do the warm-up on your own, chapter 7 on a piece … · bedford freeman worth publishers chapter 7...
TRANSCRIPT
1/12/2017
1
The Practice of Statistics, 5th Edition
Starnes, Tabor, Yates, Moore
Bedford Freeman Worth Publishers
Do the warm-up on your own, on a piece of paper
The Practice of Statistics, 5th Edition
Starnes, Tabor, Yates, Moore
Bedford Freeman Worth Publishers
CHAPTER 7 Sampling Distributions 7.3
Sample Means
Learning Objectives
After this section, you should be able to:
The Practice of Statistics, 5th Edition 3
FIND the mean and standard deviation of the sampling distribution
of a sample mean. CHECK the 10% condition before calculating the
standard deviation of a sample mean.
EXPLAIN how the shape of the sampling distribution of a sample
mean is affected by the shape of the population distribution and the
sample size.
If appropriate, use a Normal distribution to CALCULATE
probabilities involving sample means.
Sample Means
Why do we do sampling?
• It is usually difficult (or impossible) to do a
census. And it is also expensive.
• An unbiased sample is meant to represent
the population.
– How would we know if it was a good
representation?
Sampling Variability
How can x, based on a sample of only a few
of the 117 million American households, be
an accurate estimate of μ?
KEY CONCEPT
A second sample would likely result in a different mean . . .
The value of a statistic varies in repeated sampling . . .
It is why we have to check conditions!!
WHY DO WE CHECK
ASSUMPTIONS?
What are the assumptions we have used?
• Some form of randomization in context
• May use approximately Normal Distribution
• Independence
Eliminates bias, every member of population
has an equal chance to be drawn
Sample size must be large enough to insure
the sampling distribution is approximately
normal.
Sample size must be less than 10% of the
population . This allows us to use standard
deviation formulas.
1/12/2017
2
The Practice of Statistics, 5th Edition 7
The Sampling Distribution of
When we record quantitative variables we are interested in other
statistics such as the median or mean or standard deviation. Sample
means are among the most common statistics.
Consider the mean household earnings for samples of size 100.
Compare the population distribution on the left with the sampling
distribution on the right. What do you notice about the shape, center,
and spread of each?
x
The Practice of Statistics, 5th Edition 8
The Sampling Distribution of
When we choose many SRSs from a population, the sampling
distribution of the sample mean is centered at the population mean µ
and is less spread out than the population distribution. Here are the
facts.
Sampling Distribution of a Sample Mean
as long as the 10% condition is satisfied: 10n ≤ N.
x
The standard deviation of the sampling distribution of x is
s x =s
n
The mean of the sampling distribution of x is mx = m
Suppose that x is the mean of an SRS of size n drawn from a large population
with mean m and standard deviation s. Then :
Note: These facts about the mean and standard deviation of x are true
no matter what shape the population distribution has.
The Practice of Statistics, 5th Edition 9
Movies
Suppose the number of movies viewed in the last year by high school
students has an average of 19.3 with a standard deviation of 15.8.
Suppose we take an SRS of 100 high school students and calculate the
mean number of movies viewed by the members of the sample.
(a) What is the mean of the sampling distribution of ? x
x
(b) What is the standard deviation of the sampling distribution of ?
Remember to check that the 10% condition is met.
is an unbiased estimator of μ, μx=μ=19.3 movies
σx = 15.8/10=1.58 movies. The 10% condition is met because there are
more than 10(100) = 1000 high school students.
x
The Practice of Statistics, 5th Edition 10
Sampling From a Normal Population
We have described the mean and standard deviation of the sampling
distribution of the sample mean x but not its shape. That's because the
shape of the distribution of x depends on the shape of the population
distribution.
In one important case, there is a simple relationship between the two
distributions. If the population distribution is Normal, then so is the
sampling distribution of x . This is true no matter what the sample size is.
Sampling Distribution of a Sample Mean from a Normal Population
Suppose that a population is Normally distributed with mean m
and standard deviation s . Then the sampling distribution of x
has the Normal distribution with mean m and standard
deviation s / n, provided that the 10% condition is met.
The Practice of Statistics, 5th Edition 11
The Central Limit Theorem
Most population distributions are not Normal. What is the shape of the
sampling distribution of sample means when the population distribution
isn’t Normal?
