Numerical &

IT Literacy
Lecture 7:
Confidence Intervals,
Hypotheses Tes>ng and
Test of Significance
 Learning Outcomes
In this slide, you learn:
• The proper>es of a confidence interval
• To do hypotheses tes>ng
• To do test of significance by using t-test

2
 Confidence Interval
• Confidence Intervals for the Popula>on Mean,
μ
– when Popula>on Standard Devia>on σ is Known

3
 Point and Interval Es>mates

• A point es>mate is a single number,

• a confidence interval provides addi>onal informa>on
about the variability of the es>mate

Lower Upper
Confidence Confidence
Point Estimate Limit
Limit
Width of
confidence interval
4
 Point Es>mates

We can estimate a with a Sample

Statistic
Population Parameter …
(a Point Estimate)

Mean µ X
Proportion π p

5
 Confidence Intervals

• How much uncertainty is associated with a

point es>mate of a popula>on parameter?

• An interval es>mate provides more

informa>on about a popula>on
characteris>c than does a point es>mate

• Such interval es>mates are called

confidence intervals

6
 Confidence Interval Es>mate
• An interval gives a range of values:
– Takes into considera>on varia>on in sample
sta>s>cs from sample to sample
– Based on observa>ons from 1 sample
– Gives informa>on about closeness to unknown
popula>on parameters
– Stated in terms of level of confidence
• e.g. 95% confident, 99% confident
• Can never be 100% confident
7
 Confidence Interval Example

Simple example
• Popula>on has µ = 368 and σ = 15.
• If you take a sample of size n = 25:
– if you already know µ = 368
• 368 ± 1.96 * 15 / 25= (362.12, 373.88) contains 95% of the sample
means
– When you don’t know µ, you use X to es>mate µ
• If X = 362.3 the interval is 362.3 ± 1.96 * 15 / 25 = (356.42, 368.18)
• If you es>mated the µ = 368, since 356.42 ≤ µ ≤ 368.18 the interval based on
this sample makes a correct statement about µ.

But what about the intervals from other possible samples of

size 25?
8
 Confidence Interval Example

Lower Upper Contain

Sample # X
Limit Limit µ?

1 362.30 356.42 368.18 Yes

2 369.50 363.62 375.38 Yes

3 360.00 354.12 365.88 No

4 362.12 356.24 368.00 Yes

5 373.88 368.00 379.76 Yes

9
 Es>ma>on Process

Random Sample I am 95%

confident that
µ is between
Population Mean 40 & 60.
(mean, µ, is X = 50
unknown)

Sample

10
 Confidence Level, (1-α)
• Suppose confidence level = 95%
• Also wrijen (1 - α) = 0.95, (so α = 0.05)
• A rela>ve frequency interpreta>on:
– 95% of all the confidence intervals that can
be constructed will contain the unknown true
parameter
• A specific interval either will contain or
will not contain the true parameter
– No probability involved in a specific interval
11
 Confidence Interval for μ
(σ Known)
• Assump>ons
– Popula>on standard devia>on σ is known
– Popula>on is normally distributed
– If popula>on is not normal, use large sample
• Confidence interval es>mate:

σ
X ± Z α/2
n
where X is the point es>mate
Zα/2 is the normal distribu>on cri>cal value for a probability of α/2 in each tail
σ/ n is the standard error

12
 Finding the Cri>cal Value, Zα/2
Zα/2 = ±1.96
• Consider a 95% confidence interval:
1 − α = 0.95 so α = 0.05

α α
= 0.025 = 0.025
2 2

Z units: Zα/2 = -1.96 0 Zα/2 = 1.96

Lower Upper
X units: Confidence Point Estimate Confidence
Limit Limit
13
• For 95%, the value to be checked from
normal table is 0.500 - 0.025 = 0.475

1.96

14
 Common Levels of Confidence
• Commonly used confidence levels are 90%,
95%, and 99%
Confidence
Confidence
Coefficient, Zα/2 value
Level
1− α
80% 0.80 1.28
90% 0.90 1.645
95% 0.95 1.96
98% 0.98 2.33
99% 0.99 2.58
99.8% 0.998 3.08
99.9% 0.999 3.27
15
• For 80%, 0.500 - 0.100 = 0.400
• For 90%, 0.500 - 0.050 = 0.450
• For 99%, 0.500 - 0.005 = 0.495

1.28

1.645

2.58

16
 Example

• A sample of 11 circuits from a large

normal popula>on has a mean resistance
of 2.20 ohms. We know from past tes>ng
that the popula>on standard devia>on is
0.35 ohms.

• Determine a 95% confidence interval for

the true mean resistance of the
popula>on.

