• International Journal of Human Ecology
• /
• v.4 no.2
• /
• pp.77-87
• /
• 2003

This paper tried to construct statistical and econometric models on the basis of economic theory in order to discuss the issue of statistical efficiency and unbiasedness including the sample selection bias correcting problem. Comparative analytical tool were one stage Tobit of Maximum Likelihood estimation and Heckman's two-step Tobit of Ordinary Least Squares. The results showed that the adequacy of model for the analysis on demand and choice, we believe that there is no big difference in explanatory variables between the first selection model and the second linear probability model. Since the Lambda, the self- selectivity correction factor, in the Type II Tobit is not statistically significant, there is no self-selectivity in the Type II Tobit model, indicating that Type I Tobit model would give us better explanation in the demand for and choice which is less complicated statistical method rather than type II model.

• Korean Management Science Review
• /
• v.31 no.4
• /
• pp.135-150
• /
• 2014

This paper analyzes the operational efficiency of 91 individual retail stores in Seoul by a two-step procedure. In the first step, a data envelopment analysis (DEA) model is used to identify the efficiency scores. Three inputs (store size, number of items, and number of employees) and two outputs (sales and number of customers) are used for the efficiency measurement. In the second step, a Tobit regression model is used to identify the drivers of efficiency. DEA efficiency scores are used to test hypotheses on the impact of five independent variables, namely store age, number of items per store size, number of items per employee, trade area index, and number of competitors. Results of the Tobit analysis show that number of items per store size, number of items per employee, and number of competitors play a significant role in influencing the operational efficiency of retail stores. Managerial implications of the study are discussed.

• International Area Studies Review
• /
• v.13 no.3
• /
• pp.213-238
• /
• 2009

This paper empirically examines effects of exporting on employment over the period 2000-2007 for Korean listed and non-listed manufacturing firms. The paper employs the dynamic panel model of labor demand and controls for simultaneity of the exports and real wages using a two step random effect Tobit-DPD (Dynamic Panel Data) procedure. Our empirical results suggest that surprisingly, there is no robust evidence for employment effects of exporting of Korea's large firms and small-medium sized firms during the sample period after Korean financial crisis. This implies that Korean exporting patterns have been changed in a way that exporting highly capital intensive goods leads to importing more intermediate goods and thus to countervailing the employment effects of exporting. This suggests that expansion of exporting by lowering exporting prices through the bilateral FTA might not be helpful to enhancing employment in Korea.

• Journal of Korea Trade
• /
• v.24 no.7
• /
• pp.29-37
• /
• 2020

Purpose - This paper empirically investigates the relationship between country governance quality and worker remittances from foreign countries. Because remittances can be a source of funds for economic development and smoothing economic crises in developing countries, the related topic has been a concern for policy-makers and academic researchers. This paper divides the motives of remittances into altruistic and investment motives through existing papers, and then considers the governance quality the remittance receiving country as one of the determinants of remittances. Design/methodology - Our empirical model considers whether governance quality can affect the volume of remittances, and uses altruistic and investment factors studied in the literature. To do this, a two-step approach is taken. First, the panel data are examined via pooled OLS, random effects, and Tobit estimation. Second, the paper reduces six governance indicators into one variable, Governance, using the principal component technique (PCA) for a robustness check. Findings - The main findings can be summarized as follows. The negative governance variable in the estimation results shows a lower governance quality that induces workers to send savings to their home countries. This means that a country with poor governance quality seems to have more remittance inflows from abroad. It also reveals that poor governance quality is more relevant to an altruistic motive rather than an investment motive, in general. The positive per capita GDP variable shows the investment motive for developed countries. Originality/value - Existing papers have focused on various factors related to the motives of remittances. However, governance quality effects on remittance inflows have not been fully studied so far. This paper considers governance quality in an estimation equation explicitly as one of the determinants of remittances. This area of study is needed, in theory and empirically, in order to fully understand the relationship between governance and remittances.

• Journal of Korea Technology Innovation Society
• /
• v.19 no.4
• /
• pp.711-735
• /
• 2016

Drug Development is very important for promoting public health and pharmaceutical industry. There has been many studies on the efficiency of drug development, but there are few studies on the drug development R&D performed by government. Since CCR model assumes unidirectional influence of input and output, it is not appropriate to analyze the efficiency of R&D due to the time-lag and spill-over effect. Also, BBC model which assumes variable returns to scale has difficulty in deriving priorities between decision making units. Recently, Range Adjusted Measure (RAM) model has been suggested in R&D efficiency analysis. RAM model measures the efficincy by eliminating inefficiencies under variable returns to scale assumption, and its strong monotonicity enables to provide clear priorities between decision making units. In this study, we analyzed the efficiency of national R&D programs for drug development using the two-step approach, including RAM model and Tobit regression analysis, and discussed major policy implications.