hypothesis testing. to define a statistical test we 1.choose a statistic (called the test statistic)...
TRANSCRIPT
![Page 1: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/1.jpg)
Hypothesis Testing
![Page 2: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/2.jpg)
To define a statistical Test we
1. Choose a statistic (called the test statistic)
2. Divide the range of possible values for the test statistic into two parts
• The Acceptance Region
• The Critical Region
![Page 3: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/3.jpg)
To perform a statistical Test we
1. Collect the data.
2. Compute the value of the test statistic.
3. Make the Decision:
• If the value of the test statistic is in the Acceptance Region we decide to accept H0 .
• If the value of the test statistic is in the Critical Region we decide to reject H0 .
![Page 4: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/4.jpg)
The z-test for Proportions
Testing the probability of success in a binomial experiment
![Page 5: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/5.jpg)
Situation
• A success-failure experiment has been repeated n times
• The probability of success p is unknown. We want to test – H0: p = p0 (some specified value of p)
Against
– HA: 0pp
![Page 6: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/6.jpg)
The Test Statistic
n
pp
ppppz
p 00
0
ˆ
0
1
ˆ
ˆ
The Acceptance and Critical Region
• Accept H0 if:
• Reject H0 if:
2/2/ zzz
2/2/ or zzzz
Two-tailed critical region
![Page 7: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/7.jpg)
The Acceptance and Critical Region• Accept H0 if:
• Reject H0 if:
z zz z
One-tailed critical regions
These are used when the alternative hypothesis (HA) is one-sided
0 0 0i.e. : and :AH p p H p p
z z z z
0 0 0or if : and :AH p p H p p
• Accept H0 if:
• Reject H0 if:
![Page 8: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/8.jpg)
The Acceptance and Critical Region
Accept H0 if: , Reject H0 if:z z z z
One-tailed critical regions
0 0 0: and :AH p p H p p
![Page 9: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/9.jpg)
The Acceptance and Critical Region
Accept H0 if: , Reject H0 if:z z z z
One-tailed critical regions
0 0 0: and :AH p p H p p
![Page 10: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/10.jpg)
Comments
• Whether you use a one-tailed or a two-tailed tests is determined by the choice of the alternative hypothesis HA
• The alternative hypothesis, HA, is usually the research hypothesis. The hypothesis that the researcher is trying to “prove”.
![Page 11: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/11.jpg)
Examples
1. A person wants to determine if a coin should be accepted as being fair. Let p be the probability that a head is tossed.
One is trying to determine if there is a difference (positive or negative) with the fair value of p.
1 10 2 2: vs :AH p H p
![Page 12: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/12.jpg)
2. A researcher is interested in determining if a new procedure is an improvement over the old procedure. The probability of success for the old procedure is p0 (known). The probability of success for the new procedure is p (unknown) .
One is trying to determine if the new procedure is better (i.e. p > p0) .
0 0 0: vs :AH p p H p p
![Page 13: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/13.jpg)
2. A researcher is interested in determining if a new procedure is no longer worth considering. The probability of success for the old procedure is p0 (known). The probability of success for the new procedure is p (unknown) .
One is trying to determine if the new procedure is definitely worse than the one presently being used (i.e. p < p0) .
0 0 0: vs :AH p p H p p
![Page 14: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/14.jpg)
The z-test for the Mean of a Normal Population
We want to test, , denote the mean of a normal population
![Page 15: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/15.jpg)
The Situation
• Let x1, x2, x3 , … , xn denote a sample from a normal population with mean and standard deviation .
• Let
• we want to test if the mean, , is equal to some given value 0.
• Obviously if the sample mean is close to 0 the Null Hypothesis should be accepted otherwise the null Hypothesis should be rejected.
mean sample the1
n
xx
n
ii
![Page 16: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/16.jpg)
The Test Statistic
0 0 x
x xz
n
0 x
n
0 x
ns
![Page 17: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/17.jpg)
The Acceptance and Critical RegionThis depends on H0 and HA
• Accept H0 if:
• Reject H0 if:
2/2/ zzz
2/2/ or zzzz
Two-tailed critical region
0 0 0: and :AH H
• Accept H0 if:
• Reject H0 if:
One-tailed critical regions0 0 0: and :AH H
z zz z
• Accept H0 if:
• Reject H0 if:
0 0 0: and :AH H
z zz z
![Page 18: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/18.jpg)
Example
A manufacturer Glucosamine capsules claims that each capsule contains on the average:
• 500 mg of glucosamine
To test this claim n = 40 capsules were selected and amount of glucosamine (X) measured in each capsule.
