Chapter 3
Estimator
An estimator is a function of the sample data. An estimator is a RV,what makes it
random? Because the sample data is Random as well. An estimator is a procedure for using the
sample data to have an educated guess for the population parameter such as population mean.
Different methods for different guesses those diff guesses are estimators.
Median Height of the person that is in the middle.
What makes one estimator better than the other. In other words, what are the desirable
characteristics of the sampling distribution of an estimator? In general, we would like an estimator
that gets as close as possible to the unknown true value, at least in some average sense; in other
words, we would like the sampling distribution of an estimator to be as tightly centered on the
unknown true value as possible. This observation leads to three specific desirable characteristics of
an estimator 1) unbiasedness
( a lack of bias), consistency, and efficiency.
An estimate is the numerical value of the estimator in a given sample.
METHOD ESTIMATOR
NUMBERICAL VALUE ESTIMATE
Estimate unlike the estimator Is NOT a RV it is a number.
Unbiasedness
The desirable property of an estimator is that the mean of its sampling distribution
equals uy, if so estimator is said to be unbiased.
Uy—is a number.
^Uy is an estimator it is a RV, it is a method.
^Uy is an unbiased estimator if E(^Uy)= Uy
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Consistency
The larger the sample size, the smaller the uncertainity
. The probability that it is within
a small interval of the true values Uy approaches 1 as the sample size increases, that is ^uy is
consistent for uy. The larger the sample the more consistent it is.
Efficiency 
If both the estimators are unbiased chose the estimator with the tightest sampling
distribution, chose the estimator with the smallest variance. Efficiency smaller variance.
Properties of Y – Sampling distribution Y has already been examined. E(Y) = uy
Best Linear Unbiased Estimator (BLUE)? – Choose the one with the most efficiency?
Least squares estimator
 The estimator m that minimizes the sum of squared gaps Yi 
m
in
expressions is called the least squares estimator.
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 Clare
 Statistics, Normal Distribution, Standard Deviation, Statistical hypothesis testing

Click to edit the document details