• Title/Summary/Keyword: Probit Regression Model

Search Result 37, Processing Time 0.027 seconds

A Bayesian Variable Selection Method for Binary Response Probit Regression

  • Kim, Hea-Jung
    • Journal of the Korean Statistical Society
    • /
    • v.28 no.2
    • /
    • pp.167-182
    • /
    • 1999
  • This article is concerned with the selection of subsets of predictor variables to be included in building the binary response probit regression model. It is based on a Bayesian approach, intended to propose and develop a procedure that uses probabilistic considerations for selecting promising subsets. This procedure reformulates the probit regression setup in a hierarchical normal mixture model by introducing a set of hyperparameters that will be used to identify subset choices. The appropriate posterior probability of each subset of predictor variables is obtained through the Gibbs sampler, which samples indirectly from the multinomial posterior distribution on the set of possible subset choices. Thus, in this procedure, the most promising subset of predictors can be identified as the one with highest posterior probability. To highlight the merit of this procedure a couple of illustrative numerical examples are given.

  • PDF

The Effect of Bribery on Firm Innovation: An Analysis of Small and Medium Firms in Vietnam

  • NGUYEN, Toan Ngoc
    • The Journal of Asian Finance, Economics and Business
    • /
    • v.7 no.5
    • /
    • pp.259-268
    • /
    • 2020
  • This study aims to provide empirical evidence on the causal relationship between bribery and firm innovation. To this end, we use a micro-dataset of small and medium firms in Vietnam surveyed in 2015. Given the binary nature of the dependent variable, a simple probit regression model is employed. However, as bribery variable is potentially endogenous, a simple probit regression may give biased estimates. We deal with the potential endogeneity by making use of the bivariate probit model. A property of the bivariate probit model is that it can produce efficient estimates of a typical probit model with endogenous binary explanatory variable. A Hausman-like likelihood ratio test is implemented following the estimation to test the existence of endogeneity. We find that bribery significantly undermines firm innovation. Also, firms run by household appear less innovative. The probability of innovation diminishes significantly if firm owners or managers have previous experience in firm products. As expected, larger firms seem to be more innovative. Exporters tend to be more innovative compared to non-exporters. Our findings provide support to the hypothesis that bribery is detrimental to firm innovation and, thus, innovation may be a mediating channel, through which, bribery impedes firm long-term performance.

Sampling Based Approach to Bayesian Analysis of Binary Regression Model with Incomplete Data

  • Chung, Young-Shik
    • Journal of the Korean Statistical Society
    • /
    • v.26 no.4
    • /
    • pp.493-505
    • /
    • 1997
  • The analysis of binary data appears to many areas such as statistics, biometrics and econometrics. In many cases, data are often collected in which some observations are incomplete. Assume that the missing covariates are missing at random and the responses are completely observed. A method to Bayesian analysis of the binary regression model with incomplete data is presented. In particular, the desired marginal posterior moments of regression parameter are obtained using Meterpolis algorithm (Metropolis et al. 1953) within Gibbs sampler (Gelfand and Smith, 1990). Also, we compare logit model with probit model using Bayes factor which is approximated by importance sampling method. One example is presented.

  • PDF

Bayesian ordinal probit semiparametric regression models: KNHANES 2016 data analysis of the relationship between smoking behavior and coffee intake (베이지안 순서형 프로빗 준모수 회귀 모형 : 국민건강영양조사 2016 자료를 통한 흡연양태와 커피섭취 간의 관계 분석)

  • Lee, Dasom;Lee, Eunji;Jo, Seogil;Choi, Taeryeon
    • The Korean Journal of Applied Statistics
    • /
    • v.33 no.1
    • /
    • pp.25-46
    • /
    • 2020
  • This paper presents ordinal probit semiparametric regression models using Bayesian Spectral Analysis Regression (BSAR) method. Ordinal probit regression is a way of modeling ordinal responses - usually more than two categories - by connecting the probability of falling into each category explained by a combination of available covariates using a probit (an inverse function of normal cumulative distribution function) link. The Bayesian probit model facilitates posterior sampling by bringing a latent variable following normal distribution, therefore, the responses are categorized by the cut-off points according to values of latent variables. In this paper, we extend the latent variable approach to a semiparametric model for the Bayesian ordinal probit regression with nonparametric functions using a spectral representation of Gaussian processes based BSAR method. The latent variable is decomposed into a parametric component and a nonparametric component with or without a shape constraint for modeling ordinal responses and predicting outcomes more flexibly. We illustrate the proposed methods with simulation studies in comparison with existing methods and real data analysis applied to a Korean National Health and Nutrition Examination Survey (KNHANES) 2016 for investigating nonparametric relationship between smoking behavior and coffee intake.

