Inferences About Process Quality

Chapter 4 Introduction to Statistical Quality Control, 6
th
Edition by Douglas C. Montgomery.
Copyright (c) 2009 J ohn Wiley & Sons, Inc.
1
th
2
Learning Objectives
th
3
4.1StatisticsandSamplingDistributions 4.1 Statistics and Sampling Distributions
Statistical inference is concerned with drawing g
conclusions about populations (or processes) based
on sample data from that system
Randomsample asamplethat isselectedsothat the Random sample a sample that is selected so that the
observations are independent a random sample has
the property that it has the same probability of
selectionasanyother sample selection as any other sample.
Statistic any function of the observations in a
sample that doesn't contain unknown parameters
The sample mean, the sample variance, and the
sample standard deviation are all statistics
th
4
Observations in a sample are used to draw p
conclusions about the population
th
5
SamplingDistributions Sampling Distributions
A statisticisarandomvariable becausea A statistic is a random variable, because a
different sample with produce a different
observedvalueof thestatistic observed value of the statistic
Every statistic has a probability distribution
Th b bili di ib i f i i i The probability distribution of a statistic is
called a sampling distribution
th
6
Sampling from a Normal Distribution
th
7
th
8
th
9
th
10
th
11
Sampling from a Bernoulli Distribution
th
12
Sampling from a Poisson Distribution
th
13
4.2Point Estimationof ProcessParameters 4.2 Point Estimation of Process Parameters
Distributionsaredescribedbytheir parameters Distributions are described by their parameters
Parameters are generally unknown and must be
estimated estimated
Point estimator a statistic that a single
i l l h i h i f h numerical value that is the estimate of the
parameter
Examples, page 110 & 111
th
14
Properties of Point Estimators
th
15
th
16
th
17
4.3Statistical Inferencefor aSingleSample 4.3 Statistical Inference for a Single Sample
Statistical inference=decisionmaking Statistical inference decision making
Hypothesis testing
N ll h th i H Null hypothesis, H
0
Alternative hypothesis, H
1
Confidence intervals
These two techniques are closely related q y
th
18
th
19
th
20
4.3.1 Inference on the Mean of a Population, Variance Known
th
21
th
22
Minitab
output
th
23
th
24
th
25
Upper and
lower
confidence
bounds
th
26
th
27
432P-Values 4.3.2P Values
th
28
th
29
4.3.3 Inference on the Mean of a Normal
Distribution, VarianceUnknown Distribution, Variance Unknown
th
30
Checking the normality assumption we will see how to do this in
Example 4.3
th
31
th
32
th
33
th
34
th
35
4.3.4 Inference on the Variance of a Normal Distribution
th
36
Upper and
lower
fid confidence
bounds
th
37
4.3.5 Inference on a Population Proportion
th
38
th
39
th
40
th
41
4.3.6TypeII Error andSampleSize 4.3.6 Type II Error and Sample Size
th
42
th
43
th
44
Minitab can perform sample size and power calculations. From
Example 4.7:
From Example 4.3:
th
45
th
46
4.4Statistical Inferencefor TwoSamples 4.4 Statistical Inference for Two Samples
Comparing means, comparing variances, comparing proportions
th
47
4.4.1 Inference on the Difference in Means, Variances Known
th
48
th
49
th
50
This is a two-sided CI. The one-sided confidence
bounds would be found by using only one of the bounds would be found by using only one of the
limits in Equation (4.49) with /2 replaced by .
th
51
4.4.2 Inference on the Difference in Means of
T N l Di ib i V i U k Two Normal Distributions, Variances Unknown
th
52
th
53
th
54
th
55
th
56
Confidence Intervals Case 1:
Case 2:
th
57
th
58
th
59
th
60
Paired Data:
th
61
4.4.3 Inference on the Variances of Two Normal Distributions
th
62
th
63
The two-sided CI is:
th
64
4.4.4 Inference on Two Proportions
th
65
th
66
th
67
4.5 What if There Are More Than Two Populations?
Th A l i f V i The Analysis of Variance
Example: Does changing the hardwood concentration in the pulp affect Example: Does changing the hardwood concentration in the pulp affect
the mean tensile strength of paper?
th
68
th
69
The Analysis of Variance (ANOVA)
th
70
The ANOVA is based on the following partitioning of the total sum of
squares (which measures the total variability in the sample data): q ( y p )
th
71
th
72
th
73
th
74
The ANOVA test statistic is:
If F is greater than the critical value F then the null If F
0
is greater than the critical value F
,a-1, a(n-1)
then the null
hypothesis of equal treatment means is rejected. A P-value
approach can also be used. The P-value would be the probability
above F
0
in the F
1 ( 1)
distribution
th
75
above F
0
in the F
a-1, a(n-1)
distribution.
th
76
th
77
Graphical comparison of individual means
20% hardwood produces higher mean strength than the p g g
others; 5% hardwood produces lower strength; 10% and
15% hardwood dont differ but give lower strength than 20%.
th
78
4.5.3CheckingAssumptions: Residual Analysis 4.5.3 Checking Assumptions: Residual Analysis
.
ij ij ij ij i
e y y y y
j j j j
th
79
Resid al Plots Residual Plots:
th
80
4.6 Linear Regression Models
th
81
Models that are not linear in the regressors can still be fit using linear Models that are not linear in the regressors can still be fit using linear
regression techniques, so long as they are linear in the parameters.
Important cases include models with interaction terms and
l i l polynomials.
th
82
th
83
The method of least squares:
Least
squares
l normal
equations
th
84
th
85
th
86
th
87
th
88
th
89
th
90
th
91
The test procedure is to calculate the test statistic
th
92
The regression sum of squares is
th
93
th
94
See Table 4.12
( lid 91) f th t (slide 91) for the t-
tests on the
individual
regressors in the
fi consumer finance
model both
variables are
significant
th
95
th
96
th
97
th
98
th
99
th
100
th
101
th
102
th
103
th
104
th
105
Other DiagnosticTools Other Diagnostic Tools
StandardizedandStudentizedresiduals Standardized and Studentized residuals
R-student an outlier diagnostic
h SS i i The PRESS statistic
R
2
for prediction based on PRESS a measure
of how well the model will predict new data
Measure of leverage hat diagonals g g
Cooks distance a measure of influence
th
106
th
107
Learning Objectives g j
th
108

Inferences About Process Quality

Caricato da

Informazioni sul documento

Copyright

Formati disponibili

Condividi questo documento

Condividi o incorpora il documento

Opzioni di condivisione

Hai trovato utile questo documento?

Questo contenuto è inappropriato?

Copyright:

Formati disponibili

Inferences About Process Quality

Caricato da

Copyright:

Formati disponibili

Chapter 4 Introduction to Statistical Quality Control, 6

Potrebbero piacerti anche