Scribd Logo
Upload

Welcome to Scribd!

  • 33 views

    University of Palestine Gaza Strip Civil Engineering College Numerical Analysis CIVL 3309 Dr. Suhail Lubbad

    Uploaded by

    Hazem Almasry
    This document discusses linear regression and least squares regression for curve fitting data points. [1] It introduces the concept of finding the best fit curve to describe a data set by minimizing the discrepancy between the data points and the curve. [2] It then covers linear regression specifically, describing how to calculate the coefficients to determine the linear equation that best fits a set of paired data points using the least squares method. [3] Key aspects like the standard error of the estimate and coefficient of determination r2 are also defined to quantify the goodness of fit of the linear regression model.

    Copyright:

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

    University of Palestine Gaza Strip Civil Engineering College Numerical Analysis CIVL 3309 Dr. Suhail Lubbad

    Uploaded by

    Hazem Almasry
    33 views19 pages
    This document discusses linear regression and least squares regression for curve fitting data points. [1] It introduces the concept of finding the best fit curve to describe a data set by minimizing the discrepancy between the data points and the curve. [2] It then covers linear regression specifically, describing how to calculate the coefficients to determine the linear equation that best fits a set of paired data points using the least squares method. [3] Key aspects like the standard error of the estimate and coefficient of determination r2 are also defined to quantify the goodness of fit of the linear regression model.

    Original Title

    14

    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 discusses linear regression and least squares regression for curve fitting data points. [1] It introduces the concept of finding the best fit curve to describe a data set by minimizing the discrepancy between the data points and the curve. [2] It then covers linear regression specifically, describing how to calculate the coefficients to determine the linear equation that best fits a set of paired data points using the least squares method. [3] Key aspects like the standard error of the estimate and coefficient of determination r2 are also defined to quantify the goodness of fit of the linear regression model.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    33 views19 pages

    University of Palestine Gaza Strip Civil Engineering College Numerical Analysis CIVL 3309 Dr. Suhail Lubbad

    Uploaded by

    Hazem Almasry
    This document discusses linear regression and least squares regression for curve fitting data points. [1] It introduces the concept of finding the best fit curve to describe a data set by minimizing the discrepancy between the data points and the curve. [2] It then covers linear regression specifically, describing how to calculate the coefficients to determine the linear equation that best fits a set of paired data points using the least squares method. [3] Key aspects like the standard error of the estimate and coefficient of determination r2 are also defined to quantify the goodness of fit of the linear regression model.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 19

    University of Palestine

    Gaza Strip

    Civil Engineering College


    Numerical analysis
    CIVL 3309
    Formerly CVL 3308

    Dr. Suhail Lubbad


    Least Square Regression
    Curve fitting
    Data Regression

    Find a simple yet the best curve that fits the data
    points.

    To generally describe the shape and behaviour of


    that data set.

    The curve does not necessarily pass through


    individual points
    Such curve can not be arbitrarily chosen.
    Otherwise,
    different analysts would draw different curves,

    If the data set points define a perfect curve


    (better use interpolation)
    Criteria controlling the choice of the best curve:

    minimise discrepancy (error) between data points and curve

    One widely known is the


    least-squares regression
    ( today's lecture topic )
    LINEAR REGRESSION:
    fitting a straight line to a set of paired observations: (x1,
    y1), (x2, y2), . . . , (xn, yn).

    The line's equation


    y=a 0&a 1 x&e Where e describes the error
    Criteria for best fit

    Minimize the sum of the squares of the residuals


    between
    the measured y and the y calculated with the linear
    model
    n n n

    ∑ e =∑ )y
    Sr =
    2
    i i , measured
    2
    − y i , model * =∑ )y − a − a x *
    i 0 1 i
    2

    i=1 i=1 i=1

    This criterion yields a unique line for a given set of data


    Least-Squares Fit of a Straight Line

    A technique to determining the values of a0 and a1 that


    minimises Sr (defined in thelast slide)
    n n n

    Sr = ∑ 2
    ei = ∑ 2
    ∑
    ) y i , measured − yi , model * =
    2
    ) yi − a0 − a 1 xi *
    i=1 i=1 i=1

    Differentiate with respect to a0 once and with respect to a1 once more,


    The minimum occurs when those derivatives are zeros

    n n

    = −2 ∑ ∑
    ∂ Sr ∂ Sr
    )y i − a0 − a1 x i * = 0, = −2 ) yi − a 0 − a1 xi * x i = 0
    ∂ a0 ∂ a1
    i=1 i=1
    a1 =
    n ∑ xi y i − ∑x∑i yi
    2
    n ∑ x
    2
    i − )∑ x *i

    a 0 = y( − a 1 x(
    ( is the mean of Q
    where Q
    Therefore, the least-squares fit is
    y = 0.07142857 + 0.8392857x
    Error analysis:
    Least-Squares Fit of a Straight Line

    standard error of the estimate or


    the standard “deviation” for the regression line

    '
    Sr
    S y /x =
    n−2

    n - 2 because two data-derived estimates—a0 and a1—were used to compute Sr


    To quantify the “goodness” of the fit

    Compare the standard error of the estimate Sy/x


    using
    St: the total sum of the squares around the mean for the
    dependent variable (in our case, y)

    '
    n

    ∑
    2
    ) y i − y( *

    '
    St i=1
    Sy = =
    n−1
    n−1
    St − Sr,
    quantifies the improvement or error reduction due to
    describing the data in terms of a straight line rather than as
    an average value.

    r2 : coefficient of determination

    2
    St − S r
    r =
    St
    A perfect fit: Sr = 0 and r = r2 = 1, signifies that the line explains 100% of
    the variability of the data.

    When r = r2 = 0, Sr = St the fit represents no improvement.


    Linearization of Nonlinear Relationships

    In some cases, polynomial regression is appropriate.

    In some others, transformations can be used to express the


    data in a form compatible with linear regression.
    (Linearization)
    Polynomial regression
    Is
    A straight forward Generalisation of the linear regression.
    Not included in our final Exam
    This was the last topic

    Next lectures, some exercises and questions


    and some students' presentations for their Computer Programs

    Good Luck

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy