-pandemic context.

Can internet use change sport participation behavior among residents? Evidence from the 2017 Chinese General Social Survey

Purpose

The popularization of the internet has promoted the implementation of China's national fitness strategy and created conditions for Chinese residents to participate in sports. The internet is an essential medium for disseminating sports knowledge, and the use of the internet can change sport participation behaviors. Therefore, the internet can be used to popularize sports knowledge and promote the participation of all people in sports and thus improve the health of the entire population. This study attempts to empirically analyse how the use of the internet changes sport participation behavior.

Method

Utilizing data from the 2017 China General Social Survey, a probit model, ivprobit model, and bias-corrected non-parametric percentile bootstrap test were used to analyse the impact of internet use on sport participation behavior.

Results

The empirical results show that internet use significantly increased the probability of participation in sports by Chinese residents. Heterogeneity test results showed that internet use was more effective in promoting sport participation in middle-aged groups, groups of older persons, unmarried groups, and groups with a high school education or above. The mediating effect test results showed that internet use influenced residents' participation in sports by promoting social interaction, leisure and entertainment, and learning and recharging.

Conclusions

The internet has changed participation in sports; specifically, the use of the internet promotes sport participation. Additionally, internet use has a more obvious impact on improving the sport participation behavior of middle-aged, older, unmarried, and middle- and higher-educated individuals. Internet social interaction, internet entertainment and internet learning are effective channels to encourage Chinese residents to participate in sports and improve their health.

Socioeconomic Disparities in Health Care Consumption: Using the 2018-China Family Panel Studies

The existing research on residents’ health care consumption mostly covers medical care consumption and seldom regards residents’ health care consumption as an independent research object. This article takes residents’ healthcare consumption as the research object and aims to explore the impact of socioeconomic status on healthcare consumption and its mechanisms. The data of this study came from the 2018-China Family Panel Studies (CFPS). The binary probit regression model and the Tobit model explored the impact mechanism of residents’ income, education, occupation, and physical activity on health care consumption decision-making and health care expenditure, respectively. The research results showed that, from the perspective of the direct influence mechanism, residents’ work income (0.029, p < 0.01) and education level (811.149, p < 0.01) had a significant positive impact on health care consumption. Residents whose occupations (−99.697, p < 0.01) tend to be more skilled and also have higher health care consumption. From the perspective of the mediating mechanism, residents’ physical exercise duration had a significant positive impact on their participation in healthcare consumption (0.005, p < 0.01) but had a weaker impact on healthcare consumption expenditure (21.678, p < 0.1). In general, socioeconomic status represented by income, education, and occupation had a significant positive impact on residents’ health care consumption. The duration of physical exercise also played an important mediating role.

Compliance Indicators of COVID-19 Prevention and Vaccines Hesitancy in Kenya: A Random-Effects Endogenous Probit Model

Vaccine hesitancy remains a major public health concern in the effort towards addressing the COVID-19 pandemic. This study analyzed the effects of indicators of compliance with preventive practices on the willingness to take COVID-19 vaccines in Kenya. The data were from the COVID-19 Rapid Response Phone Surveys conducted between January and June 2021 during the fourth and fifth waves. The data were analyzed with the random-effects endogenous Probit regression model, with estimated parameters tested for robustness and stability. The results showed that willingness to take vaccines increased between the fourth and fifth waves. Compliance with many of the preventive practices also improved, although the utilizations of immune system-promoting practices were very low. The panel Probit regression results showed that compliance indicators were truly endogenous and there was existence of random effects. Immune system-boosting and contact-prevention indicators significantly increased and decreased the willingness to take vaccines, respectively (p < 0.01). The experience of mental health disorders in the form of nervousness and hopelessness also significantly influenced vaccine hesitancy (p < 0.10). Willingness to take vaccines also significantly increased among older people and those with a formal education (p < 0.01). Different forms of association exist between vaccine hesitancy and the prevention compliance indicators. There is a need to properly sensitize the people to the need to complement compliance with COVID-19 contact-prevention indicators with vaccination. Addressing mental health disorders in the form of loneliness, nervousness, depression, hopelessness and anxiety should also become the focus of public health, while efforts to reduce vaccine hesitancy should focus on individuals without formal education, males and youths.

