명절효과 사전조정을 위한 파급유형에 관한 연구

김기환,신현규,Kim, Kee-Whan,Shin, Hyun-Gyu 한국통계학회 2010 응용통계연구 Vol.23 No.2

본 연구에서는 계절조정을 위한 사전조정 단계 중 명절효과 조정방법에 이용되는 파급유형을 소개하고, 기존의 파급유형보다 다양하고 유연한 형태를 갖는 새로운 파급유형을 제안하였다. 그리고 명절 전후의 시계열 파급형태가 같지 않다는 현실적인 가정 하에 기존의 파급유형과 새로 제안한 파급유형을 비교하였다. 비교연구에서는 기존의 것과 새로 제안된 것으로 가능한 모든 파급유형을 구성한 후 RegARIMA로 효과를 추정하였으며 추정과정에는 우리나라의 산업별 생산지수와 출하지수 자료를 사용하였다. In this study, we introduce filters that used for the prior adjustment of the holiday effect in seasonal adjustment. And we propose new filters having more various and flexible patterns than conventional ones. Under the practical assumption that patterns of effects before and after the holiday are different, we compare adjustment effect of the proposed filters and the existing ones. In comparison study, we estimate the effect from all possible combinations of shapes of filter by RegARIMA. And then, to adjust holiday effect, we apply the estimated results to time series data of industrial production and shipment index data in South Korea.

혈관 및 장관 평활근의 K-경축 발생기전

김기환,황상익,남기용,Kim, Ki-Whan,Hwang, Sang-Ik,Nam, Kee-Yong 대한생리학회 1979 대한생리학회지 Vol.13 No.1

The activation mechanism of K-induced contracture was studied in renal vascular muscle which does not generate an action potential readily and in taenia coli which generates a spike potential spontaneously. Helical strips of arterial muscle from rabbit renal arteries and longitudinal strips of taenia coli from guinea-pig's colons, respectively, were prepared. All experiments were performed in Tris-buffered Tyrode solution which was aerated with 100% $O_2$ and kept $35^{\circ}C$. Renal arterial muscles developed the contracture rapidly, which was composed of a small phasic and a large tonic components, when exposed to a 40 mM K-Tyrode solution. In the absence of external $Ca^{++}$, however, no K-contracture appeared. The contracture induced by K-depolarization was abolished by the treatment with verapamil, which is known to be a selective $Ca^{++}-blocker$ through potential-sensitive $Ca^{++}-channel$. K-contracture of taenia coli showed the contracture composed of a large phasic and a small tonic components. In the $Ca^{++}-free$ Tyrode solution, only the tonic component was abolished and almost no change in the phasic component was observed. The amplitude of tonic component was dependent on the external $Ca^{++}$; The tonic component increased dose-dependently by a stepwise increase of the external $Ca^{++}$, and this component decreased in parallel with the increase of verapamil in the external medium. The results of this experiment suggest that K-contracture of rabbit renal artery is the direct result of the influx of the external $Ca^{++}$, while that of taenia coli is the result of both $Ca^{++}$ influx and the release of sequestered $Ca^{++}$.

적출 유두근에서 근육길이에 따른 계단현상 및 칼슘 수축력의 변화

김기환,엄융의,남기용,Kim, Ki-Whan,Earm, Yung-E,Nam, Kee-Yong 대한생리학회 1980 대한생리학회지 Vol.14 No.2

The effects of various inotropic interventions on the shape of the steady state length tension relation and the length-dependent activation process in cardiac muscle were studied. The influence of inotropic interventions upon the action potential was also observed. The range of varying muscle length was from the optimal length$(l_{max})$, where the active tension production is maximal, to 0.85 $l_{max}$. Changes in stimulus frequency or in external bathing Ca concentration constituted the inotropic interventions in this experiment. The papillary muscles were isolated from the rabbit right ventricles and perfused with $HCO-_3\;-buffered$ normal Tyrode solution which was aerated with $3%\;CO_2-97%\;O_2$ mixed gas and kept at $35^{\circ}C$. Resting Passive tension at $l_{max}$ was approximately 30% of the total tension and appeared from the muscle length of 0.90 $l_{max}$. The effect of stimulus frequency on the steady state level of developed tension was: As the stimulus frequency was increased from 0.1 to 0.5 Hz, there was little change in developed tension. As the frequency was increased further, to a value of about 3 Hz, tension increased steeply. Further increase of the frequency to 5 Hz had little additional effect on the developed tension. The length-tension curves for isometric peak tension became more steeper with the degree of potentiation by inotropic interventions. The relative steepness of the normalized length-tension curves where tension production was expressed as a percentage of maximal tension developed at $l_{max}$, varied inversely with the level of inotropic state and these curves were not superimposable one another. Thus at the stimulus frequency of 2 Hz or at the external Ca concentration of 8 mM, the relative decline in the developed tension for a given change in muscle length was considerably less than the decline observed at the frequency of 0.5 Hz or at the concentration of 2 mM Ca. Action potential duration was prolonged significantly as the frequency increased from 0.2 to 2 Hz, and this change in action potential duration was not observable on the changes in muscle length. There was a tendency of the hyperpolarization of membrane potential when the muscle length was shortened from $l_{max}$ to 0.95 $l_{max}$. These results support the hypothesis that there is a length-dependence of the activation process.