Summary statistics:
496.3 and 8.5x s
![Page 19: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/19.jpg)
We want to test:
Manufacturers claim is correct
against
0 :H
:AH Manufacturers claim is not correct
![Page 20: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/20.jpg)
The Test Statistic
s
xn
xn
n
xxz
x
0000
496.3 500 40
8.52.75
![Page 21: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/21.jpg)
The Critical Region and Acceptance Region
Using = 0.05
We accept H0 if-1.960 ≤ z ≤ 1.960
z/2 = z0.025 = 1.960
reject H0 ifz < -1.960 or z > 1.960
![Page 22: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/22.jpg)
The Decision
Sincez= -2.75 < -1.960
We reject H0
Conclude: the manufacturers’s claim is incorrect:
![Page 23: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/23.jpg)
“Students” t-test
![Page 24: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/24.jpg)
Recall: The z-test for means
ns
x
n
xxz
x
000
The Test Statistic
![Page 25: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/25.jpg)
Comments
• The sampling distribution of this statistic is the standard Normal distribution
• The replacement of by s leaves this distribution unchanged only the sample size n is large.
![Page 26: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/26.jpg)
For small sample sizes:
ns
xt 0
The sampling distribution of
Is called “students” t distribution with n –1 degrees of freedom
![Page 27: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/27.jpg)
Properties of Student’s t distribution
• Similar to Standard normal distribution– Symmetric– unimodal– Centred at zero
• Larger spread about zero.– The reason for this is the increased variability introduced
by replacing by s.
• As the sample size increases (degrees of freedom increases) the t distribution approaches the standard normal distribution
![Page 28: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/28.jpg)
-4 -2 2 4
0.1
0.2
0.3
0.4
![Page 29: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/29.jpg)
t distribution
standard normal distribution
![Page 30: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/30.jpg)
The Situation
• Let x1, x2, x3 , … , xn denote a sample from a normal population with mean and standard deviation . Both and are unknown.
• Let
• we want to test if the mean, , is equal to some given value 0.
mean sample the1
n
xx
n
ii
deviation standard sample the
11
2
n
xxs
n
ii
![Page 31: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/31.jpg)
The Test Statistic
ns
xt 0
The sampling distribution of the test statistic is the t distribution with n-1 degrees of freedom
![Page 32: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/32.jpg)
The Alternative Hypothesis HA
The Critical Region
0: AH
0: AH
0: AH
2/2/ or tttt
tt
tt
t and t/2 are critical values under the t distribution with n – 1 degrees of freedom
![Page 33: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/33.jpg)
Critical values for the t-distribution
or /2
0 t
tt or 2/
![Page 34: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/34.jpg)
Critical values for the t-distribution are provided in tables. A link to these tables are given with today’s lecture
![Page 35: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/35.jpg)
Look up df
Look up
![Page 36: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/36.jpg)
Note: the values tabled for df = ∞ are the same values for the standard normal distribution
![Page 37: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/37.jpg)
Example
• Let x1, x2, x3 , x4, x5, x6 denote weight loss from a new diet for n = 6 cases.
• Assume that x1, x2, x3 , x4, x5, x6 is a sample from a normal population with mean and standard deviation . Both and are unknown.
• we want to test:
0: AH
0:0 H
versus
New diet is not effective
New diet is effective
![Page 38: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/38.jpg)
The Test Statistic
ns
xt 0
The Critical region:
tt Reject if
![Page 39: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/39.jpg)
The Data
The summary statistics:
462418.1 and 96667.0 sx
1 2 3 4 5 6
2.0 1.0 1.4 -1.8 0.9 2.3
![Page 40: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/40.jpg)
The Test Statistic
619.1
6462418.1
096667.00
ns
xt
The Critical Region (using = 0.05)
d.f. 5for 0152050 .tt . Reject if
Conclusion: Accept H0:
![Page 41: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/41.jpg)
Confidence Intervals
![Page 42: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/42.jpg)
Confidence Intervals for the mean of a Normal Population, m, using the Standard Normal distribution
nzx
2/
Confidence Intervals for the mean of a Normal Population, m, using the t distribution
n
stx 2/
![Page 43: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/43.jpg)
The Data
The summary statistics:
462418.1 and 96667.0 sx
1 2 3 4 5 6
2.0 1.0 1.4 -1.8 0.9 2.3
![Page 44: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/44.jpg)
Example
• Let x1, x2, x3 , x4, x5, x6 denote weight loss from a new diet for n = 6 cases.