Composite likelihood inference for ordinal periodontal data with replicated spatial patterns

Spatial ordinal data observed separately for multiple subjects are common in biomedical research, yet statistical methodology for such ordinal data analysis is limited. The existing methodology often assumes a single realization of spatial ordinal data without replications, a commonplace in disease mapping studies, and thus are not directly applicable. Motivated by a dataset evaluating periodontal disease (PD) status, we propose a multisubject spatial ordinal model that assumes a geostatistical spatial structure within a regression framework through an elegant latent variable representation. For achieving computational scalability within a classical inferential framework, we develop a maximum composite likelihood method for parameter estimation, and establish the asymptotic properties of the parameter estimates. Another major contribution is the development of model diagnostic measures for our dependent data scenario using generalized surrogate residuals. A simulation study suggests sound finite sample properties of the proposed methods. We also illustrate our proposed methodology via application to the motivating PD dataset. A companion R package clordr is available for easy implementation.

Does Chronic Obstructive Pulmonary Disease Affect Workers' Health?

During recent decades, the elevation of workers' health has become the utmost point of concern since it is considered among the primary indicators of economies. The economies, especially the emerging ones, are primarily focusing on every indicator to uplift their businesses. Along with the other aspects, it is also required to assess the impact of Chronic Obstructive Pulmonary Disease (COPD) on workers' health conditions in small- and medium-scale enterprises (SMEs). With this aim, we are presenting a detailed analysis to reveal useful insights regarding the COPD-workers' health nexus. The sample set of 1,008 workers is working in various SMEs in Beijing and Tianjin from September, 2020. The findings infer that a rise in COPD concerning wages will uplift the worker health problems due to COPD affecting worker health. Whereas, the working condition and tools, smoking years, and health safety training have a statistically adverse effect on workers' health concerning wages. The outcomes in terms of insights would be useful for planning future perspectives.

Factors Determining Consumer Acceptance of Biofortified Food: Case of Zinc-Fortified Wheat in Pakistan's Punjab Province

Zinc (Zn) is a fundamental micronutrient required by all living organisms. Zn deficiency among children under 5 years, pregnant, and child-bearing women has been identified in developing countries such as Pakistan. Biofortified crops can increase micronutrient levels and decrease deficiencies. Meanwhile, consumer acceptance is essential, given that genetic alterations can occur during biofortification, resulting in changes in sensory traits and the quality of grains. Therefore, the present study focuses on the determining factors for consumer acceptance of Zn-biofortified wheat., an experimental survey was conducted to achieve the study's objectives. Qualitative and quantitative data were collected and analyzed from 203 respondents in the Punjab province. The results regarding sensory perceptions revealed that people attached great importance to the appearance of the chapati prepared with Zn-biofortified wheat. Therefore, they were willing to purchase Zn-biofortified wheat when asked to choose between the conventional wheat and the Zn-biofortified wheat. Moreover, the probit model illustrates that the level of education in the family and having young children aged under 5 years in the household positively impacted the acceptance of Zn-biofortified wheat among the participants. The findings suggest that there is significant scope for promoting Zn-biofortified wheat in the country. It is also imperative to ensure its availability across various regions so that households with weak purchasing power can buy and address their Zn deficiency. Furthermore, policymakers could introduce reforms targeting business communities for food management, keeping Zn-biofortified wheat in the priority stream.

Factors explaining the fear of being infected with COVID-19

Background

The prevalence of COVID‐19 has a social and economic impact on people, leaving them distressed and fearful of getting infected.

Objective

To determine the variables attributable to the fear of contracting COVID‐19.

Design

This is a quantitative study based on an online cross‐sectional self‐administered survey in Chile between 10 July 2020 and 10 August 2020.

Setting and participants

A sample of 531, comprising over 18‐year‐old participants from middle‐ and high‐income levels, was selected.

Outcome measures

Estimations were obtained using a probit regression model with marginal effects.

