Scribd Logo
Upload

Welcome to Scribd!

  • 9 views

    PS4 1

    Uploaded by

    asinghww1
    econ 325 problem set 4

    Copyright:

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

    PS4 1

    Uploaded by

    asinghww1
    9 views2 pages
    econ 325 problem set 4

    Original Title

    PS4-1

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    econ 325 problem set 4

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    9 views2 pages

    PS4 1

    Uploaded by

    asinghww1
    econ 325 problem set 4

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 2

    Econ 325 - Problem Set 4

    Due June 22, 2024, Saturday, 11:59pm on Canvas

    Instructions. These questions review the basics of statistical inference. Do your best to make your
    arguments rigorous.

    1. Suppose that we have i.i.d. discrete random vectors, (X i , Yi ), which are observed. Suppose further
    that X i and Yi are Bernoulli random variables with parameters pX = P{X i = 1} ∈ (0, 1) and
    pY = P{Yi = 1} ∈ (0, 1) respectively. Suppose that we know pX = 0.5 but we do not know pY .

    (i) Suppose that our parameter of interest is θ which is defined as

    θ = P{Yi = 1 | X i = 1}.

    Provide a consistent estimator of θ . (You need to prove the consistency of your estimator.)

    (ii) Suppose that our parameter of interest is β which is defined as

    Cov(X i , Yi )
    β= .
    Var(X i )

    Provide a consistent estimator of β. (You need to prove the consistency of your estimator.)

    2. Suppose that (X i , Yi ), i = 1, ..., n, are i.i.d. random vectors, where X i represents the i-th worker’s
    annual income before COVID 19 and Yi represents the i-th worker’s annual income after COVID
    19. For simplicity, we assume that X i and Yi are independent.

    For the following questions (i) and (ii-a), we assume that X i is known to follow a normal distribu-
    tion with mean µX and variance σ2X , and Yi is known to follow a normal distribution with mean
    µY and variance σ2Y .

    (i) We are interested in estimating the following quantity:

    θ = E[X i − Yi ].

    (i-a) Suppose that we know σ2X = 1 and σ2Y = 4. Construct a 95% confidence interval for θ , i.e.
    a confidence interval whose coverage probability is precisely equal to 0.95. (For the confidence
    interval, you can use the notation z1−α/2 to be the (1 − α/2) quantile of N (0, 1).)

    (i-b) Suppose that we do not know σ2X and σ2Y , but we have consistent estimators σ̂2X and σ̂2Y
    so that

    σ̂2X → P σ2X and σ̂2Y → P σ2Y .

    Using these estimators and the sample analogue estimator of θ , construct a confidence interval
    whose coverage probability converges to 0.95 as n → ∞.

    1
    (ii) We are interested testing the following:

    Y1 − X 1
    • ˜
    H0 : E = 0.5 against
    4
    Y1 − X 1
    • ˜
    H1 : E > 0.5.
    4

    (ii-a) Suppose that we know that σ2X = 1, and σ2Y = 4.

    (ii-a-a) Construct a test whose Type I Error is equal to 0.05. (Students do not need to explain
    how the Type I Error is equal to 0.05.)

    (ii-a-b) Consider the test in (ii-a-a). Compute the power of the test under the alternative
    hypothesis:

    Y1 − X 1
    • ˜
    E = 1.
    4

    (You can express the power in terms of the CDF Φ of N (0, 1).)

    For the following question (ii-b), suppose that we do not know whether X i and Yi follow a normal
    distribution.

    (ii-b) Suppose that we know that

    Var(Y1 + X 1 ) = 5.

    Using this information and the sample analogue estimator of E[(Y1 − X 1 )/4], construct a test
    whose rejection probability under the null hypothesis converges to 0.05 as n → ∞. (You need to
    show the convergence.)

    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