방법 비교

	STL 분해: Loess를 이용한 계절-추세 분해	ARIMA (Autoregressive Integrated Moving Average) 모형	LOESS / LOWESS 지역 회귀
분야	계량경제학	계량경제학	머신러닝
계열	Process / pipeline	Regression model	Machine learning
기원 연도	1990	2015	1979
창시자	Cleveland, Cleveland, McRae & Terpenning	Box & Jenkins (Box-Jenkins methodology)	William S. Cleveland
유형	nonparametric iterative smoother	Univariate time-series model	Local nonparametric regression smoother
원전	Cleveland, R. B., Cleveland, W. S., McRae, J. E., & Terpenning, I. (1990). STL: A seasonal-trend decomposition procedure based on loess. Journal of Official Statistics, 6(1), 3–73.	Box, G. E. P., Jenkins, G. M., Reinsel, G. C. & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley. ISBN: 978-1118675021	Cleveland, W. S. (1979). Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association, 74(368), 829–836.
별칭	Seasonal-Trend Decomposition using Loess, STL filtering, Loess-based seasonal decomposition, Mevsimsel-Trend Ayrıştırma (STL)	Box-Jenkins model, ARIMA(p,d,q), ARIMA Modeli	LOWESS, local regression, locally weighted scatterplot smoothing, yerel regresyon
관련	3	5	3
요약	STL Decomposition, introduced by Cleveland, Cleveland, McRae, and Terpenning (1990), is a nonparametric procedure that separates a time series into three additive components — trend, seasonal, and remainder — using iterative locally weighted regression (loess). Widely used in economics, meteorology, and data science, it handles time series of any periodicity and is robust to the presence of outliers, making it a highly flexible alternative to classical decomposition methods.	ARIMA is a univariate time-series forecasting model that combines autoregressive, integrated (differencing), and moving-average components to predict a single continuous series from its own past. It is the centrepiece of the Box-Jenkins methodology set out in Box, Jenkins, Reinsel & Ljung's Time Series Analysis (5th ed., 2015).	LOESS (locally estimated scatterplot smoothing), introduced by William Cleveland in 1979 and extended with Susan Devlin in 1988, fits a smooth curve through data by performing a separate weighted polynomial regression in the neighbourhood of each point. Nearby observations count more than distant ones, so the method follows local structure without assuming any global functional form, making it a popular exploratory smoother for scatterplots.