Kyoo-Ho Kang

We investigate the existence and timing of changes in U.S. inflation persistence. To do so, we develop an unobserved components model of inflation with Markov-switching parameters and we measure persistence using impulse response functions based on the model. An important feature of our model is its allowance for multiple regime shifts in parameters related to the size and propa-gation of shocks. Inflation persistence depends on the configuration of these parameters, although it need not change

This study proposes and estimates state‐space models with endogenous Markov regime‐switching parameters. It complements regime‐switching dynamic linear models by allowing the discrete regime to be jointly determined with observed or unobserved continuous state variables. The estimation framework involves a Bayesian Markov chain Monte Carlo scheme to simulate the latent state variable that controls the regime shifts. A simulation exercise shows that neglecting endogeneity leads to biased inferenc

Abstract This study detects a structural break in international consumer price index (CPI) inflation comovement. We estimate the dynamic common factor models with unknown breakpoints of cross-country inflation rates and global price index of all commodities. We identify two global factors from the models: a commodity global factor and a noncommodity global factor. The former is a common factor between national inflation rates and commodity price index growth; the latter is a common factor among

Background/Aims: status in patients who underwent endoscopic removal of gastric hyperplastic polyps. Methods: eradication was assessed by histology and rapid urease test or urea breath test, at least 4 weeks after the completion of eradication treatment. At follow-up, the recurrence of gastric polyp was evaluated via esophagogastroduodenoscopy. Results: infection status was a significant risk factor for gastric polyp recurrence after endoscopic removal. Conclusions: infection status is significa

본 연구는 우리나라 주택담보대출의 베이지안 머신 러닝 분포예측 기법을 제시하고 실제 예측결과를 분석한다. 주택담보대출 예측은 크게 세 단계로 이루어진다. 첫 번째 단계는 변수선택이다. 다수의 잠재적인 예측변수 중에서 주택담보대출 자료만을 이용한 일변수 모형보다 정확한 표본외 주택담보대출 예측력을 나타내는 ADL 모형의 예측변수만을 선택한다. 두 번째 단계에서는 선택된 예측변수를 대상으로 다수의 시계열 예측모형을 추정하고, 표본외 예측력을 기준으로 모형별 가중치를 산출한다. 마지막으로 예측 조합인데, 모형별 사후예측분포에 가중치를 부여한 예측분포를 샘플링한다. 2007년 12월부터 2016년 10월까지의 월별자료를 분석한 결과, 예측변수 및 모형 불확실성이 존재할 뿐만 아니라 시변하였다. 최근 주택담보대출 급등세는 수도권 아파트 매매가격지수가 주도적인 역할을 했으며, 올해 초 14%까지 달했던 주택담보대출 증가율은 2016년 11월 이후 차츰 둔화되어 10% 내외의 증가율을 보일 것으

The Kim filter (KF) approximation is widely used for the likelihood calculation of dynamic linear models with Markov regime-switching parameters. However, despite its popularity, its approximation error has not yet been examined rigorously. Therefore, this study investigates the reliability of the KF approximation for maximum likelihood (ML) and Bayesian estimations. To measure the approximation error, we compare the outcomes of the KF method with those of the auxiliary particle filter (APF). Th

Abstract This study introduces a multivariate regression model with endogenous Markov regime-switching parameters, in which the regression disturbances and regime switches are allowed to be instantaneously correlated. For the estimation and model comparison, we develop a posterior sampling algorithm for the parameters, regimes, and marginal likelihood calculation. We demonstrate the reliability of the proposed method using simulation and empirical studies. The simulation study shows that neglect

Abstract The literature on using yield curves to forecast recessions customarily uses 10‐year–3‐month Treasury yield spread without verification on the pair selection. This study investigates whether the predictive ability of spread can be improved by letting a machine learning algorithm identify the best maturity pair and coefficients. Our comprehensive analysis shows that, despite the likelihood gain, the machine learning approach does not significantly improve prediction, owing to the estimat

We propose a new dynamic Nelson–Siegel yield curve model in which two time-varying factor-specific decay parameters govern the slope and curvature factor loadings, and the factor shock variance–covariance (SV) follows a stochastic inverse Wishart process. The proposed model is compared with simpler specifications in terms of statistical and economic criteria to demonstrate the importance of jointly incorporating time-varying factor loadings and SV. We examine the out-of-sample yield curve densit