Scribd
Upload
34 views3 pages

ch7 1

Uploaded by

abulgassimg
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
34 views3 pages

ch7 1

Uploaded by

abulgassimg
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 3

Ch 7.

1 Estimation --- Point Estimation


Topics:
I. What is point estimation?
II. Criteria for evaluating point estimates
(a) unbiasedness
(b) small variability---small standard error
----------------------------------------------------------------------------------------------------------
I. Point Estimation
 What is it?
 Use a single value to guess the unknown parameter
 A point estimate is obtained by selecting a suitable statistic and computing its value
from the given sample data,
e.g.,

Parameter of interest Statistic chosen to estimate the parameter


Population mean Sample mean
Population median Sample median
Population proportion Sample proportion
Population SD Sample SD

The selected statistic is called the point estimator of the parameter,


e.g., is a point estimator of population mean

(sample proportion) is a point estimator of population success probability

1
How do we judge a good point estimator from a bad one?
Criterion I: Unbiasedness (i.e., on average, our guess is right on the target)
An estimator is unbiased if the mean of the sampling distribution of the statistic is
equal to the parameter
Ex. Use to estimate the parameter (population mean). Is unbiased?

Since the mean of is always equal to . So is an unbiased estimator of


population mean .

Criterion II: Small variability (i.e., for the uncertainty of our guess, the smaller the
better)
o The smaller the sampling variability (i.e., the SE of the statistics) is,
the better an estimate will be.

Ex. One wants to estimate population mean . Person A uses a sample of size 10,
and person B uses a sample of size 100. Which estimate is better?

Recall: If a continuous numerical variable X has mean and SD , the sampling

variability (variance) of sample mean is

o The SE of is but in reality is not known. We can estimate by

(the sample SD). Consequently, the standard error of can be estimated

by

2
Ex. Want to estimate the average rainfall in July at an NC city. Someone collected the
data of the past 5 years: 10, 20, 30, 40, 50 (mm). (1) What statistic should we
use to estimate the long-term average rainfall? (2) What are the point estimate

and its standard error? (Hint: )

(1) Use the sample mean.


(2) Point estimate = (10 + 20 + 30 + 40 +50)/5 = 30. Its standard error is

250

So the standard error is 7.07

Ex5. =P(no significant damage in a crash using a new type of bumper). We


observed 25 experiments, 15 shows no significant damage. Estimate and
report the standard error of the estimate.
= 15/25 = 0.6.

Standard error estimate

 Note: The standard error of a sample proportion is . We replace by its


point estimate p and get its standard error estimate.
 The sample standard deviation s is NOT an unbiased estimator of population standard
deviation . However, when sample size n is larger, s is approximately unbiased for .
 The sample variance is an unbiased estimator of the population variance .

You might also like