statistical inference may be divided into two major areas

12
1 IE - 2333 SWN STATISTICAL INFERENCE May be divided into two major areas PARAMETER ESTIMATION HYPOTHESIS TESTING POINT ESTIMATION INTERVAL ESTIMATION The decision making procedure about the hypothesis CONFIDENCE INTERVALS MEANS VARIANCES PROPORTIONS

Upload: belita

Post on 23-Feb-2016

41 views

Category:

Documents


0 download

DESCRIPTION

STATISTICAL INFERENCE May be divided into two major areas. PARAMETER ESTIMATION. HYPOTHESIS TESTING. POINT ESTIMATION. The decision making procedure about the hypothesis. INTERVAL ESTIMATION. CONFIDENCE. INTERVALS. MEANS. VARIANCES. PROPORTIONS. POINT ESTIMATION. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: STATISTICAL INFERENCE May be divided  into  two major areas

1IE - 2333 SWN

STATISTICAL INFERENCEMay be divided into two major

areas

PARAMETER

ESTIMATION

HYPOTHESIS

TESTING

POINT ESTIMATION

INTERVAL ESTIMATIONThe decision making procedure

about the hypothesis

CONFIDENCE INTERVALS

MEANS VARIANCES PROPORTIONS

Page 2: STATISTICAL INFERENCE May be divided  into  two major areas

2IE - 2333 SWN

POINT ESTIMATIONA statistic used to estimate a population parameter is called a point estimator for and is denoted by .The numerical value assumed by this statistic when evaluated for a given sample is called a point estimate for .There is a difference in the terms :

ESTIMATOR and ESTIMATE

is the statistic used to generate the

estimate ; it is a random variable

is a number

Page 3: STATISTICAL INFERENCE May be divided  into  two major areas

3IE - 2333 SWN

We want, the estimator to generate estimates that can be expected to be close in value to .We would like :1. to be UNBIASED for 2. to have a small variance for large sample sizes In general, If X is a random variable with probability distribution , characterized by the unknown parameter , and if X1, X2, . . . . Xn is a random sample of size n from X, then the statistic is called a point estimator of . note that is a random variable, because it is a function of random variable

( ) ( )X Xf x or p x

1 2, , nh X X X

Page 4: STATISTICAL INFERENCE May be divided  into  two major areas

4IE - 2333 SWN

Definition : A point estimate of some population parameter , is a single numerical value of a statistic

Definition : The point estimator is an unbiased estimator for the parameter if If the estimator is not unbiased, then the difference is called the biased of the estimator

( ) .E

( )E

Page 5: STATISTICAL INFERENCE May be divided  into  two major areas

5IE - 2333 SWN

VARIANCE AND MEAN SQUARE ERROR OF A POINT ESTIMATOR

A logical principle of estimation, when selecting among several estimator, is to chose the estimator that has minimum variance.

Definition : If we consider all unbiased estimator of , the one with the smallest variance is called the minimum variance unbiased estimator (MVUE).

Some times the MVUE is called the UMVUE, where the first U represents “Uniformly”, meaning “for all ”

Page 6: STATISTICAL INFERENCE May be divided  into  two major areas

6IE - 2333 SWN

MEAN SQUARE ERRORDefinition : the mean square error of an- estimator

of the parameter is defined as :

2MSE E

The mean square error can be rewritten as follows :

2 2

MSE E E E

2MSE Var bias

The mean square error is an important criterion for comparing two estimators.

Page 7: STATISTICAL INFERENCE May be divided  into  two major areas

7IE - 2333 SWN

Let be two estimators of the parameter , and let be the mean square error ofThen the relative efficiency of is defined as :

1 2and 1 2MSE and MSE

1 2.and 1 2to

If this relative efficiency is less than one, we would

conclude that is more efficient estimator of than 1

2

1

2

MSE

MSE

Example :

Suppose we wish to estimate the mean of a population. We have a random sample of n

observations X1, X2, …..Xn and we wish to compare two possible estimator for :

the sample mean and a single observation from the sample, say, Xi,X

Page 8: STATISTICAL INFERENCE May be divided  into  two major areas

8IE - 2333 SWN

Note, both and Xi are unbiased estimators of ; consequently, the MSE of both estimators is simply the variance.

X

21

22

1MSE nnMSE

2

We have MSE X Var Xn

Since for sample size n ≥ 2, we would conclude that the sample mean is a better

estimator of than a single observation Xi.

1 1n

Page 9: STATISTICAL INFERENCE May be divided  into  two major areas

9IE - 2333 SWN

EXERCISES1. Suppose we have a random sample of size 2n from

a population denoted by X, and E(X) = and Var X = 2. Let

be two estimator of . Which is the better estimator of ? Explain your choice.

2. Let X1, X2, . . . , X7 denote a random sample from a population having mean and variance 2. Consider the following estimator of :

21 1

1 221 1

n n

i in ni i

X X and X X

1 2 7 1 6 41 2

..... 2;7 2

X X X X X X

Page 10: STATISTICAL INFERENCE May be divided  into  two major areas

10IE - 2333 SWN

(a) Is either estimator unbiased?

(b) Which estimator is “best” ?

3. Suppose that are estimators of . We know

that

1 2 3, and

1 2 ,E E and

23 1 2 3, 12, 10 6E Var Var and E

Compare these three estimators. Which do you prefer? Why?

Page 11: STATISTICAL INFERENCE May be divided  into  two major areas

11IE - 2333 SWN

5. Let X1, X2, X3 and X4 be a random sample of size 4 from a population whose distribution is exponential with unknown parameter .

11 2 2: X X

n np T and T

4. In a Binomial experiment exactly x successes are observed in n independent trials. The

following two statistics are proposed as estimators of the proportion

parameter

Determine and compare the MSE for T1 and T2

Page 12: STATISTICAL INFERENCE May be divided  into  two major areas

12IE - 2333 SWN

b. Among the unbiased estimators of , determine the one with the smallest variance

1 11 1 2 3 46 3T X X X X

1 2 3 42 3 42 5

X X X XT 1 2 3 4

3 4X X X XT

a. Which of the following statistics are unbiased estimators

of ?