Results

Fear prevailed mainly in women. It has a positive relationship with variables such as chronic illnesses, infectious family or relatives, reduction in economic activity and perception of bad government response to a pandemic. Fear has a negative relationship with knowledge about COVID‐19, education level and ageing. Moreover, those who consider socioeconomic impact less important than health care do not fear a COVID‐19 infection.

Discussionand conclusion

The socioeconomic and health aspects help predict fears. Thus, the government should prioritize these variables in implementing policies. The government's credibility and communication systems can also reduce fears of contracting COVID‐19.

Patient or public contribution

A pilot focus group of COVID‐19–recuperated individuals and some members of our interest groups were consulted in the design stage of the study; this helped in constructing the survey questions. Additionally, three independent individuals volunteered to read and comment on the draft manuscript.

Social Work Responses and Household-level Determinants of Coronavirus Preparedness in Rural Ethiopia

The novel coronavirus caused the death of many people globally, and in Ethiopia. The death of people due to COVID surpasses 1,466,289with more than 63,135,973 cases in the world. This study aimed to identify the barriers toward the understanding of COVID-19, the rural (agrarians) public commitment to respond coronavirus, and the factors that affect their preparedness in rural Ethiopia. Probit regression and descriptive statistics were used to analyze data from a sample of 190 respondents. The result revealed that the public infrastructural problems (roads, health centers, telecommunication and broadcasting service) were the main barriers identified in this study. In response, the agricultural and health extension providers, college and university students, local administrators and government official, religious leaders, and community elders were contributing to enhance the public understanding and preparedness. The model result confirmed that gender, age group, family education level, membership to communal association, family mobile usage, health extension service, non-farm income, and economic situation were significant factors for preparedness. Intervention aimed at easing identified key limit factors to rural and agrarian community preparedness as well as the way to enhance public understanding through reasonable support to local stakeholders against COVID-19.

Reliability of pelvimetry is affected by observer experience but not by breed and sex: A cross-sectional study in beef cattle

Pelvis size plays an important role to prevent dystocia in cattle caused by the foeto‐maternal disproportion in commonly primiparous females. The reproducibility and repeatability are two important aspects for the reliability of the measurements to use in the selection of cattle for culling. Pelvic measures were taken with a Rice pelvimeter from 224 young cattle (180 females and 44 males) of four beef breeds in South Africa. One experienced and two inexperienced observers each measured pelvic height and width twice. The proportion measurements with a maximum difference of 0.5 cm within animal compared with the first measurement by the experienced observer are around 80% and by the inexperienced observers around 50% for pelvic height and around 60% for pelvic width. Breed and sex do not affect the reliability of pelvimetry by an experienced observer. Under‐ and overestimation of pelvis size were observed in inexperienced observers, which seems to be unrelated to breed and sex.

Estimation of Mean Variation in Prediction Probability for Prevalence of Hypertension in Middle-Aged and Older Chinese Using Probit Model

The aims of this study are to estimate the mean change in the predicted probability and identify the most important predictors of diagnosed, measured, total, and undiagnosed hypertension among aged 45+ adults in China. We used data collected from the fourth wave (2015) of the China Health and Retirement Longitudinal Study (n = 12 236). First, we estimated the prevalence of diagnosed, measured, total, and undiagnosed hypertension. Second, we used probit models to identify the factors that were associated with hypertension, and we estimated average marginal effects of variables in probit models. Among Chinese people aged 45+, the prevalence of diagnosed, measured, total, and undiagnosed hypertension were 23.1%, 32.7%, 42.6%, and 19.5%, respectively. The probability of total hypertension is higher for overweight and obesity than normal body mass index (10.4% and 19.3%, respectively), higher for past smokers and current smokers than nonsmokers (5.9% and 3.8%, respectively), higher for urban population than rural population (4.0%), and lower for married individuals than unmarried/single (-7.1%). Our results suggest that continued strengthening for smoking prevention is needed to reduce smoking-related hypertension and greater focus on prevention of hypertension are necessary for overweight or obesity and in urban areas among middle-aged and older adults in China.

