Scribd Logo
Upload

Welcome to Scribd!

  • 236 views

    QM-1 Unit 3 Formulae

    Uploaded by

    sathvik
    This document provides formulas for correlation and regression. It defines Karl Pearson's correlation coefficient as the covariance of x and y divided by the product of the standard deviations of x and y. It also provides Spearman's rank correlation coefficient formula. Regression equations are given as y=a+bx for the regression of y on x and x=A+By for x on y. The regression coefficients b and B are defined in terms of the correlation coefficient r. Properties of the regression equations include that the lines pass through the mean values and the signs of the correlation coefficient and regression coefficients are the same.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    QM-1 Unit 3 Formulae

    Uploaded by

    sathvik
    236 views3 pages
    This document provides formulas for correlation and regression. It defines Karl Pearson's correlation coefficient as the covariance of x and y divided by the product of the standard deviations of x and y. It also provides Spearman's rank correlation coefficient formula. Regression equations are given as y=a+bx for the regression of y on x and x=A+By for x on y. The regression coefficients b and B are defined in terms of the correlation coefficient r. Properties of the regression equations include that the lines pass through the mean values and the signs of the correlation coefficient and regression coefficients are the same.

    Original Description:

    QM formulas

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides formulas for correlation and regression. It defines Karl Pearson's correlation coefficient as the covariance of x and y divided by the product of the standard deviations of x and y. It also provides Spearman's rank correlation coefficient formula. Regression equations are given as y=a+bx for the regression of y on x and x=A+By for x on y. The regression coefficients b and B are defined in terms of the correlation coefficient r. Properties of the regression equations include that the lines pass through the mean values and the signs of the correlation coefficient and regression coefficients are the same.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    236 views3 pages

    QM-1 Unit 3 Formulae

    Uploaded by

    sathvik
    This document provides formulas for correlation and regression. It defines Karl Pearson's correlation coefficient as the covariance of x and y divided by the product of the standard deviations of x and y. It also provides Spearman's rank correlation coefficient formula. Regression equations are given as y=a+bx for the regression of y on x and x=A+By for x on y. The regression coefficients b and B are defined in terms of the correlation coefficient r. Properties of the regression equations include that the lines pass through the mean values and the signs of the correlation coefficient and regression coefficients are the same.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    QM-1 (UM19MB502) - Unit 3; Correlation and Regression – Formulae

    QM-1 (UM19MB502) - Unit 3


    Correlation and Regression – Formulae

    Correlation

    Covariance of(x, y) ∑(x − x̅) (y − y̅)


    r = =
    Karl Pearson’s σx ∗ σy √∑(x − x̅)2 ∗ ∑(y − y̅)2
    Correlation Coefficient
    Using Covariance of ‘x’ 1
    and ‘y’, Standard Covariance of (x, y) = ∑(x − x̅) (y − y̅)
    n
    deviations of ‘x’ and
    ‘y’
    ∑(x − x̅)2 ∑(y − y̅)2
    σx = √ ; σy = √
    n n

    Karl Pearson’s
    Correlation Coefficient n ∑ xy − (∑ x)(∑ y)
    Using values of series r =
    ‘x’ and series ‘y’ √n ∑ x 2 − (∑ x)2 ∗ √n ∑ y 2 − (∑ y)2

    1|Page Compiled by: Prof. M R Sai Prawin, MBA Dept., PES University
    QM-1 (UM19MB502) - Unit 3; Correlation and Regression – Formulae

    r = √bxy ∗ byx

    ∑(x − x̅) (y − y̅) n ∑ xy − (∑ x)(∑ y)


    Karl Pearson’s bxy = =
    Correlation Coefficient ∑(y − y̅)2 n ∑ y 2 − (∑ y)2
    Using Regression
    Coefficients ∑(x − x̅) (y − y̅) n ∑ xy − (∑ x)(∑ y)
    byx = =
    ∑(x − x̅)2 n ∑ x 2 − (∑ x)2

    bxy and byx are Regression Coefficients of Regression lines ‘x’ on ‘y’
    and ‘y’ on ‘x’ respectively.

    1 1
    6 { ∑ d2 + (m1 3 − m1 ) + (m 3 − m2 ) + ⋯ . }
    R =1− 12 12 2
    n ∗ (n2 − 1)
    Spearman’s Rank 1
    Correlation • (mi 3 − mi ) terms should be mentioned the number of
    12
    times ranks are shared.
    • mi (i = 1, 2, 3, … ) represents number of times an observation
    is repeated.
    • d = Difference in ranks of a pair “Rx - Ry”
    Coefficient of Determination 𝐫𝟐
    2|Page Compiled by: Prof. M R Sai Prawin, MBA Dept., PES University
    QM-1 (UM19MB502) - Unit 3; Correlation and Regression – Formulae

    Regression Equations
    Regression Line ‘y’ on ‘x' Regression Line ‘x’ on ‘y'
    y = a + bx x = A + By

    b = byx ; a = y̅ − bx̅ B = bxy ; A = x̅ − By̅

    ∑(x − x̅) (y − y̅) n ∑ xy − (∑ x)(∑ y) ∑(x − x̅) (y − y̅) n ∑ xy − (∑ x)(∑ y)


    byx = = bxy = =
    ∑(x − x̅)2 n ∑ x 2 − (∑ x)2 ∑(y − y̅)2 n ∑ y 2 − (∑ y)2
    σy σx
    byx =r bxy = r
    σx σy

    Properties of Regression Equations


    1. ̅ , y̅).
    Both the regression lines passes through their common intersection point (x
    If two regression equations x on y and y on x are, a1x+b1y+c1 = 0 and a2x+b2y+c2 = 0
    respectively, Then

    b1 c2 − c1 b2 c1 a2 − a1 c2 a1 b2
    x̅ = ; y̅ = ; r = ∓√
    a1 b2 − b1 a2 a1 b2 − b1 a2 b1 a2
    2. Signs of Correlation Coefficient and both the Regression Coefficients are the same.
    3. r 2 = bxy ∗ byx ≤ 1

    3|Page Compiled by: Prof. M R Sai Prawin, MBA Dept., PES University

    You might also like