17
 Example

• A sample of 11 circuits from a large normal

popula>on has a mean resistance of 2.20
ohms. We know from past tes>ng that the
popula>on standard devia>on is 0.35 ohms.
• Solu>on: X ± Z α/2
σ
n
= 2.20 ± 1.96 (0.35/ 11)
= 2.20 ± 0.2068
1.9932 ≤ µ ≤ 2.4068

18
 Interpreta>on

• We are 95% confident that the true mean

resistance is between 1.9932 and 2.4068
ohms
• Although the true mean may or may not be in
this interval, 95% of intervals formed in this
manner will contain the true mean

19
Hypotheses Tes>ng

20
 What is a Hypothesis?
• A hypothesis is a claim (assump>on) about a
popula>on parameter:

– popula>on mean
Example: The mean monthly cell phone bill
in this city is µ = $42
– popula>on propor>on

Example: The proportion of adults in this

city with cell phones is π = 0.68

21
 The Null Hypothesis, H0
• States the claim or asser>on to be tested
Example: The average number of TV sets in U.S.
Homes is equal to three ( H 0 : µ = 3)
• Is always about a popula>on parameter,
not about a sample sta>s>c

H0 : µ = 3 H0 : X = 3

22
 The Null Hypothesis, H0

• Begin with the assump>on that the null

hypothesis is true
– Similar to the no>on of innocent un>l
proven guilty

• Refers to the status quo or historical value

• Always contains “=” , “≤” or “≥” sign
• May or may not be rejected

23
The Alterna>ve Hypothesis, H1
• Is the opposite of the null hypothesis
– e.g., The average number of TV sets in U.S.
homes is not equal to 3 ( H1: μ ≠ 3 )
• Challenges the status quo
• Never contains the “=” , “≤” or “≥” sign
• May or may not be proven
• Is generally the hypothesis that the
researcher is trying to prove

24
The Hypothesis Tes>ng Process

• Claim: Assume that the popula>on mean age is 50.

– H0: μ = 50, H1: μ ≠ 50
• Sample the popula>on and find sample mean.

Population

Sample

25
 The Hypothesis Tes>ng Process

Sampling
Distribution of X

X
20 µ = 50
If H0 is true ... then you reject
If it is unlikely that you
the null hypothesis
would get a sample
that µ = 50.
mean of this value ... ... When in fact this were
the population mean…
26
 The Test Sta>s>c and
Cri>cal Values
Sampling Distribution of the test statistic

Region of Region of
Rejection Rejection
Region of
Non-Rejection

Critical Values

“Too Far Away” From Mean of Sampling Distribution

27
 Level of Significance
and the Rejec>on Region
H 0: µ = 3 Level of significance = α
H 1: µ ≠ 3
α /2 α /2

Critical values

Rejection Region

This is a two-tail test because there is a rejection region in both tails

28
 Z Test of Hypothesis for the Mean (σ
Known)
• Convert sample sta>s>c ( X ) to a ZSTAT test sta>s>c
Hypothesis
Tests for µ

σσKnown
Known σσUnknown
Unknown
(Z test) (t test)
The test statistic is:
X−µ
Z STAT =
σ
n
29
 Two-Tail Tests
H 0: µ = 3
n There are two
cutoff values H 1: µ ≠ 3
(critical values),
defining the
regions of α/2 α/2
rejection
3 X
Reject H0 Do not reject H0 Reject H0

-Zα/2 0 +Zα/2 Z

Lower Upper
critical critical
value value 30
 Hypothesis Tes>ng Example
Test the claim that the true mean # of TV sets
in US homes is equal to 3.
(Assume σ = 0.8)

1. State the appropriate null and alternative

hypotheses
n H 0: µ = 3 H1: µ ≠ 3 (This is a two-tail test)
2. Specify the desired level of significance and the
sample size
n Suppose that α = 0.05 and n = 100 are chosen

for this test

31
 Hypothesis Tes>ng Example
3. Determine the appropriate technique
n σ is assumed known so this is a Z test.

4. Determine the critical values

n For α = 0.05 the critical Z values are ±1.96

5. Collect the data and compute the test statistic

n Suppose the sample results are
n = 100, X = 2.84 (σ = 0.8 is assumed known)
So the test statistic is:
X − µ 2.84 − 3 − .16
Z STAT = = = = −2.0
σ 0.8 .08
n 100
32
 Hypothesis Tes>ng Example
• 6. Is the test sta>s>c in the rejec>on region?

α/2 = 0.025 α/2 = 0.025

Reject H0 if Reject H0 Do not reject H0 Reject H0

ZSTAT < -1.96 or -Zα/2 = -1.96 0 +Zα/2 = +1.96
ZSTAT > 1.96;
otherwise do
not reject H0 Here, ZSTAT = -2.0 < -1.96, so the
test statistic is in the rejection
region
33
 Hypothesis Tes>ng Example
6 (con>nued). Reach a decision and interpret the result

α = 0.05/2 α = 0.05/2

Reject H0 Do not reject H0 Reject H0

-Zα/2 = -1.96 0 +Zα/2= +1.96

-2.0

Since ZSTAT = -2.0 < -1.96, reject the null hypothesis

and conclude there is sufficient evidence that the mean
number of TVs in US homes is not equal to 3
34
Test of Significance

t-Test
 Difference Between Two Means

Population means, Goal: Test hypothesis or form

independent
samples
* a confidence interval for the
difference between two
population means, µ1 – µ2
σ1 and σ2 unknown,
assumed equal The point estimate for the
difference is

X1 – X2
σ1 and σ2 unknown,
not assumed equal
36
 Difference Between Two Means: Independent
Samples
• Different data sources
Population means, – Unrelated
independent
samples
* – Independent
• Sample selected from one
popula>on has no effect on the
sample selected from the other
popula>on
Use Sp to estimate unknown
σ1 and σ2 unknown, σ. Use a Pooled-Variance t
assumed equal test.