비가역성 실혈성 쇽에서 본 가토심근, 혈장의 전해질 및 혈당량 변화

김기환,남기용,Kim, Ki-Whan,Nam, Kee-Yong 대한생리학회 1968 대한생리학회지 Vol.2 No.1

Twenty white rabbits anesthetized with nembutal (30 mg/kg) were employed in this experiment. Five of them served as controls; the remaining rabbits as experimental group were subjected to irreversible hemorrhagic shock. Shock was induced by bleeding the animals until mean blood pressure decreased to a level of 50-40 mmHg. This level of pressure was maintained for 3-4 hours, after which the drawn blood was reinfused. The reinfusion of blood caused the elevation of arterial pressure almost the control level for some minutes, after which a gradual and progressive decline of blood pressure became evident. This decline was thought to be the result from irreversible hemorrhagic shock. When mean blood pressure declined to less than 50 mmHg, chest was opened and samples of arterial blood and left ventricular muscle were taken. Left ventricular muscle and blood plasma were analyzed for potassium, sodium, chloride and water content. Blood glucose concentration was determined by Somogyi-Nelson's method. Extracellular and intracellular myocardial water and electrolyte content were calculated on the basis that electrolytes are distributed between plasma water and interstitial water according to Gibbs-Donnan equilibrium. In this calculation extracellular water was substituted for Na space. The findings obtained were as follows: 1. The concentration of blood glucose was 87mg% in the controls and it rose to 222 mg% in shock (P<0.01). 2. Plasma potassium elevated significantly from 3.3 mEq/l in controls to 8.0 mEq/l in shock (P<0.01), while small decreases in sodium (151-146 mEq/l) and chloride (102-96 mEq/l) were observed (P<0.3, P<0.1), 3. The changes of blood water content (83.1-84.3%) and cardiac water content (77.5-78.3 gm/100gm WT) were observed. 4. In control animals myocardial potassium levels which averaged 30.2 mEq/100 gmDT rose significantly to 40.3 mEq/100 gmDT in shock (P<0.01), while moderate decreases in sodium(16.3-14.3 mEq/100 gmDT) were observed in shock. 5. The calculated transmembrane resting potential of left ventricular muscle of control animals averaged 95 mV, while rabbits in shock averaged 77 mV. (P <0.01). The findings of this experiment do not correspond with the conclusions that myocardial depression seems to be the cause of irreversible hemorrhagic shock, because the excitability of heart muscle is elevated. From the point of view that the lowered transmembrane resting potential, the cause of death in terminal stage of irreversible hemorrhagic shock may be ventricular fibrillation. It can't be said, however, that the lowered transmembrane resting potential is responsible for the transition from reversible to irreversible hemorrhagic shock. The marked increase in blood glucose suggested that glycogenolysis in the liver is favorably active in shock.

사망률 예측을 위한 모형 비교

박유성,김기환,이동희,이연경,Park Yousung,Kim Kee Whan,Lee Dong-Hee,Lee Yeon Kyung 한국통계학회 2005 응용통계연구 Vol.18 No.3

The Lee and Carter method has widely used to forecast mortality because of the simple structure of model and the stable forecasting. The Lee and Carter method, however, also has limitations. The assumption of the rate of decline in mortality at each age remaining invariant over time has been violated in several decades. And, there is no way to include covariates in the model for better forecasts. Here we introduce Park, Choi and Kim method to make up for Lee and Carter's weak points by using two random processes. We discuss structural features of two methods. furthermore, for each method, we forecast life expectancy for 2005 to 2050 using South Korea data and compare the results. 사망률 예측에 많이 사용되고 있는 Lee and Carter모형은 간결한 구조와 상대적으로 안정적인 예측력을 갖고 있는 것으로 알려져 있다. 그러나 연령별 사망률의 감소속도가 일정하게 유지된다는 가정으로 인하여 최근 연령별 사망률의 감소 패턴을 적절히 반영하지 못하고, 공변량을 사용할 수 없어 예측력을 제고할 수 없다는 제한점을 갖고 있다. 본 논문에서는 두 개의 확률과정을 이용하여 Lee and Carter 모형의 단점을 보완할 수 있는 Park, Choi and Kim의 모형을 소개하고 두 모형의 구조적인 특징을 서술하였다. 또한 각 모형에서 우리나라의 자료로 2005에서 2050년까지의 남녀별 예측기대여명을 작성하여 비교하였다.

