Scribd Logo
Upload

Welcome to Scribd!

  • 49 views

    Sampling Distribution of OLS Estimator of A Monte Carlo Simulation

    Uploaded by

    Amissa Astha
    This document describes a Monte Carlo simulation to analyze the sampling distribution of the OLS estimator of β2 from a linear regression model. It defines two models that differ in the variance of the error term (σ2). It then generates 1,000 random samples from each model and estimates β2 from each sample. The results show that when the error variance is lower (Model 1), the distribution of the β2 estimates is tighter around the true value of 0.9. But when the error variance is higher (Model 2), the distribution is more spread out.

    Copyright:

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

    Sampling Distribution of OLS Estimator of A Monte Carlo Simulation

    Uploaded by

    Amissa Astha
    49 views3 pages
    This document describes a Monte Carlo simulation to analyze the sampling distribution of the OLS estimator of β2 from a linear regression model. It defines two models that differ in the variance of the error term (σ2). It then generates 1,000 random samples from each model and estimates β2 from each sample. The results show that when the error variance is lower (Model 1), the distribution of the β2 estimates is tighter around the true value of 0.9. But when the error variance is higher (Model 2), the distribution is more spread out.

    Original Title

    addnot04.pdf

    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 describes a Monte Carlo simulation to analyze the sampling distribution of the OLS estimator of β2 from a linear regression model. It defines two models that differ in the variance of the error term (σ2). It then generates 1,000 random samples from each model and estimates β2 from each sample. The results show that when the error variance is lower (Model 1), the distribution of the β2 estimates is tighter around the true value of 0.9. But when the error variance is higher (Model 2), the distribution is more spread out.

    Copyright:

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

    Sampling Distribution of OLS Estimator of A Monte Carlo Simulation

    Uploaded by

    Amissa Astha
    This document describes a Monte Carlo simulation to analyze the sampling distribution of the OLS estimator of β2 from a linear regression model. It defines two models that differ in the variance of the error term (σ2). It then generates 1,000 random samples from each model and estimates β2 from each sample. The results show that when the error variance is lower (Model 1), the distribution of the β2 estimates is tighter around the true value of 0.9. But when the error variance is higher (Model 2), the distribution is more spread out.

    Copyright:

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

    ECONOMICS 351* -- Addendum to NOTE 4 M.G.

    Abbott

    Addendum to NOTE 4

    Sampling Distribution of OLS Estimator of β2

    A Monte Carlo Simulation

    The True Model: is given by the population regression equation (PRE)

    Yi = β1 + β 2 X i + u i = 90 + 0.90 X i + u i (1)

    where

    β1 = 90.0 and β2 = 0.90;

    Yi = weekly consumption expenditures of the i-th household;

    Xi = weekly disposable income of the i-th household;

    ui = an iid random error term that is assumed to be N(0, σ 2 ) .

    Two Alternative Models: specify different values for σ 2 = Var( u i X i ) .

    Model 1: sets σ 2 = Var( u i X i ) = 900, σ = Var ( u i X i ) = se( u i X i ) = 30.

    Model 2: sets σ 2 = Var( u i X i ) = 32,400, σ = Var ( u i X i ) = se( u i X i ) = 180.

    ECON 351* -- Addendum to Note 4 ... Page 1 of 3 pages


    ECONOMICS 351* -- Addendum to NOTE 4 M.G. Abbott

    The Monte Carlo Simulations

    • Set N = 40 observations.

    • Set populations values of X, β1 and β2, and σ 2 = Var( u i X i ) .

    • Generate 1,000 independent random samples of Yi, Xi and ui values.

    • For each of these 1,000 independent random samples, compute the values of the
    OLS coefficient estimators:

    ∑ xy
    βˆ 2 = i i 2 i (2)
    ∑i x i
    βˆ = Y − βˆ X
    1 2 (3)

    where x i ≡ X i − X , y i ≡ Yi − Y , X = ∑ i X i N , and Y = ∑ i Yi N .

    • Tabulate the 1,000 estimates of β2, and the 1,000 estimates of β1.

    Summary statistics for simulation of Model 1 for which σ 2 = 900, σ = 30:


    . summarize

    Variable | Obs Mean Std. Dev. Min Max


    ---------+-----------------------------------------------------
    b1ols | 1000 90.12619 10.07493 61.00864 129.009
    b2ols | 1000 .8998154 .008213 .8695259 .9269965

    Summary statistics for simulation of Model 2 for which σ 2 = 32,400, σ = 180:


    . summarize

    Variable | Obs Mean Std. Dev. Min Max


    ---------+-----------------------------------------------------
    b1ols | 1000 90.75711 60.44958 -83.94814 324.0542
    b2ols | 1000 .8988922 .0492779 .7171556 1.061979

    ECON 351* -- Addendum to Note 4 ... Page 2 of 3 pages


    ECONOMICS 351* -- Addendum to NOTE 4 M.G. Abbott

    ∑ xy
    • Comparison of Sampling Distributions of βˆ 2 = i i 2 i :
    ∑i x i

    Sampling distribution of OLS estimator of beta2: beta2 = 0.90, N = 40

    .7

    .6

    .5
    Fraction

    .4

    .3

    .2

    .1

    0
    .7 .75 .8 .85 .9 .95 1 1.05 1.1
    b2ols
    Model 1: E(u) = 0, Var(u) = 900, SE(u) = 30, N = 40

    Sampling distribution of OLS estimator of beta2: beta2 = 0.90, N = 40

    .15

    .1
    Fraction

    .05

    0
    .7 .75 .8 .85 .9 .95 1 1.05 1.1
    b2ols
    Model 2: E(u) = 0, Var(u) = 32,400, SE(u) = 180, N = 40

    ECON 351* -- Addendum to Note 4 ... Page 3 of 3 pages

    You might also like