Can Lessons Learned from Past Economic Crises Help Predict Future Economic Crises?

한치록,신관호 한국계량경제학회 2022 계량경제학보 Vol.33 No.2

Based on experience of Korea’s two recent economic crises in 1997 and 2008, we investigate if lessons learned from past economic crises can help predict future economic crises. Using the least absolute shrinkage and selection operator (lasso)-logit model, we find that the symptoms in the pre-1997 crisis period do not appear before the 2008 crisis. This finding suggests that the 2008 crisis could not be predicted using lessons learned from the precedent crisis. We also attempted to answer an even more hypothetical question of whether the first crisis could have been predicted if lessons from the second crisis had already leaned. Our findings suggest that the 1997 crisis could have been predicted using lessons learned from the 2008 crisis. Overall, our findings imply that factors that cause the future crisis encompass those of the past crisis, but it is difficult to predict a future crisis armed only with experience of a past crisis.

DEPENDENCE OF ECONOMIC GROWTH ON CO2 EMISSIONS

한치록,HYELIM LEE 중앙대학교 경제연구소 2013 Journal of Economic Development Vol.38 No.1

This paper examines the effects of CO2 emissions on GDP by using a dynamic model for panel data from 19 OECD countries. The results indicate a significant decline in the dependence of economic growth on pollution, suggesting technological progress toward economic growth with less pollution, and providing indirect empirical support for the environmental Kuznets curve hypothesis.

패널자료에서 외생성과 인과성

한치록 한국보건사회연구원 2010 한국복지패널 학술대회 논문집 Vol.3 No.-

ㆍ 패널 모형에서 누락변수 문제는 개별효과를 포함시킴으로써 어느 정도 해결됨 ㆍ 패널 모형에서 Simultaneity로 인한 내생성은 “과거”를 도구변수로 사용함으로써 해결함 ㆍ 선형모양의 경우 동태적 패널데이타 모형을 사용함으로써 많은 경우 둘 다(누락변수와 내생성) 해결할 수 있음 ㆍ 선형 동태적 패널모형의 경우 exogenous, predetermined, endogenous 설명변수의 의미를 분명히 이해하고 이를 지정할 수 있어야 함 ㆍ 비선형 모형(예: 이항종속변수, Count데이타, Censored 회귀모형 등)은 아직 완전한 이론적 발전이 이루어지지 않았음. 한두 가지 경우를 제외하면 Random effects 모형이나 여타 방법을 사용함으로써 문제를 우회함

Test of Block Zero Restrictions in Factor Loadings

한치록,김덕파 한국계량경제학회 2019 계량경제학보 Vol.30 No.3

As a companion paper to Han and Kim (2019) on testing for block zero restrictions in common factors, this paper proposes a test of block zero restrictions in factor loadings, which have empirical relevance in various topics in economics. The test statistic is constructed using the principal component estimate of factor loadings and has a chi-square distribution asymptotically under the null hypothesis of block zero restrictions. The test is applied to a panel of 132 monthly U.S. macro economic time series, which are classified into three groups. The test results show a multi-level structure in factor loadings.

Can Lessons Learned from Past Economic Crises Help Predict Future Economic Crises?

한치록(Chirok Han),신관호(Kwanho Shin) 한국계량경제학회 2022 JOURNAL OF ECONOMIC THEORY AND ECONOMETRICS Vol.33 No.2

Based on experience of Korea’s two recent economic crises in 1997 and 2008, we investigate if lessons learned from past economic crises can help predict future economic crises. Using the least absolute shrinkage and selection operator (lasso)-logit model, we find that the symptoms in the pre-1997 crisis period do not appear before the 2008 crisis. This finding suggests that the 2008 crisis could not be predicted using lessons learned from the precedent crisis. We also attempted to answer an even more hypothetical question of whether the first crisis could have been predicted if lessons from the second crisis had already leaned. Our findings suggest that the 1997 crisis could have been predicted using lessons learned from the 2008 crisis. Overall, our findings imply that factors that cause the future crisis encompass those of the past crisis, but it is difficult to predict a future crisis armed only with experience of a past crisis.

What Explains Current Account Surplus in Korea?

