목록Applied/Statistical Computing (24)
Chapter 14 - 1 ) Quasi-Newton Algorithm
참고 1. EM https://modern-manual.tistory.com/46 EM 알고리즘 예시로 쉽게 이해하기 (Expectation maximization, EM algorithm) 기댓값 최대화 알고리즘(expectation-maximization algorithm, EM algorithm)은 모수에 관한 추정 값으로 로그 가능도(log likelihood)의 기댓값을 계산하는 기댓값 (E) 단계와 이 기댓값을 최대화하는 모수 추정값 modern-manual.tistory.com 2. multinomial distribution http://faculty.washington.edu/yenchic/20A_stat512/Lec7_Multinomial.pdf
Chapter 14 - 0 ) Optimization Introduction
참고 1. Bisection Method https://byjus.com/maths/bisection-method/ Bisection Method - Definition, Procedure, and Example The bisection method is used to find the roots of an equation. It subdivides the interval in which the root of the equation lies. For more info, visit BYJU’S. byjus.com 2. secant Method https://math.iitm.ac.in/public_html/sryedida/caimna/transcendental/iteration%20methods/secant..
Bootstrap estimate of bias
#Motivation : small sample로 population parameter를 추정하고 싶다 - bootstrap 2. Consider patch data in “patch.csv” file. The data contains measurements of a certain hormone in the bloodstream of eight subjects after wearing a medical patch. The parameter of interest is θ= (E(new)−E(old)) / (E(old) − E(placebo)) If |θ| ≤ 0.20, this indicates bioequivalence of the old and new patches. The statistic is Y ..
Empirical Distribution
1. Generate 100 observations from a N (0, 1) distribution. Compute the empirical CDF F. Plot the true CDF and the empirical CDF. #F par(mfrow = c(1,2)) x
