무위험단기이자율 대용치의 안정성과 이자율기간구조모형과의 양립성 분석

김태형(Tae Hyung Kim),박정민(Jeong min Park) THE KOREAN ECONOMIC SOCIETY 2015 JOURNAL OF ECONOMIC THEORY AND ECONOMETRICS Vol.26 No.1

본 연구에서는 단기이자율 확률과정의 안정성의 특성을 규명하고 이를 통해 단기이자율의 동태적인 안정성의 특성이 기존 이자율기간구조모형의 가정과 부합하는지를 살펴보고자 한다. 단기이자율 확률과정 안정성에 대한 Conley et al. (1997)의 연구를 확장한 수준효과를 포함하는 일반적인 확률변동성모형을 이용하여 안정성을 특징짓는 수준효과의 크기를 식별하고자 하였다. 기존 단기이자율 확률변동성모형의 한계를 극복하는 일반적인 단기이자율 확률변동성모형 추정을 위해 효율적인 MCML추정법을 이용하였으며, 안정성을 특징짓는 수준효과의 크기에 대한통계적인추론을위해보조파티클필터(auxiliary particle filter)를 통해 얻은 PIT(probability integral transform)를 표준정규분포로 역변환한의 사표준 예측오차를 이용한 모형진단과 모형적합성 비교를 하였다.다양한 단기이자율 대용치들에 대한 실증분석 결과, 3개월 만기 미재무부채권 수익률과 한국의 익일물 콜금리는 ATSM 및 QTSM 등의 기존 이자율기간구조모형과 부합하는 'drift-induced stationarity'의 특성을 가지는 반면, 1개월 만기유로달러이자율, 한국의 잔존만기3개월국고채, MMF 7일물, 91일물CD, 91일물 CP 수익률은 'volatility-induced stationarity'의 특성을 가지는 것으로 나타났다. 이와 같은 결과는 단기이자율 대용치의 안정성의 특성을 충분히 고려하지 않고'drift-induced stationarity'를 가정하는 기존이론모형을 이용하는 경우 파생상품가격결정과 리스크관리에 심각한 문제가 발생할 수 있음을 시사한다. By building on the work of Conley et al. (1997), we investigate the stationarity of riskless short-term interest rate processes, analyzing generalized stochastic volatility models with level effects and examine the compatibility of stationarity of short-term interest rates with the popular dynamic term structure of models of interest rates, such as ATSM and QTSM. We extend extant stochas-tic volatility models with level effects crucial in characterizing the stationarity of a continuous time stochastic process, estimate the extended models using an ef-ficient simulation-based MCML(Monte Carlo Maximum Likelihood) estimation method using importance sampling and implement model diagnostics using the inverse of standard normal distribution of the dynamic probability integral trans-form obtained via an auxiliary particle filter. Empirical estimation results indi-cate that TB3M and Call1d exhibit drift-induced stationarity compatible with both ATSM and QTSM, and that ED1M, KTB3M, MMF7d, CD91d and CP91d are of volatility-induced stationarity. Consequently, the results imply that, with-out careful consideration for the nature of stationarity of a short-term interest rate, indiscriminate application of theoretical models assuming the drift-induced stationarity of short-term interest rates may cause serious failure in derivative pricing and risk management.

On Extraction of Time-varying Mean Wind Speed from Wind Record Based on Stationarity Index

Jun Chen,Min Wu 한국기상학회 2012 Asia-Pacific Journal of Atmospheric Sciences Vol.48 No.3

We have proposed in a previous study a non-stationary wind model to represent the typhoon record as a summation of a time-varying mean wind speed (TVM) and a stationary turbulence. This note further suggests a quantitative scheme, rather than the previous qualitative method, to find the best TVM for any given wind record. Trial TVMs are first extracted from the wind record by a data-processing technique named empirical mode decomposition. For each TVM, its corresponding turbulent component is computed by removing the TVM from the original wind record, and the degree of stationarity of the turbulence component is checked. The best TVM is taken as the one that leads to the maximum degree of stationarity. The degree of stationarity of turbulence is quantified by two indicators: β the ratio of horizontal wind variability and wind speed; and γ the ratio of friction velocity at different Reynolds averaging periods. The applicability of the suggested scheme is validated with 550 typhoon and 3300 monsoon records of 10 minute duration and at different measurement heights. Threshold values for the two stationary indicators β and γ are determined using field measurements and their sensitivities to the Reynolds averaging periods are discussed. Observations in this study demonstrate that the suggested scheme is proper for finding the TVM of a wind record. For a stationarity quantification of 10 minute duration record, the γindicator with 30 second Reynolds averaging period is recommended. We have proposed in a previous study a non-stationary wind model to represent the typhoon record as a summation of a time-varying mean wind speed (TVM) and a stationary turbulence. This note further suggests a quantitative scheme, rather than the previous qualitative method, to find the best TVM for any given wind record. Trial TVMs are first extracted from the wind record by a data-processing technique named empirical mode decomposition. For each TVM, its corresponding turbulent component is computed by removing the TVM from the original wind record, and the degree of stationarity of the turbulence component is checked. The best TVM is taken as the one that leads to the maximum degree of stationarity. The degree of stationarity of turbulence is quantified by two indicators: β the ratio of horizontal wind variability and wind speed; and γ the ratio of friction velocity at different Reynolds averaging periods. The applicability of the suggested scheme is validated with 550 typhoon and 3300 monsoon records of 10 minute duration and at different measurement heights. Threshold values for the two stationary indicators β and γ are determined using field measurements and their sensitivities to the Reynolds averaging periods are discussed. Observations in this study demonstrate that the suggested scheme is proper for finding the TVM of a wind record. For a stationarity quantification of 10 minute duration record, the γindicator with 30 second Reynolds averaging period is recommended.