It is a remarkable fact that as the sample size increases, the distribution
of sample means changes its shape: it looks less like that of the
population and more like a Normal distribution!
When the sample is large enough, the distribution of sample means is
very close to Normal, no matter what shape the population distribution
has, as long as the population has a finite standard deviation.
Uniform distribution
Sample size 1
1/12/2017
3
Uniform distribution
Sample size 2
Uniform distribution
Sample size 3
Uniform distribution
Sample size 4
Uniform distribution
Sample size 8
Uniform distribution
Sample size 16
Uniform distribution
Sample size 32
1/12/2017
4
Triangle distribution
Sample size 1
Triangle distribution
Sample size 2
Triangle distribution
Sample size 3
Triangle distribution
Sample size 4
Triangle distribution
Sample size 8
Triangle distribution
Sample size 16
1/12/2017
5
Triangle distribution
Sample size 32
Inverse distribution
Sample size 1
Inverse distribution
Sample size 2
Inverse distribution
Sample size 3
Inverse distribution
Sample size 4
Inverse distribution
Sample size 8
1/12/2017
6
Inverse distribution
Sample size 16
Inverse distribution
Sample size 32
Parabolic distribution
Sample size 1
Parabolic distribution
Sample size 2
Parabolic distribution
Sample size 3
Parabolic distribution
Sample size 4
1/12/2017
7
Parabolic distribution
Sample size 8
Parabolic distribution
Sample size 16
Parabolic distribution
Sample size 32
The Practice of Statistics, 5th Edition 40
The Central Limit Theorem
Most population distributions are not Normal. What is the shape of the
sampling distribution of sample means when the population distribution
isn’t Normal?
It is a remarkable fact that as the sample size increases, the distribution
of sample means changes its shape: it looks less like that of the
population and more like a Normal distribution!
When the sample is large enough, the distribution of sample means is
very close to Normal, no matter what shape the population distribution
has, as long as the population has a finite standard deviation.
Draw an SRS of size from any population with mean and finite
standard deviation . The says that when
is large, the sampling distribution of the sample mean is
n
n
x
central limit theorem (CLT)
approximately
Normal.
The Practice of Statistics, 5th Edition 41
The Central Limit Theorem
Consider the strange population distribution
from the Rice University sampling distribution
applet.
Describe the shape of the sampling
distributions as n increases. What do you
notice?
The Practice of Statistics, 5th Edition 42
The Central Limit Theorem
Normal/Large Condition for Sample Means
The central limit theorem allows us to use Normal probability
calculations to answer questions about sample means from many
observations even when the population distribution is not Normal.
As the previous example illustrates, even when the population
distribution is very non-Normal, the sampling distribution of the sample
mean often looks approximately Normal even with small sample sizes.
If the population distribution is normal, then so is the sampling
distribution of . This is true no matter what the sample size (n)
is.
If the population distribution is not Normal (aka unknown,
skewed, etc.), the Central Limit Theorem (“CLT”) tells us that the
sampling distribution of will be approximately Normal in most
cases, if n ≥ 30. x
x
1/12/2017
8
The Practice of Statistics, 5th Edition 43
How do you know if you can use an approximately
normal distribution?
1. It’s stated in the problem stem. If so, say so in your assumptions.
2. n is greater than or equal to 30, then you have a large enough
sample size to approximate the sampling distribution with a normal
curve.
3. Graph the actual data, draw your graph (boxplot) in the
assumptions, and state if there are no extreme outliers or severe
skewedness that we may use an approximately normal distribution
Point of clarification:
If we can’t prove a sampling distribution is approximately normal; don’t
speculate what it is . . . We only know we can not assume it is . . .
The Practice of Statistics, 5th Edition 44
The Sampling Distribution of
x
A statistic used to estimate a
parameter is unbiased if the
mean of its sampling
distribution is equal to the
true value of the parameter
being estimated.
Example: At the P. Nutty Peanut Company, dry-roasted, shelled
peanuts are placed in jars by a machine. The distribution of weights in
the jars is approximately Normal, with a mean of 16.1 ounces and a
standard deviation of 0.15 ounces.