우리나라 생명표 사망확률 추세에 관한 비교연구

김기환(Kee-Whan Kim),정승환(Seunghwan Jeong) 한국인구학회 2012 한국인구학 Vol.35 No.3

인구고령화 문제에 따른 정부정책의 개발과 평가는 지속적으로 시행되어야 하며, 이를 뒷받침할 수 있는 계량적 연구가 반드시 선행되어야 한다. 인구변화, 특히 연령별 사망패턴에 관한 계량적 연구는 장기적인 예측연구를 수반하기 때문에 이에 대한 시계열 자료가 충분히 있어야 하나, 우리나라가 보유하고 있는 인구 및 사망 자료는 자료의 확보기간과 연령구간의 불일치 등의 문제점을 갖고 있어 연구를 진행하는데 어려움이 따른다. 이러한 관점에서 생명표 사망확률은 우리나라 사망관련 자료 중에서 시간을 기준으로 연속성과 충분한 시계열 확보에 가장 적합한 자료라 할 수 있다. 본 연구에서는 과거부터 현재까지 우리나라 사망패턴을 파악하는데 있어 생명표 사망확률을 이용하였고, 일본 생명표 사망확률 패턴과 비교하였다. 사망확률에 대한 단순비교로는 종합적인 정보를 파악할 수는 있지만 연령대별로 세분화된 정보는 비교가 불가능하기 때문에 전체적인 사망확률 패턴을 분해할 수 있는 HP8 모형을 우리나라와 일본의 사망확률 자료에 적용하여 각 모수 시계열의 패턴을 비교하였다. 그리고 일본의 HP8 모형 모수패턴을 참고하여 우리나라 사망률을 예측하였고 그 결과를 바탕으로 예측 평균수명을 작성하였으며, 통계청 장래인구추계 평균수명, 일본 장래인구추계 평균수명과 비교하였다. Development and evaluation of the government policy, according to the population aging problem, should be continuously implemented, and quantitative researches in order to support such a matter should be necessarily preceded. In general, quantitative research on population change, especially on death pattern by age, involves the long-term predictions, which requires long enough time series data. However, the population and mortality data in Korea, have a problem of inconsistency including duration of secured data and the age interval, and it gives difficulties in conducting the research. From this point of view, death probability in life table can be considered as the most suitable data among death-related data in Korea, in that it satisfies sufficiency of time series as well as continuity of time period. In this study, we use death probability in life table to identify the past and present death patterns in Korea, and compare with that of Japan. The simple comparison of the death probabilities can provide the understanding of the comprehensive information, but it is impossible to perform the comparison of the detailed information by age group, so we apply HP8 model to the death probability in Korea and Japan which enables us to decompose the overall death probability pattern, and compare the time series pattern of each parameter. Finally, we predict the death probability and predicted life expectancy in Korea, with reference to the pattern of the HP8 model parameters in Japan, and then compare with the result of future population projections from Korea National Statistical Office and Ministry of Health, Labour and Welfare Japan.

진화알고리즘을 이용한 로봇 매니퓰레이터 궤적제어 최적화

김기환(Kee-Whan Kim),박진현(Jin-Hyun Park),최영규(Young-Kiu Choi) 대한전기학회 1996 대한전기학회 학술대회 논문집 Vol.1996 No.7

로버스트 추정법을 이용한 자기상관회귀모형에서의 특이치 검출

이동희,박유성,김기환,Lee Dong-Hee,Park You-Sung,Kim Kee-Whan 한국통계학회 2006 응용통계연구 Vol.19 No.2

시계열 자료에서의 특이치, 특히 이 가운데 가법적 특이치가 모형의 식별, 모수의 추정 및 예측과 관련된 분석 전과정을 왜곡하는 것은 잘 알려져 있다. 그러나 특이치가 다수 발생하는 경우, 특히 연속적으로 집단을 이루어 발생할 때 대부분 특이치 검출방법은 가면화효과와 수렁화효과때문에 이들을 정확히 판별하지 못한다. 본 논문에서는 p차 자기상관회귀모형에 대한 고붕괴점 회귀추정량을 이용한 양방향 로버스트 필터방법을 제안했다. 실제 사례와 모의실험을 통해 제안한 방법이 매우 정확하게 시계열 자료에 포함된 특이치들을 검출하고 있음을 확인할 수 있다. Outliers adversely affect model identification, parameter estimation, and forecast in time series data. In particular, when outliers consist of a patch of additive outliers, the current outlier detection procedures suffer from the masking and swamping effects which make them inefficient. In this paper, we propose new outlier detection procedure based on high breakdown estimators, called as the dual robust filtering. Empirical and simulation studies in the autoregressive model with orders p show that the proposed procedure is effective.

