Sei sulla pagina 1di 20

Session 17

References

Probability and Statistical Course.

Instructor: Dr.Ing.(c) Sergio A. Abreo C.

Escuela de Ingenier´ıas El´ectrica, Electr´onica y de Telecomunicaciones

June 17, 2017

Connectivity and Signal Processing Research Group. info@cps.uis.edu.co https://cpsuis.wordpress.com

Session 17

References

Agenda

1 Session 17

2 References

Session 17

References

Test of Hypotheses for a single sample

Variance known
The test statistic for H 0 : µ = µ 0 is deﬁned as
¯
X − µ 0
Z 0 =
σ/ √ n

Two sided alternative

The alternative hypotheses is deﬁned as H 1 : µ

= µ 0

Figure: The distribution of Z 0 when H 0 : µ = µ 0 is true. Taken from [Montgomery and Runger, 2010]

Session 17

References

Test of Hypotheses for a single sample

Variance known
The test statistic for H 0 : µ = µ 0 is deﬁned as
¯
X − µ 0
Z 0 =
σ/ √ n

One sided alternative The alternative hypotheses is deﬁned as H 1 : µ > µ 0

Figure: The distribution of Z 0 when H 0 : µ = µ 0 is true. Taken from [Montgomery and Runger, 2010]

Session 17

References

Test of Hypotheses for a single sample

Variance known
The test statistic for H 0 : µ = µ 0 is deﬁned as
¯
X − µ 0
Z 0 =
σ/ √ n

One sided alternative The alternative hypotheses is deﬁned as H 1 : µ < µ 0

Figure: The distribution of Z 0 when H 0 : µ = µ 0 is true. Taken from [Montgomery and Runger, 2010]

Session 17

References

Test of Hypotheses for a single sample

P-values is the smallest level of signiﬁcance that would lead to rejection of the null hypothesis H 0 with the given data.

We may think of the P-value as the smallest level α at which the data are signiﬁcant.

If type I error is bigger than the signiﬁcance level (α > P value ) then H 0 would be rejected.

Once the P-value is known, the decision maker can determine how signiﬁcant the data are without the data analyst formally imposing a preselected level of signiﬁcance.

Session 17

References

Test of Hypotheses for a single sample

P value with H 0 : µ = µ 0

2[1 Φ(|z 0 |)] for a two-tailed test.

1 Φ(z 0 ) for a upper-tailed test.

Φ(z 0 ) for a lower-tailed test. H 1 : µ < µ 0

Here Φ(z) is the standard normal cumulative distribution function.

In other words the P value is the blue area.

H 1 : µ

= µ 0

H 1 : µ > µ 0

Session 17

References

Connection between Hypothesis Tests and Conﬁdence Intervals

100(1 − α)%
If [l, u] is a 100(1 − α)% conﬁdence interval
then α, the signiﬁcance level, is the blue area.
In this way if I chose a CI of 99% then P value = 0.01
When the type I error is bigger than P value then the CI is
lower than the desired value and H 0 is rejected.
Remember that CI for H 0 is computed as
σ
σ
x¯ − z α/2 √ n ≤ µ 0 ≤
x¯ + z α/2
n
Therefore H 0 will be rejected when µ 0 is out of the CI.

Session 17

References

Large Sample Test

CLT

We have developed the test procedure assuming that the population is normally distributed and that σ 2 is known.

Furthermore, we may not be certain that the population is well modeled by a normal distribution.

In these situations if n is large (say n > 40) the sample standard deviation s can be substituted for σ in the test procedures with little eﬀect.

This large-sample test relies on the central limit theorem.

Session 17

References

Hypotheses Test on the Mean

Variance unknown
The test statistic for H 0 : µ = µ 0 has a t distribution with n − 1
degrees of freedom and it is deﬁned as
¯
X − µ 0
T 0 =
S/ √ n

Two sided alternative

The alternative hypotheses is deﬁned as H 1 : µ

= µ 0

Figure: The distribution of T 0 when H 0 : µ = µ 0 is true. Taken from [Montgomery and Runger, 2010]

Session 17

References

Hypotheses Test on the Mean

Variance unknown
The test statistic for H 0 : µ = µ 0 has a t distribution with n − 1
degrees of freedom and it is deﬁned as
¯
X − µ 0
T 0 =
S/ √ n