The Data:
The summary statistics:
462418.1 and 96667.0 sx
1 2 3 4 5 6
2.0 1.0 1.4 -1.8 0.9 2.3
![Page 45: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/45.jpg)
Confidence Intervals (use = 0.05)
n
stx 025.0
6
462418.1571.296667.0
535.196667.0
50.2 to57.0
![Page 46: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/46.jpg)
Comparing Populations
Proportions and means
![Page 47: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/47.jpg)
Sums, Differences, Combinations of R.V.’s
A linear combination of random variables, X, Y, . . . is a combination of the form:
L = aX + bY + …
where a, b, etc. are numbers – positive or negative.
Most common:Sum = X + Y Difference = X – Y
Simple Linear combination of X, bX + a
![Page 48: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/48.jpg)
Means of Linear Combinations
The mean of L is:
Mean(L) = a Mean(X) + b Mean(Y) + …
Most common:
Mean( X + Y) = Mean(X) + Mean(Y)
Mean(X – Y) = Mean(X) – Mean(Y)
Mean(bX + a) = bMean(X) + a
If L = aX + bY + …
![Page 49: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/49.jpg)
Variances of Linear Combinations
If X, Y, . . . are independent random variables and
L = aX + bY + … then
Variance(L) = a2 Variance(X) + b2 Variance(Y) + …
Most common:
Variance( X + Y) = Variance(X) + Variance(Y)
Variance(X – Y) = Variance(X) + Variance(Y)
Variance(bX + a) = b2Variance(X)
![Page 50: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/50.jpg)
If X, Y, . . . are independent normal random variables, then L = aX + bY + … is normally distributed.
In particular:
X + Y is normal with
X – Y is normal with
Combining Independent Normal Random Variables
22 deviation standard
mean
YX
YX
22 deviation standard
mean
YX
YX
![Page 51: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/51.jpg)
Comparing proportions
Situation• We have two populations (1 and 2)• Let p1 denote the probability (proportion) of
“success” in population 1.• Let p2 denote the probability (proportion) of
“success” in population 2.• Objective is to compare the two population
proportions
![Page 52: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/52.jpg)
We want to test either:
21210 : vs: .1 ppHppH A
21210 : vs: .2 ppHppH A
21210 : vs: .3 ppHppH A
or
or
![Page 53: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/53.jpg)
The test statistic:
ˆ1ˆˆ1ˆ
ˆˆ
ˆˆ
1
11
1
11
21
ˆˆ
21
21
npp
npp
ppppz
pp
![Page 54: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/54.jpg)
Where:
A sample of n1 is selected from population 1 resulting in x1 successes
A sample of n2 is selected from population 2 resulting in x2 successes
2
22
1
11
ˆ and
ˆ
n
xp
n
xp
![Page 55: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/55.jpg)
Logic:
1
1
11ˆ1 n
ppp
2ˆ
2ˆˆˆ 2121 pppp
1
1
22ˆ2 n
ppp
11
2
22
1
11
n
pp
n
pp
pppnn
pp
21
21
if 11
1
11
ˆ1ˆ 21
nnpp
![Page 56: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/56.jpg)
The Alternative Hypothesis HA
The Critical Region
21: ppH A
21: ppH A
21: ppH A
2/2/ or zzzz
zz
zz
![Page 57: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/57.jpg)
Example• In a national study to determine if there was an
increase in mortality due to pipe smoking, a random sample of n1 = 1067 male nonsmoking pensioners were observed for a five-year period.
• In addition a sample of n2 = 402 male pensioners who had smoked a pipe for more than six years were observed for the same five-year period.
• At the end of the five-year period, x1 = 117 of the nonsmoking pensioners had died while x2 = 54 of the pipe-smoking pensioners had died.
• Is there a the mortality rate for pipe smokers higher than that for non-smokers
![Page 58: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/58.jpg)
We want to test:
21210 : vs: ppHppH A
![Page 59: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/59.jpg)
The test statistic:
11ˆ1ˆ
ˆˆ
ˆˆ
21
21
ˆˆ
21
21
nnpp
ppppz
pp
![Page 60: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/60.jpg)
Note:
1097.01067
117
ˆ
1
11
n
xp
1343.0402
54 ˆ
2
22
n
xp
4021067
54117 ˆ
21
21
nn
xxp
1164.01469
171
![Page 61: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/61.jpg)
The test statistic:
11ˆ1ˆ
ˆˆ
21
21
nnpp
ppz
4021
10671
1164.011164.0
1343.1097.0
315.1
![Page 62: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/62.jpg)
We reject H0 if:
645.1 05.0 zzz
Not true hence we accept H0.
