Yahoo Answers is shutting down on May 4th, 2021 (Eastern Time) and beginning April 20th, 2021 (Eastern Time) the Yahoo Answers website will be in read-only mode. There will be no changes to other Yahoo properties or services, or your Yahoo account. You can find more information about the Yahoo Answers shutdown and how to download your data on this help page.

Trending News

Promoted
dusty_guy107
dusty_guy107 asked in Science & MathematicsMathematics · 1 decade ago

How to do a linear regression?

I need to do a regression model for a data set but i need to force the y-intercept to be zero. When i try to solve my equations fall back to an identity. If it makes a difference its a normalized regression where x'=x^2.

more specifically if y=ax^2 find a. im trying to solve by transforming x squared to x then solving y=a1*x+a0. then transform back. but where i keep running into difficulty is letting the a0=0 and still having something to work with. THANKS FOR ANY HELP.

2 Answers

Relevance
  • cidyah
    Lv 7
    1 decade ago
    Favorite Answer

    Using Least squares regression,

    a = Σ y(i)x(i)^2 / Σ x(i)^4 ----(1)

    You have a data set (x,y)

    x--y

    10 12

    2 13

    5 4

    7 10

    etc,

    Find x^4

    Find x^2

    Find y times x^2 for each observation and use equation (1) to find a.

  • ?
    Lv 5
    1 decade ago

    If your line is y=mx+b and you want y' =mx, then just reduce (code) all your y values by b.

Still have questions? Get your answers by asking now.