Let X1, X2, · · · , Xn ∼ N(µ, σ2 ). Show that the MLE of µ is efficient.
MLE of will be the sample
mean =
You can find this by taking a partial dervative of the log-
likelihood function with respect to and the simply
equating it to 0, as follows:
Now, an estimator is said to be efficient if the mean squared error
becomes 0, as ,
where n is the sample size:
Proof:
MSE() = +
Now, as this is an unbiased estimator, it means that Bias=0
MSE =
=
=
=
=
=
Now as
Thus, MLE of is efficient
=
X1, X2, . . . , Xn i.i.d. ∼ N (µ, σ2 ). Assume µ is known; show that ˆθ = 1 n Pn i=1(Xi− µ) 2 is the MLE for σ 2 and show that it is unbiased. Exactly 6.4-2. Xi, X2, . . . , xn i d. N(μ, μ)2 is the MLE for σ2 and show that it is unbiased. r'). Assume μ is known; show that θ- n Ση! (X,-
Exactly6.4-2. X1,X2,...,Xn ∼ N(μ,σ). Assumeμisknown; show that θ=nμ)2 is the MLE for σ2 and show that it is unbiased.
Let X1, X2 be iid, normal(µ, σ2 = 1). Show that the statistic T = X1 + X2 is sufficient for µ
Let X1, · · ·, Xn∼ N(µ, τ ) with known µ and unknown variance τ > 0. 1. Find the MLE of τ. 2. Find the MLE of √τ .
Suppose X1, X2, . . . , Xn (n ≥ 5) are i.i.d. Exp(µ) with the density f(x) = 1 µ e −x/µ for x > 0. (a) Let ˆµ1 = X. Show ˆµ1 is a minimum variance unbiased estimator. (b) Let ˆµ2 = (X1 +X2)/2. Show ˆµ2 is unbiased. Calculate V ar(ˆµ2). Confirm V ar(ˆµ1) < V ar(ˆµ2). Calculate the efficiency of ˆµ2 relative to ˆµ1. (c) Show X is consistent and sufficient. (d) Show ˆµ2 is not consistent...
Let X1, X2, . . . , Xn be IID N(0, σ2 ) variables. Find the rejection region for the likelihood ratio test at level α = 0.1 for testing H0 : σ2 = 1 vs H1 : σ2 = 2.
Let X1, ..., Xn be a random sample (i.i.d.) from a normal distribution with parameters µ, σ2 . (a) Find the maximum likelihood estimation of µ and σ 2 . (b) Compare your mle of µ and σ 2 with sample mean and sample variance. Are they the same?
8. Let X, X2, , xn all be be distributed Normal(μ, σ2). Let X1, X2, , xn be mu- tually independent. a) Find the distribution of U-Σǐ! Xi for positive integer m < n b) Find the distribution of Z2 where Z = M Hint: Can the solution from problem #2 be applied here for specific values of a and b?
5. Let X1, X2, . . . , Xn be independently distributed as N(u, σ2). Define 71 -1 /Users/rumi3/Downloads/Linear-Regression-Analysis-Seber pdf MOMENT GENERATING FUNCTIONS AND INDEPENDENCE 13 and (a) Prove that var[S2-2σ4/(n-1). (b) Show that Q is an unbiased estimate of σ2. (c) Find the variance of Qand hence show that as n → oo, the effi- ciency of Q relative to S2 is
σ2). 6. Suppose X1, Yİ, X2, Y2, , Xn, Y, are independent rv's with Xi and Y both N(μ, All parameters μί, 1-1, ,n, and σ2 are unknown. For example, Xi and Yi muay be repeated measurements on a laboratory specimen from the ith individual, with μί representing the amount of some antigen in the specimen; the measuring instrument is inaccurate, with normally distributed errors with constant variability. Let Z, X/V2. (a) Consider the estimate σ2- (b) Show that the...