Scribd
Upload
8 views2 pages

Week 2 In-Class Problems

The document outlines in-class problems for a statistics course, focusing on various statistical estimators and their properties, including bias, variance, and mean squared error (MSE). It covers topics such as Bernoulli and geometric distributions, convergence in probability, and Poisson distribution estimators, along with tasks to compute and compare different estimators. Additionally, it emphasizes the importance of consistency in estimators and includes simulation tasks to validate findings.

Uploaded by

daiyifei36
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views2 pages

Week 2 In-Class Problems

The document outlines in-class problems for a statistics course, focusing on various statistical estimators and their properties, including bias, variance, and mean squared error (MSE). It covers topics such as Bernoulli and geometric distributions, convergence in probability, and Poisson distribution estimators, along with tasks to compute and compare different estimators. Additionally, it emphasizes the importance of consistency in estimators and includes simulation tasks to validate findings.

Uploaded by

daiyifei36
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Week 2 in-class problems

PM522b Introduction to the Theory of Statistics Part 2

iid P100
1. Let X1 , ..., X100 ∼ Bernoulli(p) and let T = i=1 Xi
T T +3
a. For each of the following three alternative estimators of p, p̂ = 100 , p̃ = 100 ,
and p̆ = T106
+3
compute the bias, variance, and MSE.
b. Plot their MSE’s as a function of θ on the same graph. Comment on the plot.
Which estimator should one prefer?

2. Let X1 , . . . , Xn , . . . be a random sample from a population from a Geom0 (p) distri-


bution (Geom0 (p) is non-standard notation for the alternative version of the geo-
metric distribution that counts the number of failures –rather than the total num-
ber of trials– before the first success in a sequence of independent and identically
distributed Bernoulli trials. Its pmf is given by fX (x) = (1 − p)x p, x = 0, 1, 2, . . .,
where 0 ≤ p ≤ 1 is the unknown probability of success in an individual trial. Note
that this is the parameterization of the geometric distribution used in R. Also, if
Y has a standard Geom(p) distribution, X = Y − 1 ∼ Geom0 (p).)

a. To what does the sample mean X̄n converge in probability? Explain.


b. Let Yi = I{Xi >0} , i = 1, . . . , n. To what does the sample mean Ȳn converge in
probability? Explain

3. Convergence of a sequence of real numbers is a particular case of convergence in


probability. Let {an }n≥1 a sequence of real numbers such that lim an = a ∈ R.
n→∞
P
Show that an → a if we interpret an as a sequence of random variables taking the
single value an with probability 1, i.e. constant random variables.

4. Let X1 , ..., Xn be a random sample from a population from a P oisson(λ) distri-


x
bution (fX (x) = λx! e−λ , x = 0, 1, 2, . . ., with λ > 0 unknown. We are interested in
estimating p0 = τ (λ) = Pλ P (X1 = 0) = e−λ . Consider the two candidate estimators
for λ, λ̂ = e −X̄ and λ̃ = n ni=1 I{Xi =0} (proportion of Xi ’s equal to zero).
1

a. Explain why λ̂ and λ̃ are both natural estimators for λ.


b. Show that λ̃ is an unbiased estimator of λ.
c. Show that λ̂ is a biased estimator of λ.Conduct a small simulation in R to
compare the MSE of the two estimators over a range of λ values from 0.1 to
4.

1
e. Verify your finding in part d. by deriving the MSE of λ̂ and λ̃. Then, plot
the MSEs as a function of λ on the same graph.
f. Show that λ̂ and λ̃ are consistent estimators of λ.
g Which of the two estimators would you prefer? Justify your choice.

2. Let X1 , . . . , Xn be a random sample from an arbitrary distribution with


Pn mean 2µ
2 2 2 (X −X̄)
and variance σ . Consider the following two estimators of σ : S = i=1n−1i ,
Pn 2
i=1 (Xi −X̄)
and σ̂ 2 = n

a. Using the properties of convergence in probability show that both S 2 and σ̂ 2


are consistent if E[X14 ] < ∞.

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