Home page for accesible maths 14 Distribution of the MLE

Style control - access keys in brackets

Font (2 3) - + Letter spacing (4 5) - + Word spacing (6 7) - + Line spacing (8 9) - +

Solution:

  1. a

    There are 3 types of component, each giving rise to a constraint on θ:

    1. 1

      0θ1,

    2. 2

      03θ1,

    3. 3

      01-4θ1,

    as the components each need to have valid probabilities. The third inequality is sufficient for the other two and gives 0θ1/4.

  2. b

    Given the data, the likelihood is

    L(θ) θ2(3θ)5(1-4θ)43
    θ7(1-4θ)43.

    For the sketch note that L(0)=L(1/4)=0 and the function is concave and positive between these two with a maximum closer to 0 than 1/4.

  3. c

    To work out the MLE, we differentiate the (log-)likelihood as usual. The log-likelihood is

    l(θ)=7logθ+43log(1-4θ).

    Differentiating,

    l(θ)=7θ-4×431-4θ.

    A candidate MLE solves l(θ^)=0, giving θ^=7200.

    Moreover,

    l′′(θ)=-7θ2-4×4×43(1-4θ)2<0,

    so this is indeed the MLE.

  4. d

    The observed information is

    IO(θ^) =-l′′(θ^)
    =7θ^2+4×4×43(1-4θ^)2
    =5714.3+930.2
    =6644.5.

    So a 95% confidence interval for θ is

    (θ^-1.96IO(θ^),θ^+1.96IO(θ^))
    =(0.0110,0.0590).

    As 0.02 is within this confidence interval there is no evidence of this batch being sub-standard.