• Communications for Statistical Applications and Methods
• /
• v.23 no.2
• /
• pp.179-187
• /
• 2016

The fixed effects panel probit model faces "incidental parameters problem" because it has a property that the number of parameters to be estimated will increase with sample size. The maximum likelihood estimation fails to give a consistent estimator of slope parameter. Unlike the panel regression model, it is not feasible to find an orthogonal reparameterization of fixed effects to get a consistent estimator. In this note, a hierarchical Bayesian model is proposed. The model is essentially equivalent to the frequentist's random effects model, but the individual specific effects are estimable with the help of Gibbs sampling. The Bayesian estimator is shown to reduce reduced the small sample bias. The maximum likelihood estimator in the random effects model is also efficient, which contradicts Green (2004)'s conclusion.

• Communications for Statistical Applications and Methods
• /
• v.21 no.1
• /
• pp.45-60
• /
• 2014

We introduce a MCMC sampling for a generalized linear normal random effects model with the ordered probit link function based on latent variables from suitable truncated normal distribution. Such models have proven useful in practice and we have observed numerically reasonable results in the estimation of fixed effects when the random effect term is provided. Applications that utilize Korean Welfare Panel Study data can be difficult to model; subsequently, we find that an ordered probit model with the random effects leads to an improved analyses with more accurate and precise inferences.

• Journal of Labour Economics
• /
• v.25 no.1
• /
• pp.75-95
• /
• 2002

Using 3 years of panel data on nearly 3,507 households, the Korea Labor Income Panel Survey(KLIPS) data, the authors measure the determinants of poverty and unemployment, and the extents to which poverty influenced unemployment. The probit analysis of unemployment shows that unemployment probability is lower, when male, lower age and is higher, high-school and over junior college, work duration is over 3 years. The probit analysis of poverty shows that poverty probability is lower, when male, higher education level, longer career. specially unemployment and social insurance is determinants of increasing poverty. Bivariate probit model of unemployment and poverty also provides similar findings to those probit analysis and shows an evidence of the influence of unemployment on poverty along with the positive role of social welfare policy such that social welfare receipt reduces the impact of unemployment on poverty.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.210-219
• /
• 2010

Consumers differ in both horizontally and vertically. Market segmentation aims to divide horizontally different (or heterogeneous) consumers into more similar (or homogeneous) small segments. A specific consumer, however, may differ in vertically. He (or she) may belong to a different market segment from another one where he (or she) belonged to before. In consumer panel data, the vertical difference can be observed by his (or her) choice among brand alternatives are changing over time. The consumer's vertical difference has been defined as 'dynamics'. In this research, we have developed a binary probit model with random-walk coefficients to capture the consumer's dynamics. With an application to a consumer panel data, we have examined how have the random-walk coefficients changed over time.

• Korean Journal of Organic Agriculture
• /
• v.17 no.4
• /
• pp.413-439
• /
• 2009

This study conducts a survey and test to understand U.S. public's perception about multifunctionality. The questionnaire suggests seven alternative way of providing questions about intangible benefits provided by agriculture in the U.S. The final questionnaire was administered as an e-mail survey in June 2008 to a nationally representative household panel maintained in the U.S. by the Ipsos Observer. Data analysis shows that 64 percent of respondents considered the multifunctionality of agriculiture as an important issue and 45 percent of respondents were in favor of increasing government expenditure to support farmland preservation. Using Fishbein's multi-attribute model as a theoretical background, this paper develops an empirical model to assess and attributes of multifunctionality. For the analysis, bivariate orderd probit model was set up to reflect respondent's attitude. Regression analyses show that two questions (how much you agree with agriculture's intangible benefit and increasing government expenditure to support agriculture) are shaped by different sets of facts.

• Journal of Environmental Impact Assessment
• /
• v.25 no.2
• /
• pp.124-140
• /
• 2016

Using the Korea Labor Institute Panel Study(KLIPS), this study investigates the impacts of water pollution on life satisfaction in Korea. Panel random-effects ordered probit model is used to consider the ordered property of life satisfaction data and heterogeneity of panel data. The proxy variables to reflect the degree of water pollution are biochemical oxygen demand(BOD) and total phosphorus(TP). In addition to the environmental variables above, other determinants used in various studies on life satisfaction such as economic, social, and demographic characteristics are included. Estimation results show that water pollution is negative and significant for life satisfaction. Other indicators such as income, age, house ownership, gender, education are positively related while urban residence and own business are shown to be negatively related.