σ1 and σ2 unknown, Use S1 and S2 to estimate

not assumed equal unknown σ1 and σ2. Use a
Separate-variance t test 37
 Hypothesis Tests for
Two Popula>on Means
Two Population Means, Independent Samples

Lower-tail test: Upper-tail test: Two-tail test:

H 0: µ 1 ≥ µ 2 H 0: µ 1 ≤ µ 2 H 0: µ 1 = µ 2
H 1: µ 1 < µ 2 H 1: µ 1 > µ 2 H 1: µ 1 ≠ µ 2
i.e., i.e., i.e.,
H 0: µ 1 – µ 2 ≥ 0 H 0: µ 1 – µ 2 ≤ 0 H 0: µ 1 – µ 2 = 0
H 1: µ 1 – µ 2 < 0 H 1: µ 1 – µ 2 > 0 H 1: µ 1 – µ 2 ≠ 0

38
 Hypothesis tests for μ1 – μ2
Two Population Means, Independent Samples
Lower-tail test: Upper-tail test: Two-tail test:

H 0: µ 1 – µ 2 ≥ 0 H 0: µ 1 – µ 2 ≤ 0 H 0: µ 1 – µ 2 = 0
H 1: µ 1 – µ 2 < 0 H 1: µ 1 – µ 2 > 0 H 1: µ 1 – µ 2 ≠ 0
α α α/2 α/2

-tα tα -tα/2 tα/2

Reject H0 if tSTAT < -tα Reject H0 if tSTAT > tα Reject H0 if tSTAT < -tα/2
or tSTAT > tα/2

39
 Hypothesis tests for µ1 - µ2 with σ1 and σ2
unknown and assumed equal

Population means, Assumptions:

independent
§ Samples are randomly
samples and
independently drawn

σ1 and σ2 unknown,
assumed equal
* § Populations are normally
distributed or both sample
sizes are at least 30

§ Population variances are

σ1 and σ2 unknown, unknown but assumed
not assumed equal equal
40
 Hypothesis tests for µ1 - µ2 with σ1 and σ2
unknown and assumed equal

• The pooled variance is:

Population means, 2 2
independent S 2
=
(n1 − 1)S 1 + (n2 − 1)S 2
p
samples (n1 − 1) + (n2 − 1)

σ1 and σ2 unknown,
assumed equal
* ( X1 − X 2 ) − ( µ 1 − µ 2 )
•
t STAT The= test statistic is:
2 ⎛⎜ 1 1 ⎞
Sp ⎜ + ⎟
⎝ n1 n 2 ⎟⎠
σ1 and σ2 unknown,
not assumed equal
• Where tSTAT has d.f. = (n1 + n2 – 2) 41
 t Test Example
You are a financial analyst for a brokerage firm. Is there a
difference in dividend yield between stocks listed on the NYSE
& NASDAQ? You collect the following data:
NYSE NASDAQ
Number 21 25
Sample mean 3.27 2.53
Sample std dev 1.30 1.16

Assuming both populations are

approximately normal with equal
variances, is
there a difference in mean
yield (α = 0.05)?
42
 t Test Example:
Calcula>ng the Test Sta>s>c (continued)

H0: µ1 - µ2 = 0 i.e. (µ1 = µ2)

H1: µ1 - µ2 ≠ 0 i.e. (µ1 ≠ µ2)
The test statistic is:

t=
(X1 − X 2 ) − (µ1 − µ 2 )
=
(3.27 − 2.53) − 0 = 2.040
2 ⎛⎜ 1 1 ⎞ ⎛1 1 ⎞
Sp ⎜ + ⎟ 1.5021⎜ + ⎟
⎝ n1 n 2
⎟
⎠ ⎝ 21 25 ⎠

2 2
2 (n1 − 1)S1 + (n 2 − 1)S 2 (21 − 1)1.30 2 + (25 − 1)1.16 2
S =
p = = 1.5021
(n1 − 1) + (n2 − 1) (21- 1) + (25 − 1)
43
 Pooled-Variance t Test Example: Hypothesis Test
Solu>on
Reject H0 Reject H0
H0: μ1 - μ2 = 0 i.e. (μ1 = μ2)
H1: μ1 - μ2 ≠ 0 i.e. (μ1 ≠ μ2)
α = 0.05 .025 .025

df = 21 + 25 - 2 = 44 -2.0154 0 2.0154 t
CriPcal Values: t = ± 2.0154
2.040
Test StaPsPc: Decision:
3.27 − 2.53
t= = 2.040 Reject H0 at α = 0.05
⎛ 1 1⎞
Conclusion:
1.5021 ⎜ + ⎟
⎝ 21 25 ⎠ There is evidence of a
difference in means.
44
t = 2.021 – ((2.021-.
000)*4/20)
= 2.0168

45