השוואת שיטות

	שיטת שרשרת-סולם להערכת עתודות הפסדים (מודל מאק)	היסק בוטסטרפ	שיטת הריבועים הפחותים המוכללת (GLS)
תחום	מדע אקטוארי	סטטיסטיקה	סטטיסטיקה
משפחה	Regression model	Regression model	Regression model
שנת המקור	1993	1979	1935
הוגה השיטה	Thomas Mack	Bradley Efron	Alexander Craig Aitken
סוג	Stochastic loss reserving model	Resampling-based inference	Linear estimator
מקור מכונן	Mack, T. (1993). Distribution-free calculation of the standard error of chain ladder reserve estimates. ASTIN Bulletin, 23(2), 213–225.	Efron, B. (1979). Bootstrap Methods: Another Look at the Jackknife. Annals of Statistics, 7(1), 1-26.	Aitken, A. C. (1935). IV.—On least squares and linear combination of observations. Proceedings of the Royal Society of Edinburgh, 55, 42–48.
כינויים	Development Factor Method, Link Ratio Method, Loss Development Method, Zincir Merdiven Yöntemi	bootstrap, bootstrap resampling, nonparametric bootstrap, Bootstrap Çıkarımı	GLS, Aitken estimator, EGLS, feasible GLS
קשורות	3	5	3
תקציר	Chain-Ladder Reserving is a stochastic actuarial method for estimating outstanding claim liabilities from a run-off triangle of cumulative paid losses. Formalized by Thomas Mack in 1993, it provides distribution-free estimates of reserve amounts along with their standard errors, making it a cornerstone of property-casualty insurance reserving and regulatory practice worldwide.	Bootstrap inference, introduced by Bradley Efron in 1979, estimates the sampling distribution of a statistic by repeatedly resampling the observed data with replacement. It requires no distributional assumption and produces reliable confidence intervals even in small samples.	Generalized Least Squares (GLS) is a linear regression estimator that extends ordinary least squares to handle situations where the error terms are correlated or have non-constant variance (heteroscedasticity). Introduced by Alexander Craig Aitken in 1935, GLS achieves the Best Linear Unbiased Estimator (BLUE) under a general error covariance structure by weighting observations according to their precision, providing a theoretical bridge between OLS and modern linear mixed models.