Statistical Inference For Two Samples PDF

Statistical Inference for Two Samples
Umi Yuliatin,M.Sc
PEM Akamigas
29 Januari 2020
Umi Yuliatin,M.Sc (PEM Akamigas) Statistical Inference for Two Samples 29 Januari 2020 1 / 16
Content:
1 Introduction
2 Inference for a Difference in Means of Two normal Distributions, Variances Known
3 Inference for a Difference in Means of Two normal Distributions, Variances

Unknown
σ12 = σ22 = σ2
σ12 6= σ22
Statistical Inference for Two Samples
Umi Yuliatin,M.Sc
PEM Akamigas
29 Januari 2020
Introduction
The previous chapter presented hypothesis tests for a single population parameter (the
mean µ, the variance σ2 , or a proportion p. This chapter extends those results to the
case of two independent populations.
Most of the practical applications of the procedures in this chapter arise in the context
of simple comparative experiments in which the objective is to study the difference in
the parameters of the two populations.
Inference for a Difference in Means of Two normal Distributions, Variances
Known
Inference for a Difference in Means of Two normal Distributions,

Variances Known
Assumptions
1 X11 , X12 , ..., X1n1 is a random sample from population 1.
2 X21 , X22 , ..., X2n2 is a random sample from population 2.
3 The two populations represented by X1 and X2 are independent.
4 Both populations are normal.
Known
Gambar: Two independent populations
Known
Suppose that we are interested in testing that the difference in means µ1 − µ2 is equal
to a specified ∆0 . Thus the null hypothesis and alternative hypothesis stated as
H0 : µ 1 − µ 2 = ∆ 0
H1 : µ 1 − µ 2 6 = ∆ 0
The standard normal distribution is the reference distribution for the statistics.
Known
Five-steps hypothesis testing for two means :

1 Hypotheses
µ1 − µ2 = ∆0 µ1 − µ2 ≤ ∆0 µ1 − µ2 ≥ ∆0
µ1 − µ2 6 = ∆0 µ1 − µ2 > ∆0 µ1 − µ2 < ∆0
2 Level significance α
3 Test statistics
x̄1 − x¯2 − ∆0
zcalc = s
σ12 σ2
+ 2
n1 n2
4 Critical region
Reject H0 if zcalc > Zα/2 or zcalc < −Zα/2
Reject H0 if zcalc > Zα
Reject H0 if zcalc < −Zα
5 Conclusion
Known
Example:
A product developer is interested in reducing the drying time of a primer paint. Two
formulations of the paint are tested; formulation 1 is the standard chemistry, and
formulation 2 has a new drying ingredient that should reduce the drying time. From
experience, it is known that the standard deviation of drying time is 8 minutes, and
this inherent variability should be unaffected by the addition of the new ingredient.
Ten specimens are painted with formulation 1, and another 10 specimens are painted
with formulation 2; the 20 specimens are painted in random order. The two sample
average drying times are x¯1 = 121 minutes and x¯2 = 112 minutes, respectively. What
conclusions can product developer draw about effectiveness of the new ingredient,
using α = 0.05?
Known
We apply five-steps procedures hypothesis testing:

1 Hypotheses:
µ1 − µ2 ≤ ∆0 µ1 − µ2 > ∆0
2 Level significance α = 0.05
3 Test statistics
x̄1 − x¯2 − ∆0
zcalc = s
σ12 σ2
+ 2
n1 n2
121 − 112
= r
82 82
+
10 10
= 2.52
4 Critical region
Reject H0 if zcalc > Zα/2 or zcalc < −Zα/2
Reject H0 if zcalc > Zα
Reject H0 if zcalc < −Zα
5 Conclusions
Unknown
Inference for a Difference in Means of Two normal Distributions,