Conclusion: There is not a significant ( = 0.05) increase in the mortality rate due to pipe-smoking
![Page 63: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/63.jpg)
Estimating a difference proportions using confidence intervals
Situation• We have two populations (1 and 2)• Let p1 denote the probability (proportion) of
“success” in population 1.• Let p2 denote the probability (proportion) of
“success” in population 2.• Objective is to estimate the difference in the
two population proportions = p1 – p2.
![Page 64: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/64.jpg)
Confidence Interval for = p1 – p2
100P% = 100(1 – ) % :
ˆˆ21 ˆˆ2/21 ppzpp
2
22
1
112/21
ˆ1ˆˆ1ˆ ˆˆ
n
pp
n
ppzpp
![Page 65: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/65.jpg)
Example• Estimating the increase in the mortality rate
for pipe smokers higher over that for non-smokers = p2 – p1
2
22
1
112/12
ˆ1ˆˆ1ˆ ˆˆ
n
pp
n
ppzpp
402
1343.011343.0
1067
1097.011097.0 960.11097.01343.0
0382.00247.0
0629.0 to0136.0%29.6 to%36.1
![Page 66: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/66.jpg)
Comparing MeansSituation• We have two normal populations (1 and 2)• Let 1 and 1 denote the mean and standard
deviation of population 1.• Let 2 and 2 denote the mean and standard
deviation of population 1.• Let x1, x2, x3 , … , xn denote a sample from a
normal population 1.• Let y1, y2, y3 , … , ym denote a sample from a
normal population 2.• Objective is to compare the two population means
![Page 67: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/67.jpg)
We want to test either:
21210 : vs: .1 AHH
21210 : vs: .2 AHHor
21210 : vs: .3 AHH
or
![Page 68: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/68.jpg)
Consider the test statistic:
22yxyx
yxyxz
m
s
ns
yx
mn
yx
yx222
221
![Page 69: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/69.jpg)
If: trueis : 210 H
• will have a standard Normal distribution
• This will also be true for the approximation (obtained by replacing 1 by sx and 2 by sy) if the sample sizes n and m are large (greater than 30)
m
s
ns
yx
mn
yxz
yx222
221
![Page 70: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/70.jpg)
Note:
n
xx
n
ii
1
11
2
n
xxs
n
ii
x
m
yy
n
ii
1
11
2
m
yys
n
ii
y
![Page 71: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/71.jpg)
The Alternative Hypothesis HA
The Critical Region
21: AH
21: AH
21: AH
2/2/ or zzzz
zz
zz
![Page 72: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/72.jpg)
Example• A study was interested in determining if an
exercise program had some effect on reduction of Blood Pressure in subjects with abnormally high blood pressure.
• For this purpose a sample of n = 500 patients with abnormally high blood pressure were required to adhere to the exercise regime.
• A second sample m = 400 of patients with abnormally high blood pressure were not required to adhere to the exercise regime.
• After a period of one year the reduction in blood pressure was measured for each patient in the study.
![Page 73: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/73.jpg)
We want to test:
210 : H
The exercize group did not have a higher
average reduction in blood pressure
The exercize group did have a higher
average reduction in blood pressure
21: AHvs
![Page 74: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/74.jpg)
The test statistic:
22yxyx
yxyxz
m
s
ns
yx
mn
yx
yx222
221
![Page 75: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/75.jpg)
Suppose the data has been collected and:
67.101
n
xx
n
ii
895.3
11
2
n
xxs
n
ii
x
83.71
m
yy
n
ii
224.4
11
2
m
yys
n
ii
y
![Page 76: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/76.jpg)
The test statistic:
400224.4
500895.3
83.767.10
2222
m
s
ns
yxz
yx
4.10273765.0
84.2
![Page 77: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/77.jpg)
We reject H0 if:
645.1 05.0 zzz
True hence we reject H0.
Conclusion: There is a significant ( = 0.05) effect due to the exercise regime on the reduction in Blood pressure
![Page 78: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/78.jpg)
Estimating a difference means using confidence intervals
Situation
• We have two populations (1 and 2)
• Let 1 denote the mean of population 1.
