Consider a Bernoulli distribution f(x|θ) = θ^x (1 − θ)^(1−x) for x = 0 and x...

Consider a Bernoulli distribution f(x|θ) = θ^x (1 − θ)^(1−x) for x = 0 and x = 1. Let the prior distribution for θ be f(θ) = 6θ(1 − θ) for θ ∈ (0, 1).

(a) Find the posterior distribution for θ.

(b) Find the Bayes’ estimator for θ.

Expert Solution

orchestra answered 2 years ago

Consider an exponential distribution f(x|θ) = θe^(−θx) for x > 0. Let the prior distribution for...

Consider an exponential distribution f(x|θ) = θe^(−θx) for x > 0. Let the prior distribution for θ be f(θ) = e^ −θ for θ > 0. (a) Show that the posterior distribution is a Gamma distribution. With what parameters? (b) Find the Bayes’ estimator for θ.

Let f(x; θ) = θxθ−1 for 0 < x < 1 and θ ∈ Ω =...

Let f(x; θ) = θxθ−1 for 0 < x < 1 and θ ∈ Ω = {θ : 0 < θ < ∞}. Let X1, . . . , Xn denote a random sample of size n from this distribution. (a) Sketch the pdf of X for (i) θ = 1/2, (ii) θ = 1 and (iii) θ = 2. (b) Show that ˆθ = −n/ ln (Qn i=1 Xi) is the maximum likelihood estimator of θ. (c) Determine the...

4. Consider the triangular probability distribution with PDF f(x) = 0 if x <= 0 or...

4. Consider the triangular probability distribution with PDF f(x) = 0 if x <= 0 or x >= 4, x/2 if 0 < x <= 1, (4-x)/6 if 1 < x < 4. (a) Obtain the CDF F (b) Obtain its inverse F^-1 (c) Describe the inverse CDF simulation method for this given problem.

is 1. f(x/θ) = 2x/θ^2 complete sufficient statistic 2. f(x/θ) =((logθ) θ^x ) / (θ -1) complete...

is 1. f(x/θ) = 2x/θ^2 complete sufficient statistic 2. f(x/θ) =((logθ) θ^x ) / (θ -1) complete sufficient statistic?

Let X1. . . . Xn be i.i.d f(x; θ) = θ(1 − θ)^x x =...

Let X1. . . . Xn be i.i.d f(x; θ) = θ(1 − θ)^x x = 0.. Is there a function of θ for which there exists an unbiased estimator of θ whose variance achieves the CRLB? If so, find it

For a random variable X with a Cauchy distribution with θ = 0 , so that...

For a random variable X with a Cauchy distribution with θ = 0 , so that f(x) =(1/ π)/( 1 + x^2) for -∞ < x < ∞ (a) Show that the expected value of the random variable X does not exist. (b) Show that the variance of the random variable X does not exist. (c) Show that a Cauchy random variable does not have ﬁnite moments of order greater than or equal to one.

For f(x; θ) = θ exp(-xθ) , x>0 1a) Determine the most powerful critical region for...

For f(x; θ) = θ exp(-xθ) , x>0 1a) Determine the most powerful critical region for testing H0 θ=θ0 against H1 θ=θ1 (θ1 > θ0) using a random sample of size n. 1b) Find the uniformly most powerful H0 θ<θ0 against H1 θ>θ1

Find f. f ''(x) = x−2, x > 0, f(1) = 0, f(4) = 0 f(x)=

One obervation is taken from the probability model. f(x;θ)=((θ/2)^|x|)*((1-θ)^(1-|x|)) for x=-1,0,1 and θ ∈ [0,1]. We...

One obervation is taken from the probability model. f(x;θ)=((θ/2)^|x|)*((1-θ)^(1-|x|)) for x=-1,0,1 and θ ∈ [0,1]. We find that the MLE of θ is |x|. Now consider T(X) where T(X)=2 when x=1 and T(X)=0 otherwise. Show that the MLE of θ has a smaller variance than T(X).

Let Y1, ..., Yn be a random sample with the pdf: f(y;θ)= θ(1-y)^(θ-1) with θ>0 and...

Let Y1, ..., Yn be a random sample with the pdf: f(y;θ)= θ(1-y)^(θ-1) with θ>0 and 0<y<1. i) Obtain the minimum variance unbiased estimator ( for θ)

Question