• The Korean Journal of Applied Statistics
• /
• v.27 no.6
• /
• pp.923-932
• /
• 2014

The Hurdle model can to analyze zero-inflated count data. This model is a mixed model of the logit model for a binary component and a truncated Poisson model of a truncated count component. We propose a new hurdle model with a general heterogeneous random effects covariance matrix to analyze longitudinal zero-inflated count data using modified Cholesky decomposition. This decomposition factors the random effects covariance matrix into generalized autoregressive parameters and innovation variance. The parameters are modeled using (generalized) linear models and estimated with a Bayesian method. We use these methods to carefully analyze a real dataset.

• Journal of Korea Technology Innovation Society
• /
• v.17 no.3
• /
• pp.449-466
• /
• 2014

There have been various researches on the relationship between a company's R&D investment and the outcome from innovation. However, these studies failed to effectively analyze the decision-making process followed by companies in relation to knowledge production. Especially, in analyzing the patent of companies, the Poisson model has been commonly used, but its limitations have been pointed out. In recent years, many studies have adopted negative binomial models, but they still pose limitations in analyzing the selection process. This paper proposed a hurdle negative binomial model to effectively reflect the company's decision embedded within patent information and conduct an empirical analysis on a survey of businesses' activities. In particular, the study analyzed the selection process of companies in determining the number of patents. As a result of estimation, the presence of over-dispersion was identified. In addition, the Wald-test confirmed that setting up of hurdles was valid, and there was a difference between the results of hurdle models and those of general negative binomial settings.

• Korea journal of population studies
• /
• v.30 no.3
• /
• pp.107-135
• /
• 2007

This paper uses a static Gamma count model, a traditional hurdle model and an endogenous switching Poisson model, respectively for determining married women's completed fertility rates in Korea. This paper analyzes the impact of household income, women's wage and education, and women's job market participation on the number of children of married women above age 40 and on the expected number of children of women aged below 40. The paper shows that a household income significantly increases the number of children for at least women aged above 40, however, this income effect is disappearing for younger generation. The empirical model suggests that women having a job tend to have fewer children for a group 39 years old and below and find that there is an endogeneity problem between child birth and labor force participation, too. The education level of married women gives a positive effect for giving a birth, itself, while it gives a negative impact on the number of children. Based on the empirical results, it concludes that Becker's Quantity-Quality theory works for Korea, too.

• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1459-1473
• /
• 2016

Both longitudinal data and survival data are collected simultaneously in longitudinal data which are observed throughout the passage of time. In this case, the effect of the independent variable becomes biased (provided that sole use of longitudinal data analysis does not consider the relation between both data used) if the missing that occurred in the longitudinal data is non-ignorable because it is caused by a correlation with the survival data. A joint model of longitudinal data and survival data was studied as a solution for such problem in order to obtain an unbiased result by considering the survival model for the cause of missing. In this paper, a joint model of the longitudinal zero-inflated count data and survival data is studied by replacing the longitudinal part with zero-inflated count data. A hurdle model and proportional hazards model were used for each longitudinal zero inflated count data and survival data; in addition, both sub-models were linked based on the assumption that the random effect of sub-models follow the multivariate normal distribution. We used the EM algorithm for the maximum likelihood estimator of parameters and estimated standard errors of parameters were calculated using the profile likelihood method. In simulation, we observed a better performance of the joint model in bias and coverage probability compared to the separate model.

• Korean small business review
• /
• v.42 no.4
• /
• pp.309-326
• /
• 2020

There often is information asymmetry between start-ups and the investors, which is because start-up companies in the early stages do not have track records. Meanwhile, since the government grants programs go through a fair and the intense competition process, the government grants can provide a more objective information for start-ups in the early stages and perform a signal function that guarantees a company's capabilities and potential. This study confirms the quantitative relationship between government grants and investment attraction by using the hurdler model. We found that, although there is the proportionate relationship between the scale of government grants and that of external funds, more than a certain amount of government grants is required for technology-based start-ups to exceed the stage of attracting their first external funds. Our findings suggest that it is necessary to consider the hurdles structure in the study of signaling theory perspective, as the mechanisms for determining whether or not to attract external funds are different from determining the level of external funds. In addition, differentiated policy support is needed to help early-stage technology start-ups go beyond the threshold of investment attraction-the creation of a 'threshold effect'.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1511-1520
• /
• 2017

The purpose of this study is to analyze military combat training data to improve military operation and training methods and verify required military doctrine. We set the number of combat disabled enemies, which the individual combatants make using their weapons, as the response variable regarding offensive operations from scientific military training data of reinforced infantry battalion. Our response variable has more zero observations than would be allowed for by the traditional GLM such as Poisson regression. We used the zero-inflated regression and the hurdle regression for data analysis considering the over-dispersion and excessive zero observation problems. Our result can be utilized as an appropriate reference in order to verify a military doctrine for small units and analysis of various operational and tactical factors.

• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.131-143
• /
• 2012

The past researches on roadway segment safety estimation focused on intersections, which are the primary traffic accident regions. The past researches on roadway segments, However, analyzed the effects of certain factors on the traffic accident occurrence rate by organizing the individual geometric structures of the roads, and there is still a dearth of researches on the development of a traffic accident estimation model for rural roadway segments. Therefore, this research focused on rural two-lane and multilane roadway segments and developed traffic accident estimation models through the application of statistical techniques. This is required to explain such high frequency of zero counts in the traffic accident data. In this research, it was found that the Hurdle model is more suitable than the Poisson or negative binomial-regression model for explaining the excess zeros case. In addition, main variables were chosen to estimate their effects on traffic accident occurrence at rural roadway segments, and the safety at such rural roadway segments was estimated. In this research, it was assumed that there are different factors that affect the safety at two-way lane and multilane roadway segments, and a traffic accident estimation model was developed by dividing the two-way lane and multilane roadway segments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.76-91
• /
• 2019

There have been many studies to examine the patterns in innovations reflecting industry-specific characteristics from an evolutionary economics perspective. The purpose of this study is to identify industry-specific differences in product innovation patterns and determinants of innovation performance. For this, Korean manufacturing is classified into high-tech industries and low-tech industries according to technology intensity. It is also pointed out that existing research does not reflect the decision-making process of firms' R&D implementations. In order to solve this problem, this study presents a Heckman sample selection model and a double-hurdle model as alternatives, and analyzes data from 1,637 firms in the 2014 Survey on Technology of SMEs. As a result, it was confirmed that the determinants and patterns of manufacturing in small and medium-size enterprise (SME) product innovation are significantly different between high-tech and low-tech industries. Also, through an extended empirical model, we found that there exist a sample selection bias and a hurdle-like threshold in the decision-making process. In this study, the industry-specific features and patterns of product innovation are examined from a multi-sided perspective, and it is meaningful that the decision-making process for manufacturing SMEs' R&D performance can be better understood.

• Journal of Korean Society of Rural Planning
• /
• v.21 no.2
• /
• pp.137-147
• /
• 2015

In this study, consumers who have experience of visiting Jeongsun Arirang Market has been selected as samples to understand the characteristics of agricultural products purchase. For this, double hurdle model was used in order to resolve sample selection problem and obtain consistent estimator. The key points are the following. First, as the age increases(up to 59.8 years), chances of purchasing the products at traditional market increase as income increases. Second, when the residence area is outside of Gangwon-province, the purchase amount of the products increased compared to those from visitors within the Gangwon province. Also, visitors who use public transportations purchase less products compared to those who use their own car. Third, probability of agricultural products increase as the visitors consider positive effect the product purchase leads to the local farmers. Fourth, if the visitors consider the quality of the agricultural products, probability of purchasing agricultural product at the site increases. However, if the visitors consider the freshness of the agricultural products, the purchase amount rather drops. Fifth, the probability of purchase increases as visitors consider the brand of traditional market.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.9
• /
• pp.427-434
• /
• 2018

As noted by Pavitt (1984) and Malerbar (2002), previous studies have focused on identifying differences in industry characteristics between the machinery industry and other manufacturing industries. This study considered quantitative and qualitative aspects of performance of product innovation in analyzing what factors determine those outcomes. In particular, this study examined stepwise selection processes embedded in innovation activities by applying a hurdle negative binomial model as well as the Heckman two-step selection model. Results show that factors affecting performance improvement and patents differ, and the threshold effect and the intensity effect of innovation were also distinguished. These results imply that the R&D capability should be enhanced and external innovation is required to be effectively embodied in the organization. Furthermore, motivating employees plays a pivotal role in this technology and skill-intensive sector.