Professional Documents
Culture Documents
Lecture note 5
Sampling distributions
and Estimation
1
Lecture note 5 Spring 2013
Sampling Variation
• Depending on the sample size, the sample statistic could either represent the
population well or differ greatly from the population.
2
Lecture note 5 Spring 2013
3
Lecture note 5 Spring 2013
4
Lecture note 5 Spring 2013
Examples of Estimators
5
Lecture note 5 Spring 2013
Sampling Distributions
• The sampling distribution of an estimator is the probability distribution of
all possible values the statistic may assume when a random sample of size
n is taken.
• An estimator is a random variable since samples vary.
• Sampling error = θ θ
6
Lecture note 5 Spring 2013
Bias
Bias is the difference between the expected value of the estimator and the true
parameter
Bias=E θ θ
An estimator is unbiased if E θ θ
7
Lecture note 5 Spring 2013
Efficiency
8
Lecture note 5 Spring 2013
Consistency
A consistent estimator converges toward the parameter being estimated as the
sample size increases.
9
Lecture note 5 Spring 2013
E X)= E X μ
σ
σ
√n
10
Lecture note 5 Spring 2013
If the population is exactly normal, then the sample mean follows a normal
distribution
11
Lecture note 5 Spring 2013
E X)= E X μ=80
σ = =2.236
√ √
• If the distribution of prices for these players is a normal distribution, then the
sampling distribution on x is N(80.00, 2.236).
12
Lecture note 5 Spring 2013
13
Lecture note 5 Spring 2013
14
Lecture note 5 Spring 2013
Questions
1. (T or F) The expected value of an unbiased estimator is equal to the parameter
whose value is being estimated
3. (T or F) The Central Limit Theorem says that if n exceeds 30, the population
will be normal.
15
Lecture note 5 Spring 2013
4. A certain population has a mean of 529 and a standard deviation of 29.7. Many
samples of size 36 are randomly selected and means calculated.
1) What value would you expect to find for the standard deviation of all these
sample means?
2) What shape would you expect the distribution of all these samples means to
have? Why?
16
Lecture note 5 Spring 2013
• The confidence level is the probability that the confidence interval contains
the true population mean.
• The confidence level (usually expressed as α %) is the area under the curve
of the sampling distribution.
17
Lecture note 5 Spring 2013
s
X t
√n
18
Lecture note 5 Spring 2013
Student’s t Distribution
19
Lecture note 5 Spring 2013
• t distributions are symmetric and shaped like the standard normal distribution.
20
Lecture note 5 Spring 2013
Degrees of Freedom
d.f= v=n-1
21
Lecture note 5 Spring 2013
22
Lecture note 5 Spring 2013
Construct a 90% confidence interval for the mean GMAT score of all MBA
applicants
x 510 , s 73.77
• Since σ is unknown, use the Student’s t for the confidence interval with n =
20 – 1 = 19 d.f.
23
Lecture note 5 Spring 2013
• We are 90% certain that the true mean GMAT score is within the interval
481.48 < μ < 538.52.
24
Lecture note 5 Spring 2013
25
Lecture note 5 Spring 2013
Using Appendix D
• Beyond v = 50, Appendix D shows n in steps of 5 or 10.
• If the table does not give the exact degrees of freedom, use the t-value for the
next lower n.
• This is a conservative procedure since it causes the interval to be slightly
wider.
• For d.f. above 150, use the z-value.
26
Lecture note 5 Spring 2013
STATA Practice
Data file: rent.xls
1. Import the given excel file as a *.dta file
3. Construct 90% and 95% confidence intervals for population mean of “rent”
variable.
27
Lecture note 5 Spring 2013
Questions
1. (T or F) As n increases, the width of the confidence interval will decrease ,
ceteris paribus.
28
Lecture note 5 Spring 2013
4. Given the following information: the sample size n = 20, the sample mean=
75.3, and the population standard deviation is unknown.
A) Find the 99% confidence interval for mean.
29