(a) Without doing any calculations, explain which outcome is more
likely:
1) randomly selecting a single jar and finding that the contents
weigh less than 16 ounces or
2) randomly selecting 10 jars and finding that the average
contents weigh less than 16 ounces.
(b) Find the probability of each event described above, you may
assume all the assumptions have been met..
It’s more likely to have a
single jar weigh less,
than a group of 10
(they’d be closer to the
mean).
Example: At the P. Nutty Peanut Company, dry-roasted, shelled
peanuts are placed in jars by a machine. The distribution of weights in
the jars is approximately Normal, with a mean of 16.1 ounces and a
standard deviation of 0.15 ounces.
(b) Find the probability of each event described above, you may assume
all the assumptions have been met..
1) randomly selecting a single jar and finding that the contents
weigh less than 16 ounces or
State the distribution and values of interest.
Let µ = the true average weight of a jar of peanuts. N(16.1, 0.15)
x
Perform the calculations.
2514.0)67.0(
67.015.0
1.1616
zP
z OR Normalcdf(-9999,16,16.1,0.15) = 0.2525
Answer the question.
There is a 25% chance that a single jar will contain less than 16 oz of peanuts.
Example: At the P. Nutty Peanut Company, dry-roasted, shelled
peanuts are placed in jars by a machine. The distribution of weights in
the jars is approximately Normal, with a mean of 16.1 ounces and a
standard deviation of 0.15 ounces.
(b) Find the probability of each event described.
2) randomly selecting 10 jars and finding that the average
contents weigh less than 16 ounces.
State the distribution and values of interest.
Let µ = the true average weight of 10 randomly selected jars of peanuts.
Thus has roughly N(16.1, 0.047)
Perform the calculations.
0166.0)13.2(
13.2047.0
1.1616
zP
z OR Normalcdf(-9999,16,6.1,0.047) = 0.0167
Answer the question.
There is a 2% chance that a random sample of 10 jars will contain less than 16 oz
of peanuts.
047.010
15.0
nx
x
1/12/2017
9
Example: Suppose that the number of texts sent during a typical day by a
randomly selected high school student follows a right-skewed distribution with
a mean of 45 and a standard deviation of 35.
Assuming that students at your school are typical texters, how likely is it that a
random sample of 50 students will have sent more than a total of 2500 texts in
the last 24 hours?
State the distribution and values of interest.
Let = true average number of texts sent by 50 randomly selected students.
Thus has roughly N(45, 4.95)
Check assumptions!
Problem stated randomly selected high school students
10%, the sample (50 students) is less than 10% of all students
95.450
35
nx
Since n = 50 and 50 > 30, we may use an approximately
normal distribution for the sampling distribution of x
Example: Suppose that the number of texts sent during a typical day by a
randomly selected high school student follows a right-skewed distribution with
a mean of 45 and a standard deviation of 35.
Assuming that students at your school are typical texters, how likely is it that a
random sample of 50 students will have sent more than a total of 2500 texts in
the last 24 hours?
State the distribution and values of interest.
Let = the true average number of texts sent by 50 randomly selected students.
Thus has roughly N(45, 4.95)
Perform the calculations.
1562.0)01.1(
01.195.4
4550
zP
z OR Normalcdf(50,1E99,45,4.95) = 0.1562
Answer the question.
There is a 16% chance that a random sample of 50 students will have sent over
2500 texts in the last 24 hours.
95.450
35
nx
What is the shape of the sampling distribution of
a mean when the sample is not taken from a
normally distributed population. Does the sample
size matter. Does the concept have a name.
Depends on either the size being large
enough (n>30) or on graphing the actual data
in a boxplot . . .
Try Practice problems on page 11
Review other practice problem in the packet
10-11
12 Internet exercise
13- more practice . . . Section Summary
In this section, we learned how to…
The Practice of Statistics, 5th Edition 54
FIND the mean and standard deviation of the sampling distribution of
a sample mean. CHECK the 10% condition before calculating the
standard deviation of a sample mean.
EXPLAIN how the shape of the sampling distribution of a sample
mean is affected by the shape of the population distribution and the
sample size.
If appropriate, use a Normal distribution to CALCULATE probabilities
involving sample means.
Sample Means