Documente Academic
Documente Profesional
Documente Cultură
• Overview
• Homeworks
• Stata & Review standard errors
• Chapter 5
• Point estimation. (A&F 5.1)
• Confidence intervals…
o for a population mean (A&F 5.2)
o for a population proportion (A&F 5.3)
• Choosing a sufficient sample size (A&F 5.4)
1
What we have accomplished with sampling
distributions
2
What’s next
4
The basics of point estimation
ˆ s
i
(Y Y ) 2
n 1
6
Typical point estimators for standard errors.
7
Choosing a good estimator
You can technically use any equation you want as a
point estimator, but the most popular ones have
certain desirable properties.
•Unbiasedness: The sampling distribution for the estimator
‘centers’ around the parameter. (On average, the estimator
gives the correct value for the parameter.)
•Efficiency: If at the same sample size one unbiased
estimator has a smaller sampling error than another unbiased
estimator, the first one is more efficient.
•Consistency: The value of the estimator gets closer to the
parameter as sample size increases. Consistent estimators
may be biased, but the bias must become smaller as the
sample size increases if the consistency property holds true.
8
Examples for point estimates:
Given the following sample of seven observations:
5,2,5,2,4,5,5
. ci age
Variable | Obs Mean Std. Err. [95% Conf. Interval]
-------------+---------------------------------------------------------------
age | 215754 27.34663 .0416549 27.26499 27.42827
15
Equations for interval estimates.
17
5.3: Confidence intervals for population proportions:
ˆ (1 ˆ )
ˆ z
n
• Example, 424 of 1000 respondents in a poll report that they
plan to vote for candidate X. Calculate a 95% c.i. for this
result.
o = .424 +- 1.96 * sqrt { [ .424 * (1-.424)] / 1000 }
o = .424 +- 1.96 * sqrt { [ .424 * .576 ] / 1000 }
o = .424 +- 1.96 * sqrt { .000244}
o = .424 +- 1.96 * .0156
o = .424 +- 0.031
18
o = .395 -> .455
Normality rules for confidence intervals for sample
proportions:
19
Putting it all together:
20
What is the best phrasing for an interval estimate?
ˆ (1 ˆ )
c.i. ˆ z
n
• When we choose the best sample size, we choose one half
of the confidence interval (the top one) and solve for n
(1 )
nz 2
(c.i.top1/ 2 ) 2
• Agresti and Finlay’s term for one half of the confidence
interval is the confidence bound B
24
Sample size example:
25
Choosing the best sample size for a sample mean
26
Choosing the best sample size for a population mean
s
c.i. Y z
n
• When we choose the best sample size, we choose one half
of the confidence interval (the top one) and solve for n
2
nz 2
(c.i.top1/ 2 ) 2
28