한치록 ( Han Chirok ),신관호 ( Shin Kwanho ) 대외경제정책연구원 2016 Working Papers Vol.16 No.15

Can Obesity Cause Depression? A Pseudo-panel Analysis

하형석,한치록,김범수 대한예방의학회 2017 예방의학회지 Vol.50 No.4

Objectives: The US ranks ninth in obesity in the world, and approximately 7% of US adults experience major depressive disorder. Social isolation due to the stigma attached to obesity might trigger depression. Methods: This paper examined the impact of obesity on depression. To overcome the endogeneity problem, we constructed pseudo-panel data using the Behavioral Risk Factor Surveillance System from 1997 to 2008. Results: The results were robust, and body mass index (BMI) was found to have a positive effect on depression days and the percentage of depressed individuals in the population. Conclusions: We attempted to overcome the endogeneity problem by using a pseudo-panel approach and found that increases in the BMI increased depression days (or being depressed) to a statistically significant extent, with a large effect size.

경제지표 활용 수요예측모델 연구

박상수,한치록,이홍식 대한산업공학회 2022 대한산업공학회 추계학술대회논문집 Vol.2022 No.11

빅데이터 분석기법에 기초한 가계 부실징후 분석

신관호,한치록 예금보험공사 2022 金融安定硏究 Vol.23 No.2

The most significant risk for the Korean economy is the surge in household debt. By relying on an extensive data analysis technique, this study presents a method of estimating the possibility of a macroeconomic crisis of household insolvency. This study uses the Bank of Korea household debt database based on the credit rating data provided by NICE Investors Service Co. Most existing studies on household debts have analyzed household debt determinants by considering only limited variables. In contrast, this study not only constructs an optimal forecast model through learning and prediction that utilize all available micro variables but also derives a final model using big data techniques that combine various macroeconomic variables. The prediction based on the methodology proposed by this study is marginally superior to the prediction based on a simple random walk. 한국경제에서 가장 큰 리스크 요인은 급증한 가계부채이다. 본 연구는 민간회사인 나이스신용정보의 자료에 기초한 한국은행의 가계부채DB를 빅데이터 분석기법을 이용하여 분석함으로써 거시적인 가계부실 위기 가능성을 추정하는 방법을 제시하였다. 대부분의 기존 가계부채 관련 연구들은 제한된 변수만을 고려하여 가계의 부채결정 요인을 분석하였다. 하지만본 연구는 이용 가능한 모든 미시 변수를 고려하여 학습과 예측을 통해 최적의 예측모형을구축할 뿐 아니라 다양한 거시 경제변수들을 빅데이터 기법을 통해 결합하여 최종적인 모형을 도출한다는 점에서 기존의 접근 방법과 차별성을 가진다. 본 연구의 방법론에 의한 예측은 단순 임의보행에 따른 예측에 비해 근소하게 우월한 것으로 나타났다.

프랜차이즈 가맹점 환경개선 효과의 실증분석

윤기호,한치록 한국산업조직학회 2014 産業組織硏究 Vol.22 No.1

본 논문은 한 프랜차이즈 가맹점포 환경개선(리뉴얼, 이전 또는 확장)의 효과를 실증적으로 분석하여, 이 중 어떤 방식이 가맹점주에게 더 유리한 방식이었는지 살펴본다. 이를 위 해 우선 환경개선의 증분비용 및 증분이익을 구한다. 증분비용은 환경개선시점에 투입되는 회수불가능 한 시설투자비이고, 연간 증분이익은 연간 영업이익 증가액에서 임차보증금 및 권리금 증가액에 대한 이자금액을 차감한 연간 실질이익 증가액이다. 시설투자비를 연간 실 질 이익증가액으로 나눔으로써 경제적 효과를 판단할 수 있는데, 논문에서는 매출액의 시간 추세를 제거한 다음 환경개선으로 인한 실질이익 증가액을 도출한다. 그 결과 리뉴얼보다는 확장이, 그리고 확장보다는 이전이 가맹점주에게 더 유리한 방식이었음을 보인다. 논문은 또한 ‘성향점수 매칭(propensity score matching)’ 방법을 이용하여 성격이 유사한 점포들을 대응시키는 방법으로 점포 고유의 속성을 통제한 후에도 환경개선 유형별 비교에서 동 일한 결론이 성립함을 보인다. This paper performs an empirical analysis on the effects of franchisees` store renovation (renewal, relocation, or expansion) and finds which method of renovation is more favorable to store owners. This paper first calculates the incremental cost and incremental profit of store renovation: The incremental cost is the non-recoverable capital investment on physical facilities at the time of store renovation, whereas the annual incremental profit is the annual increase in the real profit which is obtained by subtracting the annual interest amount of the increased lease deposits and goodwills from the annual increase in the operating profit. The economic effect can be judged by dividing the incremental cost by the annual incremental profit, while eliminating the time-trend effect. This paper shows that the relocation is more favorable than the expansion, which in turn is more favorable than the renewal to the franchisees. This paper also shows that the same conclusion holds even after controlling for the store-specific attributes using the `propensity score matching` method.