手法を比較

	長期記憶モデル（ARFIMA、FIGARCH）	高頻データと市場マイクロストラクチャ分析	最小二乗法 (OLS) 回帰
分野	ファイナンス	ファイナンス	計量経済学
系統	Regression model	Regression model	Regression model
提唱年	1980	2007	2019
提唱者	Granger & Joyeux (ARFIMA); Baillie, Bollerslev & Mikkelsen (FIGARCH)	Hasbrouck (2007); Aït-Sahalia & Jacod (2014)	Wooldridge (textbook treatment); classical least squares
種類	Fractionally integrated time series model	Market microstructure / high-frequency econometrics	Linear regression
原典	Granger, C. W. J. & Joyeux, R. (1980). An Introduction to Long-Memory Time Series Models and Fractional Differencing. Journal of Time Series Analysis, 1(1), 15-29.	Hasbrouck, J. (2007). Empirical Market Microstructure: The Institutions, Economics, and Econometrics of Securities Trading. Oxford University Press. ISBN: 978-0195301649	Wooldridge, J. M. (2019). Introductory Econometrics: A Modern Approach (7th ed.). Cengage Learning. ISBN: 978-1337558860
別名	ARFIMA, FIGARCH, fractionally integrated models, fractional integration	market microstructure, high-frequency financial econometrics, tick data analysis, Yüksek Frekanslı Veri ve Piyasa Mikro Yapısı	ordinary least squares, classical linear regression, linear regression, en küçük kareler regresyonu
関連	4	5	5
概要	Long-memory models are fractional-integration methods that capture genuine long memory through a hyperbolically decaying autocorrelation structure. ARFIMA, introduced by Granger and Joyeux (1980), models long memory in return series, while FIGARCH, introduced by Baillie, Bollerslev and Mikkelsen (1996), captures long memory in volatility series; the parameter d measures the degree of fractional integration.	Market microstructure analysis studies how prices form from tick-level trade and quote data, examining order-book dynamics, the bid-ask spread, and price discovery. The modern econometric framework was set out by Hasbrouck (2007) and extended for high-frequency data by Aït-Sahalia and Jacod (2014).	Ordinary Least Squares is the classical linear regression method that explains a continuous outcome as a linear combination of predictors. It estimates the coefficients by minimising the sum of squared residuals, and under the Gauss-Markov assumptions these estimates are the best linear unbiased estimator (BLUE).