Variances Unknown
when small samples are taken, we will assume that the populations are normally
distributed and base our hypotheses tests and confidence intervals on the t
distribution. This nicely parallels the case of inference on the mean of a single sample
with unknown variance. Hare are two conditions implied on test statistics.
1 Case 1 : σ12 = σ22 = σ2
2 Case 2 : σ12 6= σ22
Unknown σ2 = σ22 = σ2
1
σ12 = σ22 = σ2
Five-steps hypothesis testing for two means, variance unknown and σ12 = σ22 = σ2 :
1 Hypotheses:
µ1 − µ2 = ∆0 µ1 − µ2 ≤ ∆0 µ1 − µ2 ≥ ∆0
µ1 − µ2 6 = ∆0 µ1 − µ2 > ∆0 µ1 − µ2 < ∆0
3 Test statistics
x̄1 − x¯2 − ∆0
tcalc = r (1)
1 1
sp +
n1 n2
4 Critical region
Reject H0 if tcalc > tα/2,n1 +n2 −2 or tcalc < −tα/2,n1 +n2 −2
Reject H0 if tcalc > tα,n1 +n2 −2
Reject H0 if tcalc < −tα,n1 +n2 −2
5 Conclusion
The pooled estimator of σ2 , denoted by s2p is define by:
(n1 − 1)s21 + (n2 − 1)s22

s2p = (2)
n1 + n2 − 2
Unknown σ2 = σ22 = σ2
1
Example:
Two catalysts are being analyzed to determine how they affect the mean yield of a
chemical process. Specifically, catalyst 1 is currently in use, but catalyst 2 is acceptable.
Since catalyst 2 is cheaper, it should be adopted, providing it does not change the
process yield. A test is run in the pilot plant and results in the data shown in Table
bellow. Is there any difference between the mean yields? Use α = 0.05, and assume
equal variances.
Unknown σ2 6= σ22
1
σ12 6= σ22
In some situations, we cannot reasonably assume that the unknown variances σ12 and
σ22 are equal.
Five-steps hypothesis testing for two means, variance unknown and σ12 6= σ22 :
1 Hypotheses:
µ1 − µ2 = ∆0 µ1 − µ2 ≤ ∆0 µ1 − µ2 ≥ ∆0
µ1 − µ2 6 = ∆0 µ1 − µ2 > ∆0 µ1 − µ2 < ∆0
3 Test statistics
x̄1 − x¯2 − ∆0
tcalc = s (3)
s21 s2
+ 2
n1 n2
4 Critical region
Reject H0 if tcalc > tα/2,df or tcalc < −tα/2,df
Reject H0 if tcalc > tα,df
Reject H0 if tcalc < −tα,df
5 Conclusion
Unknown σ2 6= σ22
1
the df (degree of freedom) given by:

!
s21 s2
+ 2
n1 n2
v= (4)
(s21 /n1 )2 (s22 /n2 )2
+
n1 − 1 n2 − 1
Unknown σ2 6= σ22
1
example In semiconductor manufacturing, wet chemical etcing is often used to remove

silicon from the backs of wafers prior to metalization. The etch rate is an important
characteristic in this process and known to follow a normal distribution. Two different
etching solutions have been compared, using two random samples of 10 wafers for
each solution. The observes etch rates are as follows (in mils per minute):
Do the data support the claim that the mean etch rate is the same both solutions? In
reaching your conclusions, use α = 0.05 and assume that both population variances are
different.

Statistical Inference For Two Samples PDF

Uploaded by

Document Information

Original Title

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

Statistical Inference For Two Samples PDF

Uploaded by

Copyright:

Available Formats

Statistical Inference for Two Samples

2 Inference for a Difference in Means of Two normal Distributions, Variances Known

3 Inference for a Difference in Means of Two normal Distributions, Variances

Inference for a Difference in Means of Two normal Distributions,

Gambar: Two independent populations

Five-steps hypothesis testing for two means :

We apply five-steps procedures hypothesis testing:

Inference for a Difference in Means of Two normal Distributions,

(n1 − 1)s21 + (n2 − 1)s22

the df (degree of freedom) given by:

example In semiconductor manufacturing, wet chemical etcing is often used to remove

You might also like