• Let 2 denote the mean of population 2.
• Objective is to estimate the difference in the two population proportions = 1 – 2.
![Page 79: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/79.jpg)
Confidence Interval for
= 1 – 2
ˆˆ21 ˆˆ2/21 z
m
s
n
szyx yx
22
2/
![Page 80: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/80.jpg)
Example• Estimating the increase in the average
reduction in Blood pressure due to the excercize regime = 1 – 2
m
s
n
szyx yx
22
2/
400
224.4
500
895.3 960.183.767.10
22
)273765(.96.184.2 537.0.842
.3373 to.3032
![Page 81: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/81.jpg)
Comparing Means – small samplesSituation• We have two normal populations (1 and 2)• Let 1 and 1 denote the mean and standard
deviation of population 1.• Let 2 and 2 denote the mean and standard
deviation of population 1.• Let x1, x2, x3 , … , xn denote a sample from a
normal population 1.• Let y1, y2, y3 , … , ym denote a sample from a
normal population 2.• Objective is to compare the two population means
![Page 82: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/82.jpg)
We want to test either:
21210 : vs: .1 AHH
21210 : vs: .2 AHH
21210 : vs: .3 AHH
or
or
![Page 83: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/83.jpg)
Consider the test statistic:
22yxyx
yxyxz
m
s
ns
yx
mn
yx
yx222
221
![Page 84: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/84.jpg)
If the sample sizes (m and n) are large the statistic
m
s
ns
yxt
yx22
will have approximately a standard normal distribution
This will not be the case if sample sizes (m and n) are small
![Page 85: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/85.jpg)
The t test – for comparing means – small samples
Situation• We have two normal populations (1 and 2)• Let 1 and denote the mean and standard
deviation of population 1.• Let 2 and denote the mean and standard
deviation of population 1.• Note: we assume that the standard deviation
for each population is the same.
1 = 2 =
![Page 86: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/86.jpg)
Let
n
xx
n
ii
1
11
2
n
xxs
n
ii
x
m
yy
n
ii
1
11
2
m
yys
n
ii
y
![Page 87: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/87.jpg)
The pooled estimate of .
2
11 22
mn
smsns yx
Pooled
Note: both sx and sy are estimators of .
These can be combined to form a single
estimator of , sPooled.
![Page 88: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/88.jpg)
The test statistic:
mns
yx
ms
ns
yxt
PooledPooledPooled
11
22
If 1 = 2 this statistic has a t distribution with n + m –2 degrees of freedom
![Page 89: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/89.jpg)
The Alternative Hypothesis HA
The Critical Region
21: AH
21: AH
21: AH
2/2/ or tttt
tt
tt
tt and 2/
are critical points under the t distribution with degrees of freedom n + m –2.
![Page 90: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/90.jpg)
Example• A study was interested in determining if
administration of a drug reduces cancerous tumor size.
• For this purpose n +m = 9 test animals are implanted with a cancerous tumor.
• n = 3 are selected at random and administered the drug.
• The remaining m = 6 are left untreated. • Final tumour sizes are measured at the end
of the test period
![Page 91: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/91.jpg)
We want to test:
210 : H
21: AH
The treated group did not have a lower
average final tumour size.
The exercize group did have a lower
average final tumour size.
vs
![Page 92: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/92.jpg)
The test statistic:
mns
yxt
Pooled
11
![Page 93: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/93.jpg)
Suppose the data has been collected and:
657.11
n
xx
n
ii
3215.01
1
2
n
xxs
n
ii
x
915.11
m
yy
n
ii
3693.01
1
2
m
yys
n
ii
y
drug treated 1.89 1.79 1.29untreated 2.08 1.28 1.75 1.90 2.32 2.16
![Page 94: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/94.jpg)
The test statistic:
025.1252.
258.
61
31
3563.0
915.1657.1
t
2
11 22
mn
smsns yx
Pooled
3563.0
7
3693.053215.02 22
![Page 95: Hypothesis Testing. To define a statistical Test we 1.Choose a statistic (called the test statistic) 2.Divide the range of possible values for the test](https://reader030.vdocuments.site/reader030/viewer/2022032701/56649c6f5503460f94921eae/html5/thumbnails/95.jpg)
We reject H0 if:
895.1 050 .ttt
Hence we accept H0.
Conclusion: The drug treatment does not result in a significant ( = 0.05) smaller final tumour size,
with d.f. = n + m – 2 = 7