STAT2303 UARK Week 03 Lesson 01 Confidence Intervals

Z-Scores and Estimating a
Population Proportion
Todd J. Thomas, University of Arkansas
n this lesson, we will present methods for 1.

reading a z-score, 2. understanding a standard normal distribution, and 3. Calculating
z-scores. We wil then present how to use a sample proportion to make an inference about the
value of a corrsponding porpulation proprtion.
There are three main concepts the student needs
to understand: 1. Point Estimate, 2. Confidence
Interval, and 3. Sample Size. We will also work
with probabilitities and percentages of the popultaton proportion, p. We start with definitions
needed for this lesson
Examples
Example 01: Suppose that your company made five
expermental screws for a new Air Force fighter jet. The
weight of each screw is: 45, 37, 48, 42, 51. Calculate the
mean weight of the screws.
Solution: Since the company only made 5 screws,
we are dealing with a population, thus we use use the
population notation to find the mean,
Chapter 6.2: The Standard Normal

Distribution
45 + 37 + 48 + 42 + 51
223
=
= 44.6
5
5
(1)
Example 02: You work for a company that makes

chocolates chip cookies and you are concerted that the
chocolate chips in one particular lot are not evenly
Population and Sample Mean
distributed among all other lots for that day. Find the
Recall in the last lesson that a parameter is a measure- mean value of chocolate chips in the first 6 cookies
ment from a population. A statistic is a measurement you pull from the bag, given that the the number of
taken from a sample. We also finished last lesson talking chocolate chips are: 24, 28, 36, 18, 12, 42.
about uniform distributions and we discussed that
Solution: Since we are finding the mean weight of
because the total area under the density curve is is equal
to 1 there is a correspondence to between area and prob- only the first six cookies, we are dealing with a sample,
x. Thus to find the mean, we:
ability.
1. Population Mean: Denoted by the greek letter
mu, , it is found by taking all the sum of all the
values in the population, and dividing it by the total
count of all values.
x =
24 + 28 + 36 + 18 + 12 + 42
136
=
= 22.7
6
6
(2)
As a rule of thumb, when you round the value

2. Sample Mean: Denoted by the letter x, it is cal- of a mean, you carry one more decimal place
culated in the same manner as the population mean, than is present in the original data set.
but it is taken from a sample instead of a population.
Standard Deviation
Later we will learn the emperical rule, but for now,

know that 95% of all data points will fall within two
1. Standard Deviation: The standard deviation of standard deviations of the mean. This implies that any
a set of values deonted by s, for a sample and the data points that fall to the left of 27.3 is considered an
greek lower case letter sigma, , for a population, is unusual value.
a measure of how much data values deviate away
from the mean it is calculated by:
Chapter 6: Normal Probability
s
(x x)2
s=
(3) Distributions
n1
r
6.4: Sampling Distribution of Sample
(x )2
=
(4)
Proportions
n
Calculators and software use the following formual Sampling Distribution of the Sample Proportion:
is the distribtuion of sample proportions, with all samples
for the sample standard deviation:
having the same sample size n, taken from the same
population.
s
n(x2 ) (x)2
s=
(5) Notation: Now we need to distinguish between a popn(n 1)
ulationproportion and some sample proportion. p =
population proportion, and p = sample proportion.
Examples
Calculating a sample proportion: To calculate a
Example 03 Find the standard deviation of the sample sample proportion use the formula:
values 22, 22, 26, and 24.
x
(6)
p =
n
Solution: Now start by listing all your values in the
formula above:
Where n is the sample size, and x is the number of
successes observed.
There are two important properties to know about
n=4
sample proportins:
x = 22 + 22 + 26 + 24 = 94
1. Sample proportions target the value of the popux2 = 222 + 222 + 262 + 242 = 2220
lation proportion. That is the expected value of
the sample proportion is equal to the population
Now plug in for the values:
proportion.
s
r
2
4(2220) (94 )
44
2. The distribtuion of sample proportions tends to
s=
=
= 1.9
4(4 1)
12
approximate a normal distribution.
So 1.9 is the standard deviation of the sample values.
Now, what is the value at the first standard deviation?
The Second standard deviation? The Third standard
deviation?
The mean is given by:
x =
x
22 + 22 + 26 + 24
94
=
=
= 23.5
n
4
4
So the value of the first standard deviation