A mediation analysis for a nonrare dichotomous outcome with sequentially ordered multiple mediators

Mediation analyses can help us to understand the biological mechanism in which an exposure or treatment affects an outcome. Single mediator analyses have been used in various applications, but may not be appropriate for analyzing intricate mechanisms involving multiple mediators that affect each other. Thus, in this article, we studied multiple sequentially ordered mediators for a dichotomous outcome and presented the identifiability assumptions for the path-specific effects on the outcome, that is, the effect of an exposure on the outcome mediated by a specific set of mediators. We proposed a closed-form estimator for the path-specific effects by modeling the dichotomous outcome using a probit model. Asymptotic variance of the proposed estimator is derived and can be approximated via delta method or bootstrapping. Simulations under a finite sample showed the validity of our method in capturing the path-specific effects when the probability of each potential counterfactual outcome is not small and demonstrated the utility of a computationally efficient alternative to bootstrapping for calculating variance. The method is applied to investigate the effects of polycystic ovarian syndrome on live birth rates mediated by estradiol levels and the number of oocytes retrieved in a large electronic in vitro fertilization database. We implemented the method into an R package SOMM, which is available at https://github.com/roqe/SOMM.

Beyond Smoking: Environmental Determinants of Asthma Prevalence in Western Nepal

BACKGROUND

Asthma is widely prevalent in Nepal, but the causes are not well known aside from some general associations with ambient air pollution and microbial exposures. Information on the wide-ranging determinants of asthma prevalence among the population at risk can help policy makers to reduce risk.

OBJECTIVE

The present study is a preliminary investigation of the environmental, socioeconomic and behavioral determinants of asthma prevalence in western Nepal.

METHODS

A survey was conducted among 420 randomly selected households in western Nepal. A cross-sectional analytical study design was employed with the primary data using econometric tools of probit and logistic regression.

RESULTS

Environmental variables such as extreme cold winter, deteriorating river water quality and air pollution were associated with an increase in asthma prevalence. However, individual or household characteristics such as advancing age of household head, use of pesticides in the home for the control of pests, piped drinking water with old pipes and lack of participation in awareness programs were associated with an increase in asthma prevalence.

DISCUSSION

Among environmental factors, decreasing river water quality, increasing air pollution, and extremely cold winters are more likely to contribute to asthma prevalence. In light of the effects of environmental factors on the prevalence of asthma in Nepal, the high public and private costs of asthma could further impoverish the rural poor.

CONCLUSIONS

Environmental health policy makers should design adaptation strategies along with additional community programs addressing asthma-instigating factors. Programs to reduce environmental pollution can reduce morbidity due to asthma.

PARTICIPANT CONSENT

Obtained.

ETHICS APPROVAL

This study was approved by the Ethical Committee of the Nepal Health Research Council.

COMPETING INTERESTS

The authors declare no competing financial interests.

Validation of Molecular Typing for Endometrial Screening Test That Predicts Benign and Malignant Lesions

The aim of this study is to examine the immunocytochemical expression of p53, Ki-67, and CA125 in endometrial brush samples for endometrial cancer. Forty-four patients were recruited with liquid-based cytology preparations during a 5-month period. Both the histological and cytological samples were assessed by histology based on hematoxylin and eosin (H&E), and the expression of p53, CA125, and Ki-67 in endometrial cells was examined by immunocytochemistry. The percentage and intensity of endometrial cells were scored on a scale of 0-3. The final score was calculated by the addition of all partial scores, and then Probit model was used to predict the possibility for malignant lesions. The mean immunoreactivity score of the three immunocytochemical biomarkers (p53, CA125, and Ki-67) in the positive group (including atypical hyperplastic cells and malignant cells) was significantly higher than in the negative group (benign cells and non-atypical hyperplastic cells). The possibility value of the positive group was also significantly higher than the negative group (P < 0.05). The cutoff value of the possibility value was 0.754, the sensitivity and specificity of which were 86.4 and 95.5%. The assessment of p53, CA125, and Ki-67 combined with the prediction model is valuable for the detection of endometrial cancer and atypical hyperplasia in endometrial cytology.