로버스트 회귀추정에 의한 신뢰구간 구축

이동희,박유성,김기환,Lee Dong-Hee,Park You-Sung,Kim Kee-Whan 한국통계학회 2006 응용통계연구 Vol.19 No.1

대부분의 자료는 여러가지 원인으로 인한 특이치로 오염되어 있으며, 이러한 상황에서 신뢰성 있는 추정량을 얻어내고 이에 대한 통계적 추론을 시행하는 것은 중요한 문제이다. 그러나 이제까지 제안된 로버스트 회귀추정량들은 계산상의 어려움과 정규오차모형에서 최소제곱추정량에 비하여 떨어지는 효율성때문에 통계적 추론의 정확성을 확신할 수 없었다. 최근 제안된 Lee(2004)의 가중자기조율회귀추정량(weighted self-tuning estimator, WSTE)은 다른 로버스트 회귀추정량에 비하여 정확한 계산과정과 그에 따른 추정량의 점근적 정규성 및 고붕괴점을 갖는다. 그러나 통계적 추론을 위하여 이제까지 널리 사용해왔던 로버스트 추정량에 기반한 가중최소제곱추정방법(weighted least squares estimator)은 WSTE에서조차 정규오차모형하에서 최소제곱추정량과 동일한 수준의 효율성을 제공해주지 는 못한다. 본 논문에서는 WSTE에 기반한 또다른 통계적 추론 방법을 제안하고, 이 방법을 사용함으로써 정규오차모형 및 대표본에서 보다 정확한 결과를 얻을 수 있음을 몬테칼로 모의실험을 통해 제시하였다. Since it is well-established that even high quality data tend to contain outliers, one would expect fat? greater reliance on robust regression techniques than is actually observed. But most of all robust regression estimators suffers from the computational difficulties and the lower efficiency than the least squares under the normal error model. The weighted self-tuning estimator (WSTE) recently suggested by Lee (2004) has no more computational difficulty and it has the asymptotic normality and the high break-down point simultaneously. Although it has better properties than the other robust estimators, WSTE does not have full efficiency under the normal error model through the weighted least squares which is widely used. This paper introduces a new approach as called the reweighted WSTE (RWSTE), whose scale estimator is adaptively estimated by the self-tuning constant. A Monte Carlo study shows that new approach has better behavior than the general weighted least squares method under the normal model and the large data.

풍속 자료의 공간예측

정승환,박만식,김기환,Jeong, Seung-Hwan,Park, Man-Sik,Kim, Kee-Whan 한국통계학회 2010 응용통계연구 Vol.23 No.2

오래 전부터 지속적으로 제기된 기후변화에 의한 문제들은 전 세계적인 문제점으로 언급되고 있다. 이러한 환경적 위기에 처한 각 나라들의 대처방법 중에 하나는 친환경적이고 지속가능한 발전 설비를 마련하기 위한 노력과 연구를 진행하고 있다는 것이다. 그중에서 풍력을 이용한 발전은 해외 선진국에서 오래 전부터 개발되어 발전해 오고 있고 우리나라 역시 최근에 풍력 발전에 관심을 갖고 기술개발에 노력을 기울이고 있다. 이러한 실정에서 우리나라 지역의 풍력에 대한 분석 및 예측은 천연자원의 적절한 이용이라는 관점에서 매우 중요한 연구라고 할 수 있겠다. 본 논문에서는 기상청에서 제공하는 풍속 측정 자료로 선형회귀모형에 근간을 둔 추정방법을 이용하여 주요도서지역을 제외한 남한지역의 공간적 특성을 파악할 수 있는 적절한 모형을 찾고 각 모형의 비교를 실시하였다. 이 결과를 바탕으로 남한지역의 풍속 예측지도를 구성하였다. In this paper, we introduce the linear regression model taking the parametric spatial association structure into account and employ it to five-year averaged wind speed data measured at 460 meteorological monitoring stations in South Korea. From the prediction map obtained by the model with spatial association parameters, we can see that inland area has smaller wind speed than coastal regions. When comparing the spatial linear regression model with classical one by using one-leave-out cross-validation, the former outperforms the latter in terms of similarity between the observations and the corresponding predictions and coverage rate of 95% prediction intervals.