is 23.5 + 1.9 = 25.4, the second deviation is
25.4 = 1.9 = 27.3 and the third standard deviation is 27.3 + 1.9 = 29.2.
3.4 Measure of Relative Standing

z-scores
Common Confidence Intervals

90% confidence level
values of
= 0.10
= .05
= 0.01
A z-score is thenumber of standard deviations that a

given value x is above or below the mean. We calculate
the z-score for a population, sample, and proportion Interpreting a Confidence Interval
respectively:
Be careful to interpret the confidence interval in
the proper way. There is only one correct interx
zpopulation =
(7) pertation. For example the only correct interpre
tation of a 95% confidence level estimate of the
x x
zsample =
(8) population proportion p is 0.828 < p < 0.872 is:
s
p p
Response
Zproportion = r
(9)
p(1 p)
We are 95% confident that the
n
Correct
interval (0.828, 0.872) actually
Interpretation does contain the true value of
1. A z-score represents the how much a given value, x
the population proportion p.
deviates from the center of the data.
There is a 95% chance that
Incorrect
2. the value can help to assess how extreme a par- Interpertation the true value of p will
fall between (0.828, 0.872).
ticular data value is based on the distribution the
95% of sample proportions
value is suppose to follow.
Incorrect
will fall between 0.828
Interpertation
and 0.872.
3. we can also use this score to convert sample data
into a measure of relative standing so that we can
compare samples to one another.
Make sure you know the correct intpretation

of a confidence interval as given above.
4. the sign of the z-score tells you what side of the

center of the data the x value is on, with negative z- Critical Values
scores being to the left of center and positive z-score
1. Critical Value: The critical value is a number on
being to the right of center.
the borderline separating sample statistics that are
5. z denotes the z-score with an area under the normal
likely to occur from those that are unlikely. The
density curve of to the Right of center.
number z/2 is a critical value that is a z-score with
the property that it separates an area of /2 in the
right tail of a standard normal distribution.
1 7.2 Estimating a Population

Proportion
Example Find the critical value z/2 corresponding

to a 95% confidence level.
1. Point Estimate: A point estimate is a single value

(or point) used to approximate a population param- Solution A 95% confidence level corresponds to a
/2 = 0.025. We find z0.025 = 1.96, by noting that
eter.
the cummulative area the left must be 1 0.025, or .975.
2. Confidence Interval: is a range of values used to We know that .975 refers to the area under the density
estimate the true value of a population parameter. curve, so we can plug this into Statcrunch to get a z-score
of 1.96.
A confidence interval will be abbreviated CI.
Get use to working with and confidence levels. We
3. Confidence Level: is the probability 1 that the
confidence interval interval actually does contain the will work with this in every class, on every project, and
population parameter assuming that the estimation it will be on every tests for the rest of the semester.
process is repeated a large number of times. (Think
Law of Large Numbers).

STAT2303 UARK Week 03 Lesson 01 Confidence Intervals

Uploaded by

Copyright:

Available Formats

STAT2303 UARK Week 03 Lesson 01 Confidence Intervals

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

STAT2303 UARK Week 03 Lesson 01 Confidence Intervals

Uploaded by

Copyright:

Available Formats

Z-Scores and Estimating a

n this lesson, we will present methods for 1.

Chapter 6.2: The Standard Normal

Example 02: You work for a company that makes

As a rule of thumb, when you round the value

Later we will learn the emperical rule, but for now,

So the value of the first standard deviation

3.4 Measure of Relative Standing

Common Confidence Intervals

A z-score is thenumber of standard deviations that a

Make sure you know the correct intpretation

4. the sign of the z-score tells you what side of the

1 7.2 Estimating a Population

Example Find the critical value z/2 corresponding

1. Point Estimate: A point estimate is a single value

You might also like