Upload
others
View
2
Download
0
Embed Size (px)
Citation preview
DOE Basics in 90’
Eko Pujiyanto08122783991http://eko.staff.uns.ac.id
Out lines
Basic Principles Guidelines for Designing Experiments Experiment with a single Factor Randomized Block
http://eko.staff.uns.ac.id
Basic Principles
Randomization Running the trials in an experiment in random order
Notion of balancing out effects of “lurking” variables
Replication Sample size (improving precision of effect estimation,
estimation of error or background noise)
Replication versus repeat measurements?
Blocking Dealing with nuisance factors
http://eko.staff.uns.ac.id
Randomization
Simple Random Sampling
Permuted block randomization
Stratified Random Sampling.
http://eko.staff.uns.ac.id
Replication
Replication is the repetition of an experimental condition so that the variability associated with the phenomenon can be estimated.
Replication is not the same as repeated measurements
Replication reflects sources of variability both between runs and (potentially) within runs.
http://eko.staff.uns.ac.id
Blocking
Blocking is a design technique used to improve the precision with which comparisons among the factors of interest are made.
Blocking is used to reduce or eliminate the variability transmitted from nuisance factors—that is, factors that may influence the experimental response but in which we are not directly interested.
http://eko.staff.uns.ac.id
Guidelines for Designing Experiments
1. Recognition of the statement of problem
2. Selection of the response variable(s)
3. Choice of factors, levels, and ranges
4. Choice of design
5. Conducting the experiment
6. Statistical analysis
7. Drawing conclusions, recommendations
http://eko.staff.uns.ac.id
Selection of the response variable(s)
In selecting the response variable, the experimenter should be certain that this variable really provides useful information about the process under study.
Most often, the average or standard deviation (or both) of the measured characteristic will be the response variable.
http://eko.staff.uns.ac.id
Choice of factors, levels, and ranges
http://eko.staff.uns.ac.id
Choice of factors, levels, and ranges
http://eko.staff.uns.ac.id
Choice of factors, levels, and ranges
http://eko.staff.uns.ac.id
Experiment with a single Factor
An engineer is interested in investigating the relationship between the RF power setting and the etch rate for this tool.
The objective of an experiment like this is to specify the power setting that will give a desired target etch rate.
She wants to test four levels of RF power: 160, 180, 200, and 220 W.
She decided to test five wafers at each level of RF power.
http://eko.staff.uns.ac.id
Experiment with a single Factor
http://eko.staff.uns.ac.id
This is an example of a single-factor experiment with a 4 levels of the factor and n 5 replicates.
The 20 runs should be made in random order.
Experiment with a single Factor
http://eko.staff.uns.ac.id
The Analysis of Variance
http://eko.staff.uns.ac.id
The Analysis of Variance
http://eko.staff.uns.ac.id
The Analysis of Variance
http://eko.staff.uns.ac.id
The Plasma Etching Experiment
The Analysis of Variance
http://eko.staff.uns.ac.id
The Analysis of Variance
http://eko.staff.uns.ac.id
Randomized Block
http://eko.staff.uns.ac.id
Blocking is a technique for dealing with nuisancefactors
A nuisance factor is a factor that probably has some effect on the response, but it’s of no interest to the experimenter, however, the variability it transmits to the response needs to be minimized
Typical nuisance factors include batches of raw material, operators, pieces of test equipment and time
Randomized Block
http://eko.staff.uns.ac.id
Many industrial experiments involve blocking (or should)
Failure to block is a common flaw in designing an experiment (consequences?)
Hardness testing experiment
http://eko.staff.uns.ac.id
We wish to determine whether 4 different tips produce different (mean) hardness reading on a Rockwell hardness tester
Assignment of the tips to an experimental unit; that is, a test coupon
Hardness testing experiment
http://eko.staff.uns.ac.id
Structure of a completely randomized experiment
The test coupons are a source of nuisance variability
To conduct this experiment as a RCBD, assign all 4 tips to each coupon
Hardness testing experiment
http://eko.staff.uns.ac.id
Each coupon is called a “block”; that is, it’s a more homogenous experimental unit on which to test the tips
Variability between blocks can be large, variability within a block should be relatively small
Hardness testing experiment
http://eko.staff.uns.ac.id
In general, a block is a specific level of the nuisance factor
A complete replicate of the basic experiment is conducted in each block
A block represents a restriction on randomizationAll runs within a block are randomized
Hardness testing experiment
http://eko.staff.uns.ac.id
Anova to the RCBD
http://eko.staff.uns.ac.id
Suppose that there are a treatments (factor levels) and bblocks
A statistical model (effects model) for the RCBD is
The relevant (fixed effects) hypotheses are
1,2,...,
1,2,...,ij i j ij
i ay
j b
Anova to the RCBD
http://eko.staff.uns.ac.id
Anova to the RCBDExample : Vascular Graft Experiment
http://eko.staff.uns.ac.id
A medical device manufacturer produces vascular grafts (artificial veins). These grafts are produced by extruding billets of polytetrafluoroethylene (PTFE) resin combined with a
lubricant into tubes. Frequently, some of the tubes in a production run contain small, hard protrusions on the external surface.
Anova to the RCBDExample : Vascular Graft Experiment
http://eko.staff.uns.ac.id
Anova to the RCBDExample : Vascular Graft Experiment
http://eko.staff.uns.ac.id
http://eko.staff.uns.ac.id