Scribd
Upload
20 views22 pages

Lecture 11 - Linear Regression

The document provides an overview of experimental analysis and design, focusing on hypothesis testing for means of normal distributions and the analysis of variance (ANOVA). It details various methods for comparing means, including single mean comparisons, two means, and paired comparisons, as well as the structure and criteria for conducting ANOVA in different experimental designs. Examples illustrate the application of these statistical methods in real-world scenarios.

Uploaded by

EDISON LIMBAGA
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
20 views22 pages

Lecture 11 - Linear Regression

The document provides an overview of experimental analysis and design, focusing on hypothesis testing for means of normal distributions and the analysis of variance (ANOVA). It details various methods for comparing means, including single mean comparisons, two means, and paired comparisons, as well as the structure and criteria for conducting ANOVA in different experimental designs. Examples illustrate the application of these statistical methods in real-world scenarios.

Uploaded by

EDISON LIMBAGA
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 22

Experimental Analysis and

Design

Analysis of Variance

PROF. GEVELYN B. ITAO


Doctor in Sustainable Engineering (Environmental
Engineering)
Experimental Analysis and Design
Hypothesis Testing for Means of Normal Distributions:
A. Comparing a Single Mean to a Specified Value
Experimental Analysis and Design
Hypothesis Testing for Means of Normal Distributions:
B. Comparing Two Means
Experimental Analysis and Design
Hypothesis Testing for Means of Normal Distributions:
B. Comparing Two Means
Experimental Analysis and Design
Hypothesis Testing for Means of Normal Distributions:
C. Paired Comparison
Experimental Analysis and Design
Simple Linear Regression and Correlation
Test of linear association:

1. H0:  = 0
2. H1:   0
3.  = 0.05

4. Critical region: or

5. Computations:

6. Decision
Experimental Analysis and Design
Analysis of Variance (ANOVA)

➢ is used to deal problems that involves one or more


factor with more than two levels and thus more
than two samples.
e.g. in testing population means where k > 2,
there are k samples from k populations.
Experimental Analysis and Design
Analysis of Variance (ANOVA)

The model for this is as follows:

𝑯 𝒐 : 𝝁𝟏 = 𝝁𝟐 = 𝝁𝟑 … = 𝝁𝒌

𝑯𝟏 : 𝑨𝒕 𝒍𝒆𝒂𝒔𝒕 𝒕𝒘𝒐 𝒐𝒇 𝒕𝒉𝒆 𝒎𝒆𝒂𝒏𝒔 𝒂𝒓𝒆 𝒏𝒐𝒕 𝒆𝒒𝒖𝒂𝒍.

✓ It is assumed that k populations are independent


and normally distributed with means
𝝁 𝟏 , 𝝁𝟐 , 𝝁 𝟑 , … , 𝝁𝒌
and common variance σ2.
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Completely Randomized Experiment: Data Organization

Treatment
Observations Totals Averages
(level)
1 y11 y12 ... y1n y1.
2 y21 y22 ... y2n y2.
. . . ... . . .
. . . ... . . .
. . . ... . . .
a ya1 ya2 ... yan ya.
y..

Treatment
level
Observation
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Completely Randomized Experiment: ANOVA

Source of Sum of Degrees Mean Fo f(v1, v2)


Variation Squares of Square
Freedom

Between
treatments SSTreatments a–1 MSTreatments

Error SSE N–a MSE


Total SST N–1

Criteria:
▪ If F0 > f, there is a significant difference between treatment levels.
Otherwise, there is no significant difference between treatment levels
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Completely Randomized Experiment:
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Completely Randomized Experiment: Data Organization
Example 10.1: A development engineer is interested in
determining if varying the cotton content in a synthetic
fiber affects the tensile strength, and he has run a
completely randomized experiment with five levels of
cotton percentage and five replicates.
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Completely Randomized Experiment: Data Organization
Example 1:
Observed tensile strength
Percentage Totals
(lb/in2) Averages
of cotton yi
1 2 3 4 5
15 7 7 15 11 9 49 9.8
20 12 17 12 18 18 77 15.4
25 14 18 18 19 19 88 17.6
30 19 25 22 19 23 108 21.6
35 7 10 11 15 11 54 10.8
y.. = 376 15.04
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Randomized Block Design with 1 nuisance factor: Data
Organization
Example 2: An experiment is run to test four different types of tip of a
hardness testing machine. The machine operates by pressing the tip into a
metal test coupon, and from the depth of the resulting depression, the
hardness of the coupon is determined. Determine whether the four types
of tip differ significantly in their reading of hardness.

Types of Test Coupon Average


Tip 1 2 3 4
1 9.3 9.4 9.6 10.0 9.58
2 9.4 9.3 9.8 9.9 9.64
3 9.2 9.4 9.5 9.7 9.45
4 9.7 9.6 10.0 10.2 9.80
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Randomized Block Design with 1 nuisance factor: ANOVA

Source of Sum of Degrees of Mean


F0 f(v1,v2)
Variation Squares freedom Square

Treatments SSTreatments a–1 MSTreatments

Blocks SSBlocks b–1 MSBlocks


Error SSE (a – 1)(b - 1) MSE
Total SST N–1
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Randomized Block Design with 1 nuisance factor: ANOVA
Experimental Analysis and Design
Analysis of Variance (ANOVA)
Single-Factor Randomized Block Design with 1 nuisance factor: ANOVA
Probability and Statistics
Analysis of Variance (ANOVA)
Two-Factor Factorial Design (replicated): Data Organization
Example 3: An engineer wanted to test the effect of three plate materials
at three temperature levels on the life of a battery. Four batteries are
tested at each combination of plate material and temperature, and all 36
tests are run in random order. The data of the experiment is summarized
in the table:
Probability and Statistics
Analysis of Variance (ANOVA)
Two-Factor Factorial Design (replicated): Data Organization
Example 3:

Material Temperature (oF) [B]


Type [A] 15 70 125
130 155 34 40 20 70
1
74 180 80 75 82 58
150 188 126 122 25 70
2
159 126 106 115 58 45
138 110 174 120 96 104
3
168 160 150 139 82 60
Probability and Statistics
Analysis of Variance (ANOVA)
Two-Factor Factorial Design (replicated): ANOVA
Source of Sum of Degrees of Mean
F0 f(v1,v2)
Variation Squares freedom Square
A
SSA a–1 MSA f[(a-1),ab(n-1)]
Treatments
B
SSB b–1 MSB f[(b-1),ab(n-1)]
Treatments
Interaction SSAB (a – 1)(b - 1) MSAB f[(a-1)(b-1),ab(n-1)]
Error SSE ab(n – 1) MSE
Total SST N–1
Probability and Statistics
Analysis of Variance (ANOVA)
Two-Factor Factorial Design (replicated): ANOVA
Probability and Statistics
Analysis of Variance (ANOVA)
Two-Factor Factorial Design (replicated): ANOVA
Example 3:
Source of Sum of Degrees of Mean
F0 F0.05(v1,v2)
Variation Squares freedom Square
Material Type 10,683.72 2 5,341.86 7.91 3.35

Temperature 39,118.72 2 19,558.36 28.97 3.35


Interaction 9,613.78 4 2,403.44 3.56 2.73
Error 18,230.75 27 675.21
Total 77,646.97 35

You might also like