• Communications for Statistical Applications and Methods
• /
• v.26 no.3
• /
• pp.315-323
• /
• 2019

Panel data sets have recently been developed in various areas, and many recent studies have analyzed panel, or longitudinal data sets. Often a dichotomous dependent variable occur in survival analysis, biomedical and epidemiological studies that is analyzed by a generalized linear mixed effects model (GLMM). The most common estimation method for the binary panel data may be the maximum likelihood (ML). Many statistical packages provide ML estimates; however, the estimates are computed from numerically approximated likelihood function. For instance, R packages, pglm (Croissant, 2017) approximate the likelihood function by the Gauss-Hermite quadratures, while Rchoice (Sarrias, Journal of Statistical Software, 74, 1-31, 2016) use a Monte Carlo integration method for the approximation. As a result, it can be observed that different packages give different results because of different numerical computation methods. In this note, we discuss the pros and cons of numerical methods compared with the exact computation method.

• Health Policy and Management
• /
• v.19 no.1
• /
• pp.62-80
• /
• 2009

The purpose of this study was to examine the factors influencing the attitude toward the increasing role of private health insurance(PHI). In the Korea Welfare Panel Data 2007, a sample of 1,675 (adjusted by weight value: 1,607) respondents on an opinion on promoting PHI was used in the study. With independent variables including socio-demographic characteristics, health status, health-related behavior, and opinions on welfare service, ordered-probit model was used to analyze the attitude toward PHI. Negative opinion on the increasing role of PHI were responded by 54.6%(n=877) of the respondents, whereas 22.2%(n=373) were positive and 23.2%(n=357) were neutral. Old people, the better off, those with worse self-assessed health status, and those having an experience of health examination tend to have the positive attitude toward the increasing role of PHI. Women, those with chronic diseases or disorders and those who do not agree that comprehensive welfare benefits reduce work incentive showed negative attitude toward PHI. When comparing the needs for PHI before and after medical utilization, ex-ante need tends to strengthen the tendency to support private health insurance. This study will contribute to the discussion on the optimal mix of public and private health insurance in Korea by a better recognition of attitude toward PHI and health care system.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.2
• /
• pp.29-36
• /
• 2022

This study uses the panel probit model to investigate and evaluate the relationship between exchange rate regimes, political stability, and carbon dioxide during currency crises. To understand currency crisis times, we study a panel dataset of seven South Asian nations that contain annual observations from 1996 to 2020. Furthermore, we created the EMPI exchange market pressure indicator to detect crises. Our results strongly suggested that fixed exchange rate is negatively associated with currency crises, with good regulatory quality and better effective governments. Simultaneously, the floating exchange rate is positively related to the currency crises in those countries where the rule of law has less adequately flowed. However, CO₂, exports, and interest rates are buoyantly associated with crises. The floating exchange rate, the rule of law, exports, and interest rate are associated positively and contribute more prone to the crisis episodes. Negatively associated variables contributed less amid crises episodes: fixed exchange rate regime, government effectiveness, and regulatory quality. Meanwhile, CO₂ has a positive relationship with a currency crisis and contributes more likelihood to the probability of a currency crisis. Countries that adopted the fixed exchange rates with effective governments and regulatory quality faced more minor currency crises.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_3
• /
• pp.1293-1302
• /
• 2022

The relationship between homeownership and participation in giving and volunteering overall indicates that homeowners are more likely to give and participate in volunteering organizations than renters. This study compared 'giving and participation in volunteering between homeowners(n=6,078) and renters(3,587) in the 14^th Korean Welfare Panel Survey data collected in 2019. The outcome measure of study is a binary outcome of giving and volunteering participation. This study accounted for a bias arising from selection on observables. Specifically, this study employed a recursive bivariate probit model to simultaneously estimate respondents' participation in giving and volunteering participation and their selection of homeownership. Findings from this study have provided some evidence that homeowners and renters have different behaviors in giving and volunteering participation. Finally, issues relating to homeownership and social outcomes were discussed. Implications for social work practice and research were further discussed.