Normal frailty probit model for clustered interval-censored failure time data

Clustered interval-censored data commonly arise in many studies of biomedical research where the failure time of interest is subject to interval-censoring and subjects are correlated for being in the same cluster. A new semiparametric frailty probit regression model is proposed to study covariate effects on the failure time by accounting for the intracluster dependence. Under the proposed normal frailty probit model, the marginal distribution of the failure time is a semiparametric probit model, the regression parameters can be interpreted as both the conditional covariate effects given frailty and the marginal covariate effects up to a multiplicative constant, and the intracluster association can be summarized by two nonparametric measures in simple and explicit form. A fully Bayesian estimation approach is developed based on the use of monotone splines for the unknown nondecreasing function and a data augmentation using normal latent variables. The proposed Gibbs sampler is straightforward to implement since all unknowns have standard form in their full conditional distributions. The proposed method performs very well in estimating the regression parameters as well as the intracluster association, and the method is robust to frailty distribution misspecifications as shown in our simulation studies. Two real-life data sets are analyzed for illustration.

Semiparametric probit model for informative current status data

Semiparametric probit models have recently attracted some attention for regression analysis of failure time data partly due to the popularity of the normal distribution and its special features. In this paper, we discuss the fitting of such models to informative current status data, which often occur in many areas such as medical studies and whose analysis has also recently attracted a lot of attention. For inference, a sieve maximum likelihood approach is developed and the methodology is further generalized to a class of generalized semiparametric probit models. A simulation study is conducted to assess the finite sample properties of the presented approach and indicates that it works well in practical situations. An application that motivated this study is provided.

Residuals and Diagnostics for Ordinal Regression Models: A Surrogate Approach

Ordinal outcomes are common in scientific research and everyday practice, and we often rely on regression models to make inference. A long-standing problem with such regression analyses is the lack of effective diagnostic tools for validating model assumptions. The difficulty arises from the fact that an ordinal variable has discrete values that are labeled with, but not, numerical values. The values merely represent ordered categories. In this paper, we propose a surrogate approach to defining residuals for an ordinal outcome Y. The idea is to define a continuous variable S as a "surrogate" of Y and then obtain residuals based on S. For the general class of cumulative link regression models, we study the residual's theoretical and graphical properties. We show that the residual has null properties similar to those of the common residuals for continuous outcomes. Our numerical studies demonstrate that the residual has power to detect misspecification with respect to 1) mean structures; 2) link functions; 3) heteroscedasticity; 4) proportionality; and 5) mixed populations. The proposed residual also enables us to develop numeric measures for goodness-of-fit using classical distance notions. Our results suggest that compared to a previously defined residual, our residual can reveal deeper insights into model diagnostics. We stress that this work focuses on residual analysis, rather than hypothesis testing. The latter has limited utility as it only provides a single p-value, whereas our residual can reveal what components of the model are misspecified and advise how to make improvements.

A Bayesian analysis of quantal bioassay experiments incorporating historical controls via Bayes factors

This paper addresses model-based Bayesian inference in the analysis of data arising from bioassay experiments. In such experiments, increasing doses of a chemical substance are given to treatment groups (usually rats or mice) for a fixed period of time (usually 2 years). The goal of such an experiment is to determine whether an increased dosage of the chemical is associated with increased probability of an adverse effect (usually presence of adenoma or carcinoma). The data consists of dosage, survival time, and the occurrence of the adverse event for each unit in the study. To determine whether such relationship exists, this paper proposes using Bayes factors to compare two probit models, the model that assumes increasing dose effects and the model that assumes no dose effect. These models account for the survival time of each unit through a Poly-k type correction. In order to increase statistical power, the proposed approach allows the incorporation of information from control groups from previous studies. The proposed method is able to handle data with very few occurrences of the adverse event. The proposed method is compared with a variation of the Peddada test via simulation and is shown to have higher power. We demonstrate the method by applying it to the two bioassay experiment datasets previously analyzed by other authors. Copyright © 2017 John Wiley & Sons, Ltd.

