Scribd Logo
Upload

Welcome to Scribd!

  • 14 views

    Formulae Sheet

    Uploaded by

    Inês Cabral
    The simple linear regression model relates a dependent variable y to an independent variable x using an intercept β0 and slope β1. The ordinary least squares estimators β̂0 and β̂1 are calculated. The multiple linear regression model relates a dependent variable y to multiple independent variables x1, x2, etc. using intercept β0 and slopes β1, β2, etc. Each slope βj measures the effect of xj on y while holding other variables fixed. The coefficient of determination R2 measures how much variation in y is explained by the regression model compared to its mean.

    Copyright:

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

    Formulae Sheet

    Uploaded by

    Inês Cabral
    14 views1 page
    The simple linear regression model relates a dependent variable y to an independent variable x using an intercept β0 and slope β1. The ordinary least squares estimators β̂0 and β̂1 are calculated. The multiple linear regression model relates a dependent variable y to multiple independent variables x1, x2, etc. using intercept β0 and slopes β1, β2, etc. Each slope βj measures the effect of xj on y while holding other variables fixed. The coefficient of determination R2 measures how much variation in y is explained by the regression model compared to its mean.

    Original Description:

    statistics formulas to help study

    Original Title

    formulae sheet (1)

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The simple linear regression model relates a dependent variable y to an independent variable x using an intercept β0 and slope β1. The ordinary least squares estimators β̂0 and β̂1 are calculated. The multiple linear regression model relates a dependent variable y to multiple independent variables x1, x2, etc. using intercept β0 and slopes β1, β2, etc. Each slope βj measures the effect of xj on y while holding other variables fixed. The coefficient of determination R2 measures how much variation in y is explained by the regression model compared to its mean.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    14 views1 page

    Formulae Sheet

    Uploaded by

    Inês Cabral
    The simple linear regression model relates a dependent variable y to an independent variable x using an intercept β0 and slope β1. The ordinary least squares estimators β̂0 and β̂1 are calculated. The multiple linear regression model relates a dependent variable y to multiple independent variables x1, x2, etc. using intercept β0 and slopes β1, β2, etc. Each slope βj measures the effect of xj on y while holding other variables fixed. The coefficient of determination R2 measures how much variation in y is explained by the regression model compared to its mean.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 1

    The simple linear regression model: y = β 0 + β 1 x + u.

    The OLS estimators are: β̂ 0 = ȳ − β̂ 1 x̄, β̂ 1 =


    Pn  
    (x −x̄)(yi −ȳ) Pn Pn Pn
    Pn i
    i=1
    2 = w i yi , where w i = Pn xi −x̄ , ȳ = 1
    yi , x̄ = 1
    x i . Moreover, V ar β̂ 0 =
    i=1 (xi −x̄)
    i=1 i=1 xi (xi −x̄) n i=1 n i=1
    2
      2
    σ
    P n 2 σ 2 1
    P n 2
    (n−1)n S 2
    x i=1 xi , V ar β̂ 1 = (n−1)S 2 , where Sx = (n−1)
    x i=1 (xi − x̄) .

    The multiple linear regression model: y = β 0 + β 1 x1 + β 2 x2 + ... + β k xk + u. Interpretation of β j : holding


    2
    xi , i = 1, ...k and i ̸= j, fixed implies that ∆ŷ = β̂ j ∆xj , j = 1, ..., k. Moreover, V ar(β̂ j ) = SST σ1−R2 ,
    j( j)
    Pn 2
    where the SSTj = i=1 (xij − x̄j ) and Rj2 is the R2 from the regressing xj on all other x′ s. Moreover σ̂ 2 =
    Pn
    ( i=1 û2i )/(n − k − 1).
    [ n (ŷi −ŷ )(yi −ȳ)]2
    P
    Pn 2
    R-squared of regression: R2 = SSE/SST = 1−SSR/SST = Pn i=1 2 Pn 2
    , where SST = i=1 (yi − ȳ) ,
    i=1 ( i
    ŷ −ŷ ) i=1 i(y −ȳ)
    Pn 2 Pn
    SSE = i=1 (ŷi − ȳ) , SSR = i=1 û2i .
    Suppose that we know that the true model is y = β 0 + β 1 x1 + β 2 x2 + u, but we estimate ỹ = β̃ 0 + β̃ 1 x1 .
     
    S
    E β̃ 1 = β 1 + β 2 Corr(x1 , x2 ) Sxx2 , and the direction of bias is:
    1

    Corr(x1 , x2 ) > 0 Corr(x1 , x2 ) < 0


    β2 > 0 Positive Bias Negative Bias
    β2 < 0 Negative Bias Positive Bias

    Interpretation of partial effects:

    y xj ∆xj = 1 → ∆ E(y|x) = β j
    ln(y) xj ∆xj = 1 → ∆ E(y|x) = 100β j %
    y ln(xj ) ∆xj = 1% → ∆ E(y|x) = β j /100
    ln(y) ln(xj ) ∆xj = 1% → ∆ E(y|x) = β j %

    Under the CLM assumptions, conditional on the sample values of the independent variables for j = 0, ..., k,
    q  
    β̂ j −β j β̂ j −β j σ̂
    sd(β̂ )
    ∼ N (0, 1), where sd(β̂ j ) = V ar(β̂ j ); se(β̂ )
    ∼ t(n − k − 1), where se β̂ j = √ 2
    .
    j j SSTj (1−Rj )
    A 100(1 − α)% CI: (β̂ j − tα/2 se(β̂ j ), β̂ j + tα/2 se(β̂ j )).
    2
    
    (SSRr − SSRur ) /q Rur − Rr2 /q
    F = = 2 )/ (n − k − 1)
    .
    SSRur / (n − k − 1) (1 − Rur
    \ = β̂ + β̂ x1 + . . . + β̂ xk , then ŷ = exp( σ̂2 ) exp(β̂ + β̂ x1 + . . . + β̂ xk ).
    Let log(y) 0 1 k 2 0 1 k

    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