표면근전도 신호의 정상성 검사를 위한 Run-검증과 RA-검증의 정확도 분석

이진(Jin Lee) 대한전기학회 2014 전기학회논문지 Vol.63 No.2

Most of the statistical signal analysis processed in the time domain and the frequency domain are based on the assumption that the signal is weakly stationary(wide sense stationary). Therefore, it is necessary to know whether the surface EMG signals processed in the statistical basis satisfy the condition of weak stationarity. The purpose of this study is to analyze the accuracy of the Run-test, modified Run-test, RA(reverse arrangement)-test, and modified RA-test for assessing surface EMG signal stationarity. Six stationary and three non-stationary signals were simulated by using sine wave, AR(autoregressive) modeling, and real surface EMG. The simulated signals were tested for stationarity using nine different methods of Run-test and RA-test. The results showed that the modified Run-test method2 (mRT2) classified exactly the surface EMG signals by stationarity with 100% accuracy. This finding indicates that the mRT2 may be the best way for assessing stationarity in surface EMG signals.

표면근전도 신호의 정상성 검사를 위한 수정된 Run-검증과 RA-검증에 최적인 신호분할 길이

이진(Jin Lee) 대한전기학회 2014 전기학회논문지 Vol.63 No.8

Most of the statistical signal analysis processed in the time domain and the frequency domain are based on the assumption that the signal is weakly stationary(wide sense stationary). Therefore, it is necessary to know whether the surface EMG signals processed in the statistical basis satisfy the condition of the weak stationarity. The purpose of this study is to find optimal segment length of surface EMG signal for assessing stationarity with the modified Run-test and RA-test. Ten stationary surface EMG signals were simulated by AR(autoregressive) modeling, and ten real surface EMG signals were recorded from biceps brachii muscle and then modified to have non-stationary structures. In condition of varying segment length from 20ms to 100ms, stationarity of the signals was tested by using six different methods of modified Run-test and RA-test. The results indicate that the optimal segment length for the surface EMG is 30ms~35ms, and the best way for assessing surface EMG signal stationarity is the modified Run-test (Run2) method using this optimal length.

시계열 자료의 안정성을 고려한 항공수요 계량경제모형 개발

박재성,김병종,김원규,장은혁 대한교통학회 2016 大韓交通學會誌 Vol.34 No.1

Air transportation demand is consistently increasing in Korea due to economic growthand low cost carriers. For this reason, airport expansion plans are being discussed in Korea. Therefore, it is essential to forecast reliable air transportation demand with adequatemethods. However, most of the air transportation demand models in Korea has beendeveloped by simple regression analysis with several dummy variables. Simple regressionanalysis may occur spurious regression which means between explanatory variables anddependent variable do not have direct causal relationship, yet it may be wrongly inferredthat they do, due to trend of variables seems similar. In this paper, we developedeconometric model for air transportation demand based on stationarity in time-series data. Unit root test and co-integration test are used for testing hypothesis of stationarity. 우리나라 항공 여객수요는 2014년 기준 국제선 5,700만명, 국내선 2,400만명에 도달하였으며, 지속적인 증가 추세를 보일 것으로 예상되고 있다. 이에 따른 국내 공항시설들의 확충 계획이 활발히 진행되고 있으며, 이를 위해 선행적으로 항공수요 예측을위한 모형 개발이 필요하다. 우리나라에서는 국내총생산을 설명변수로 한 계량경제모형을 주로 항공수요 모형으로 이용하고 있으며, 시계열 자료의 안정성을 고려하지 않을 때 발생하는 허구적 회귀 현상에 대한 많은 논의가 이루어지지 않은 상태이다. 본연구에서는 시계열 자료의 안정성을 고려한 항공수요 계량경제모형을 개발하였다. 시계열 자료의 특성을 검정하기 위한 단위근 검정과 변수들 간의 장기균형관계를 분석하기 위한 공적분 검정에 대한 이론적 고찰을 수행하였다. 마지막으로, 시계열 자료의 안정성을 고려한 항공수요 계량경제모형 개발 프로세스를 정립하였다. 정립된 프로세스의적용 가능성을 검증하기 위해 제주공항 국내선 수요를 대상으로 항공수요 모형을 산정하였다. 수요 모형의 설명변수는 국내총생산과 항공요금지수를 이용하였으며, 기존 항공수요 계량경제모형에서 발생하는 문제점을 해소한 것으로나타났다.

Long-run Variance Estimation for Linear Processes Under Possible Degeneracy

이진(Jin Lee) THE KOREAN ECONOMIC SOCIETY 2010 JOURNAL OF ECONOMIC THEORY AND ECONOMETRICS Vol.21 No.1

We analyze the asymptotic behavior of the long-run variance estimator for linear processes under degeneracy, where the spectral density function near the origin equals to zero. Given degeneracy which typically arises from over-differencing, standard results in the literature of heteroskedasticity and autocorrelation consistent (HAC) estimation are invalid. We provide asymptotic distribution of the long-run variance estimator from long term trends in linear processes. Further, we propose a test statistic to testing degeneracy, which achieves asymptotic normality. Our test is directly applied to testing for trend stationarity. Under the null of trend stationarity, the spectrum near the origin for the differenced process becomes zero. On the other hand, under the alternative of difference stationarity, the spectrum becomes strictly positive at the zero frequency. It is found that, depending on the signal-to-ratio, our test has significant power advantages over the KPSS test. Thus, the proposed test becomes an useful complement to the KPSS test

Long-run Variance Estimation for Linear Processes Under Possible Degeneracy

이진 한국계량경제학회 2010 계량경제학보 Vol.21 No.1

We analyze the asymptotic behavior of the long-run variance estimator for linear processes under degeneracy, where the spectral density function near the origin equals to zero. Given degeneracy which typically arises from over-differencing, standard results in the literature of heteroskedasticity and autocorrelation consistent (HAC) estimation are invalid. We provide asymptotic distribution of the long-run variance estimator from long term trends in linear processes. Further, we propose a test statistic to testing degeneracy, which achieves asymptotic normality. Our test is directly applied to testing for trend stationarity. Under the null of trend stationarity, the spectrum near the origin for the differenced process becomes zero. On the other hand, under the alternative of difference stationarity, the spectrum becomes strictly positive at the zero frequency. It is found that, depending on the signal-to-ratio, our test has significant power advantages over the KPSS test. Thus, the proposed test becomes an useful complement to the KPSS test

Improving empirical size of the KPSS test of stationarity

InChoi 한국계량경제학회 2009 JOURNAL OF ECONOMIC THEORY AND ECONOMETRICS Vol.20 No.1

This note proposes a new testing procedure that can alleviate the size prob-Lem associated with semiparametric tests of stationarity. The note is focused on The test by Kwiatkowski, Phillips, Schmidt and Shin (1992) considering its pop-ularity in the literature. The testing procedure of this note employs sample-split and the Bonferronitest. The sample is split into two parts, one corresponding to the odd index and the other to the even index, and the KPSS test is applied to each subsample. The two KPSS tests are then combined using the Bonfer-roni principle. Simulation results demonstrate that this procedure significantly reduces the size distortion of the KPSS test.

Improving empirical size of the KPSS test of stationarity

최인 한국계량경제학회 2009 계량경제학보 Vol.20 No.1

This note proposes a new testing procedure that can alleviate the size prob-Lem associated with semiparametric tests of stationarity. The note is focused on The test by Kwiatkowski, Phillips, Schmidt and Shin (1992) considering its pop-ularity in the literature. The testing procedure of this note employs sample-split and the Bonferroni test. The sample is split into two parts, one corresponding to the odd index and the other to the even index, and the KPSS test is applied to each subsample. The two KPSS tests are then combined using the Bonfer-roni principle. Simulation results demonstrate that this procedure significantly reduces the size distortion of the KPSS test.

Detection of Climate Non Stationarity of Indian Rainfall Using Innovative Trend Family of Techniques

Arathy Nair GR,Adarsh S.,Anishka PS,Celina Thomas,Aiswarya K Ajith,Amalenthu AV 대한토목학회 2024 KSCE Journal of Civil Engineering Vol.28 No.6

The hydrological cycle is significantly impacted by climatic changes, and understanding such changes using statistical or graphical methods is essential for proper management of water resources. This study performs the applications of two most recently proposed variants of popular Sen’s Innovative Trend Analysis (ITA) methods namely Innovative Polygonal Trend Analysis (IPTA) and Innovative Trend Pivot Analysis (ITPA) for analysing the temporal trend of rainfall data of India. The rainfall data of All India along with five Homogeneous regions spanning from 1871 − 2016, are considered for this study. In order to determine the transition of changes throughout months and seasons, the trend length and trend slope were computed, which explicitly demonstrated a climatic shift in the rainfall of the Indian main land. The IPT and ITP analyses were carried out on both arithmetic mean (AM) and standard deviation (SD) based frameworks and SD of the data is found to be more decisive for monthly and seasonal rainfall over Indian regions in inducing climate non stationarity. The Central Northeast and North East regions show vulnerability to changing climate in rainfall magnitude and variability, while North West and West Central regions brings more risk as captured by ITPA method.