A Bayesian inference for fixed effect panel probit model

  • Lee, Seung-Chun
    • 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.

Influence of Credit on the Income of Households Borrowing from Banks: Evidence from Vietnam Bank for Agriculture and Rural Development, Kien Giang Province

  • Quang Vang, DANG;Viet Thanh Truc, TRAN;Hieu, PHAM;Van Nam, MAI;Quoc Duy, VUONG
    • The Journal of Asian Finance, Economics and Business
    • /
    • v.10 no.2
    • /
    • pp.257-265
    • /
    • 2023
  • This paper investigates the determinants of credit accessibility and the effect of credit on the income of farm households borrowing from Vietnam Bank for Agriculture and Rural Development, Giong Rieng District Branch, Kien Giang Province. Based on the primary data of 200 farming households who are the customer of the bank, the study applied the Probit regression model to examine determinant factors of credit accessibility of farm households and employed the Propensity score matching method to investigate the impact of credit on households' income. The findings of the Probit regression shown that three independent variables that significantly influence the access to credit of households are household size, income source, and farm size. Besides that, the Propensity score matching method results showed a difference of 23.799 million VND/year between the income of borrowing households and that of non-borrowing households at the significance level of 1%. The difference in the imcome from the interval and central matching methods are VND 24.700 million VND/year and VND 24.633 million VND/year, respectively. Given empirical findings suggetsted that several recommendations to increase the credit accessibility of farm households, thereby creating favorable conditions for improving their income.

Assessing Public Attitude for Multifunctional Roles of the U.S. Agriculture Using a Bivariate Ordered Probit Model (Bivariate Ordered Probit 모형을 이용한 미국 농업의 다원적 기능에 대한 소비자 인식분석)

  • Han, Jung-Hee;Moon, Wan-Ki;Cho, Yong-Sung
    • 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.

  • PDF

Determinants of Accounting Policy for R&D Costs (연구개발에 대한 회계정책 결정요인 분석)

  • 조성표
    • Journal of Technology Innovation
    • /
    • v.5 no.1
    • /
    • pp.67-89
    • /
    • 1997
  • This study investigates the factors determining accounting method for R&D costs (capitalizevs. expense) in Korea. Using agency theory and other economic factors, probit and regression model have been developed to distinguish between firms choosing different accounting alternatives for R&D costs. The results are consistent to debt contract, R&D burden and regulation hypotheses both in probit and regression analysis. The size variable has opposite sign in univariate t-test and probit analysis, which may be due to the differences of political environment between Korea and the US. Generally, the results are consistent to those of previous research. The evidence suggests that larger firms with higher leverage and larger burden of R&D costs are more likely to capitalize R&D costs, while regulated firms are more likely to expense R&D costs.

  • PDF

Binary regression model using skewed generalized t distributions (기운 일반화 t 분포를 이용한 이진 데이터 회귀 분석)

  • Kim, Mijeong
    • The Korean Journal of Applied Statistics
    • /
    • v.30 no.5
    • /
    • pp.775-791
    • /
    • 2017
  • We frequently encounter binary data in real life. Logistic, Probit, Cauchit, Complementary log-log models are often used for binary data analysis. In order to analyze binary data, Liu (2004) proposed a Robit model, in which the inverse of cdf of the Student's t distribution is used as a link function. Kim et al. (2008) also proposed a generalized t-link model to make the binary regression model more flexible. The more flexible skewed distributions allow more flexible link functions in generalized linear models. In the sense, we propose a binary data regression model using skewed generalized t distributions introduced in Theodossiou (1998). We implement R code of the proposed models using the glm function included in R base and R sgt package. We also analyze Pima Indian data using the proposed model in R.

A Bayesian Method for Narrowing the Scope fo Variable Selection in Binary Response t-Link Regression

  • Kim, Hea-Jung
    • Journal of the Korean Statistical Society
    • /
    • v.29 no.4
    • /
    • pp.407-422
    • /
    • 2000
  • This article is concerned with the selecting predictor variables to be included in building a class of binary response t-link regression models where both probit and logistic regression models can e approximately taken as members of the class. It is based on a modification of the stochastic search variable selection method(SSVS), intended to propose and develop a Bayesian procedure that used probabilistic considerations for selecting promising subsets of predictor variables. The procedure reformulates the binary response t-link regression setup in a hierarchical truncated normal mixture model by introducing a set of hyperparameters that will be used to identify subset choices. In this setup, the most promising subset of predictors can be identified as that with highest posterior probability in the marginal posterior distribution of the hyperparameters. To highlight the merit of the procedure, an illustrative numerical example is given.

  • PDF