Loading [MathJax]/jax/output/CommonHTML/jax.js

ABOUT ME

For organizing technical knowledge and experience. demyank88@gmail.com

Today
Yesterday
Total
  • Lack-of-fit sum of squares and Pure-error sum of squares
    Stats/Inferential 2020. 2. 4. 12:17

    1. Overview

    In statistics, a sum of squares due to lack of fit, or more tersely a lack-of-fit sum of squares, is one of the components of a partition of the sum of squares of residuals in an analysis of variance, used in the numerator in an F-test of the null hypothesis that says that a proposed model fits well. The other component is the pure-error sum of squares.

    2. Description

    2.1 Intuition

    SSE=SSPE+SSLF

    (observedvaluefittedvalue)2(error)=(observedvaluelocalaverage)2(pureerror)+(weight×(localaveragefittedvalue)2(lackoffit)

    2.1.1 The sum of squares due to "pure" error (SSPE)

    The sum of squares of the differences between each observed y-value and the average of all y-values corresponding to the same x-value.

    2.1.2 The sum of squares due to lack of fit (SSLF)

    The weighted sum of squares of differences between each average of y-values corresponding to the same x-value and the corresponding fitted y-value, the weight in each case being simply the number of observed y-values for that x-value.

    2.2 Formular

    ni=1nij=1ˆε2ij=ni=1nij=1(YijˆYi)2=ni=1nij=1(YijˉYi)2sumofsquaresduetopureerror+ni=1ni(ˉYiˆYi)2sumofsquaresduetopureerror

    3. Reference

    https://en.wikipedia.org/wiki/Lack-of-fit_sum_of_squares

    https://www.youtube.com/watch?v=6VhjGw90TB4

    http://reliawiki.org/index.php/Simple_Linear_Regression_Analysis

    'Stats > Inferential' 카테고리의 다른 글

    Power and Effective size  (0) 2020.02.05
    Type 1 Error and Type 2 Error  (0) 2020.01.30
    Confidence Interval  (0) 2020.01.16
Designed by Tistory.