A dose-schedule finding design for phase I-II clinical trials

Dose-finding methods aiming at identifying an optimal dose of a treatment with a given schedule may be at a risk of misidentifying the best treatment for patients. In this article we propose a phase I/II clinical trial design to find the optimal dose-schedule combination. We define schedule as the method and timing of administration of a given total dose in a treatment cycle. We propose a Bayesian dynamic model for the joint effects of dose and schedule. The proposed model allows us to borrow strength across dose-schedule combinations without making overly restrictive assumptions on the ordering pattern of the schedule effects. We develop a dose-schedule-finding algorithm to sequentially allocate patients to a desirable dose-schedule combination, and select an optimal combination at the end of the trial. We apply the proposed design to a phase I/II clinical trial of a γ-secretase inhibitor in patients with refractory metastatic or locally advanced solid tumours, and examine the operating characteristics of the design through simulations.

Graphical Models for Ordinal Data

A graphical model for ordinal variables is considered, where it is assumed that the data are generated by discretizing the marginal distributions of a latent multivariate Gaussian distribution. The relationships between these ordinal variables are then described by the underlying Gaussian graphical model and can be inferred by estimating the corresponding concentration matrix. Direct estimation of the model is computationally expensive, but an approximate EM-like algorithm is developed to provide an accurate estimate of the parameters at a fraction of the computational cost. Numerical evidence based on simulation studies shows the strong performance of the algorithm, which is also illustrated on data sets on movie ratings and an educational survey.

Estimating the marginal effect of socioeconomic factors on the demand of specialty drugs

Given the growing importance and role of drugs in the treatment of diseases, as well as replacement of them rather than expensive and often unsafe procedures, study of socioeconomicfactors affecting future demand for them seems necessary.we seek to examine the extent of to which socioeconomic factors affect specialty medicine use by the patients.using data from questionnaires completed by 280 patients with multiple sclerosis, hemophilia, thalassemia, and chronic kidney disease, we estimate marginal effect of significant variables in probit model.We found that the need for the patient(ME = 0.858), deterioration of the patient (ME = -0.001), household size (ME = 0.0004), House Ownership (ME = -0.002), gender (ME = -0.04), income (ME = -0.0007), education (ME = -0.0021) and job (ME = -0.0021) are significant variables affecting demand for specialty drugs. We conclude that it can be programmed to promote and protect the welfare of patients by specific factors such as income, and largely affect the demand of medication and medical services. Therefore economic aid to these patients should not be limited only to medical subsidies, especially in patients with MS, income and welfare can reduce drug demand.

Variance-components methods for linkage and association analysis of ordinal traits in general pedigrees

Many complex human diseases such as alcoholism and cancer are rated on ordinal scales. Well-developed statistical methods for the genetic mapping of quantitative traits may not be appropriate for ordinal traits. We propose a class of variance-component models for the joint linkage and association analysis of ordinal traits. The proposed models accommodate arbitrary pedigrees and allow covariates and gene-environment interactions. We develop efficient likelihood-based inference procedures under the proposed models. The maximum likelihood estimators are approximately unbiased, normally distributed, and statistically efficient. Extensive simulation studies demonstrate that the proposed methods perform well in practical situations. An application to data from the Collaborative Study on the Genetics of Alcoholism is provided.

A latent model approach to define event onset time in the presence of measurement error

For progressive diseases, it is often not so straightforward to define an onset time of certain disease condition due to disease fluctuation and clinical measurement variation. When a disease onset is claimed through the first presence of some clinical event which is subject to large measurement error, such onset time could be difficult to interpret if patients can often be seen to "recover" from the disease condition automatically. We generalize the traditional event onset time concept to control the recovery probability through the use of a stochastic process model. A simulation algorithm is provided to evaluate the recovery probability numerically. Bayesian latent residuals are developed for model assessment. This methodology is applied to define a new postural instability onset time measure using data from a Parkinson's disease clinical trial. We show that our latent model not only captures the essential clinical features of a postural instability process, but also outperforms independent probit model and random effects model. A table of estimated recovery probabilities is provided for patients under various baseline disease conditions. This table can help physicians to determine the new postural instability onset time when different thresholds of estimated recovery probability are used in clinical practice.