One sided alternative The alternative hypotheses is deﬁned as H 1 : µ > µ 0

Figure: The distribution of T 0 when H 0 : µ = µ 0 is true. Taken from [Montgomery and Runger, 2010]

Session 17

References

Hypotheses Test on the Mean

Variance unknown
The test statistic for H 0 : µ = µ 0 has a t distribution with n − 1
degrees of freedom and it is deﬁned as
¯
X − µ 0
T 0 =
S/ √ n

One sided alternative The alternative hypotheses is deﬁned as H 1 : µ < µ 0

Figure: The distribution of T 0 when H 0 : µ = µ 0 is true. Taken from [Montgomery and Runger, 2010]

Session 17

References

Hypotheses Test on

The variance
2
The test statistic for H 0 : σ 2 = σ
deﬁned as
has a chi-squared distribution
0
= (n − 1)S 2
2
χ 0
2
σ
0

Two sided alternative

The alternative hypotheses is deﬁned as H 1 : σ 2 = σ

2

0

Figure: The distribution of χ 0 when H 0 : σ 2 = σ [Montgomery and Runger, 2010]

2

2

0

is true. Taken from

Session 17

References

Hypotheses Test on

The variance
2
The test statistic for H 0 : σ 2 = σ
deﬁned as
has a chi-squared distribution
0
= (n − 1)S 2
2
χ 0
2
σ
0

One sided alternative

The alternative hypotheses is deﬁned as H 1 : σ 2 > σ

2

0

Figure: The distribution of χ 0 when H 0 : σ 2 = σ [Montgomery and Runger, 2010]

2

2

0

is true. Taken from

Session 17

References

Hypotheses Test on

The variance
2
The test statistic for H 0 : σ 2 = σ
deﬁned as
has a chi-squared distribution
0
= (n − 1)S 2
2
χ 0
2
σ
0

One sided alternative

The alternative hypotheses is deﬁned as H 1 : σ 2 < σ

2

0

Figure: The distribution of χ 0 when H 0 : σ 2 = σ [Montgomery and Runger, 2010]

2

2

0

is true. Taken from

Session 17

References

Hypotheses Test on

The population The hypothesis-testing procedures that we have discussed previously are designed for problems in which the population or probability distribution is known and the hypotheses involve the parameters of the distribution.

Another kind of hypothesis is often encountered: we do not know the underlying distribution of the population, and we wish to test the hypothesis that a particular distribution will be satisfactory as a population model.

For example, we might wish to test the hypothesis that the population is normal.

Session 17

References

Test of Hypotheses

Exercise 1 The mean water temperature downstream from a power plant cooling tower discharge pipe should be no more than 100 o F. Past experience has indicated that the standard deviation of temperature is 2 o F. The water temperature is measured on nine randomly chosen days, and the average temperature is found to be 98 o F.

Should the water temperature be judged acceptable with α = 0.05.

What is the P-value for this test?

What is the probability of accepting the null hypothesis at α = 0.05 if the water has a true mean temperature of 104 o F?

Session 17

References

Test of Hypotheses

Exercise 2 The sodium content of thirty 300-gram boxes of organic corn ﬂakes was determined. The data (in milligrams) are as follows:

131.15, 130.69, 130.91, 129.54, 129.64, 128.77, 130.72, 128.33,
128.24, 129.65, 130.14, 129.29, 128.71, 129.00, 129.39, 130.42,
129.53, 130.12, 129.78, 130.92, 131.15, 130.69, 130.91, 129.54,
129.64, 128.77, 130.72, 128.33, 128.24, and 129.65.
Can you support a claim that mean sodium content of this
brand of cornﬂakes is 130 milligrams? Use α = 0.05.
Is there evidence that sodium content is normally distributed?
Compute the power of the test if the true mean sodium
content is 130.5 miligrams.
Explain how the ﬁrst question could be answered by
constructing a two-sided conﬁdence interval on the mean
sodium content.

Session 17

References

Test of Hypotheses

Exercise 3

A research engineer for a tire manufacturer is investigating tire life

for a new rubber compound and has built 16 tires and tested them

to end-of-life in a road test. The sample mean and standard

deviation are 60,139.7 and 3645.94

Can you conclude, using α = 0.05, that the standard deviation of tire life exceeds 200 kilometers? State any necessary assumptions about the underlying distribution of the data.

Find the P-value for this test.

Session 17

References

References I

Montgomery, D. C. and Runger, G. C. (2010). Applied statistics and probability for engineers. John Wiley & Sons.