CPE 619 2k-p Factorial DesignPART IV: Experimental Design and AnalysisIntroduction2k-p Fractional Factorial DesignsExample: 27-4 DesignFractional Design FeaturesAnalysis of Fractional Factorial DesignsExample 19.1Sign Table for a 2k-p DesignExample: 27-4 DesignExample: 24-1 DesignConfoundingConfounding (cont’d)Slide 14Other Fractional Factorial DesignsAlgebra of ConfoundingAlgebra of Confounding (cont’d)Example 19.7Example 19.7 (cont’d)Design ResolutionDesign Resolution (cont’d)Case Study 19.1: Latex vs. troffCase Study 19.1 (cont’d)Case Study 19.1: ConclusionsCase Study 19.1: Conclusions (cont’d)Case Study 19.2: Scheduler DesignMeasured ThroughputsEffects and Variation ExplainedCase Study 19.2: ConclusionsSummaryExercise 19.1Exercise 19.2HomeworkCPE 6192k-p Factorial DesignAleksandar MilenkovićThe LaCASA LaboratoryElectrical and Computer Engineering DepartmentThe University of Alabama in Huntsvillehttp://www.ece.uah.edu/~milenkahttp://www.ece.uah.edu/~lacasa2PART IV: Experimental Design and AnalysisHow to:Design a proper set of experiments for measurement or simulationDevelop a model that best describes the data obtainedEstimate the contribution of each alternative to the performanceIsolate the measurement errorsEstimate confidence intervals for model parametersCheck if the alternatives are significantly differentCheck if the model is adequate3Introduction2k-p Fractional Factorial DesignsSign Table for a 2k-p Design ConfoundingOther Fractional Factorial DesignsAlgebra of ConfoundingDesign Resolution42k-p Fractional Factorial DesignsLarge number of factors ) large number of experiments ) full factorial design too expensive ) Use a fractional factorial design 2k-p design allows analyzing k factors with only 2k-p experiments2k-1 design requires only half as many experiments2k-2 design requires only one quarter of the experiments5Example: 27-4 DesignStudy 7 factors with only 8 experiments!6Fractional Design FeaturesFull factorial design is easy to analyze due to orthogonality of sign vectorsFractional factorial designs also use orthogonal vectorsThat isThe sum of each column is zeroi xij =0 8 jjth variable, ith experimentThe sum of the products of any two columns is zeroi xijxil=0 8 j l The sum of the squares of each column is 27-4, that is, 8i xij2 = 8 8 j7Analysis of Fractional Factorial DesignsModel:Effects can be computed using inner products8Example 19.1Factors A through G explain 37.26%, 4.74%, 43.40%, 6.75%, 0%, 8.06%, and 0.03% of variation, respectively Use only factors C and A for further experimentation9Sign Table for a 2k-p Design Steps:1. Prepare a sign table for a full factorial design with k-p factors2. Mark the first column I3. Mark the next k-p columns with the k-p factors4. Of the (2k-p-k-p-1) columns on the right, choose p columns and mark them with the p factors which were not chosen in step 110Example: 27-4 Design11Example: 24-1 Design12ConfoundingConfounding: Only the combined influence of two or more effects can be computed.13Confounding (cont’d)) Effects of D and ABC are confounded. Not a problem if qABC is negligible.14Confounding (cont’d)Confounding representation: D=ABCOther Confoundings:I=ABCD ) confounding of ABCD with the mean15Other Fractional Factorial DesignsA fractional factorial design is not unique. 2p different designsConfoundings:Not as good as the previous design16Algebra of ConfoundingGiven just one confounding, it is possible to list all other confoundingsRules:I is treated as unity. Any term with a power of 2 is erased.Multiplying both sides by A:17Algebra of Confounding (cont’d)Multiplying both sides by B, C, D, and AB:and so on.Generator polynomial: I=ABCDFor the second design: I=ABC.In a 2k-p design, 2p effects are confounded together18Example 19.7In the 27-4 design:Using products of all subsets:19Example 19.7 (cont’d)Other confoundings:20Design ResolutionOrder of an effect = Number of termsOrder of ABCD = 4, order of I = 0. Order of a confounding = Sum of order of two termsE.g., AB=CDE is of order 5.Resolution of a Design = Minimum of orders of confoundingsNotation: RIII = Resolution-III = 2k-pIII Example 1: I=ABCD RIV = Resolution-IV = 24-1IV21Design Resolution (cont’d)Example 2:I = ABD RIII design. Example 3:This is a resolution-III designA design of higher resolution is considered a better design22Case Study 19.1: Latex vs. troff23Case Study 19.1 (cont’d)Design: 26-1 with I=BCDEF24Case Study 19.1: ConclusionsOver 90% of the variation is due to: Bytes, Program, and Equations and a second order interactionText file size were significantly different making it's effect more than that of the programsHigh percentage of variation explained by the ``program £ Equation'' interaction Choice of the text formatting program depends upon the number of equations in the text. troff not as good for equations25Case Study 19.1: Conclusions (cont’d)Low ``Program £ Bytes'' interaction ) Changing the file size affects both programs in a similar manner.In next phase, reduce range of file sizes. Alternately, increase the number of levels of file sizes.26Case Study 19.2: Scheduler DesignThree classes of jobs: word processing, data processing, and background data processing.Design: 25-1 with I=ABCDE27Measured Throughputs28Effects and Variation Explained29Case Study 19.2: ConclusionsFor word processing throughput (TW): A (Preemption), B (Time slice), and AB are important.For interactive jobs: E (Fairness), A (preemption), BE, and B (time slice).For background jobs: A (Preemption), AB, B (Time slice), E (Fairness).May use different policies for different classes of workloads.Factor C (queue assignment) or any of its interaction do not have any significant impact on the throughput.Factor D (Requiring) is not effective.Preemption (A) impacts all workloads significantly.Time slice (B) impacts less than preemption.Fairness (E) is important for interactive jobs and slightly important for background jobs.30SummaryFractional factorial designs allow a large number of variables to be analyzed with a small number of experimentsMany effects and interactions are confoundedThe resolution of a design is the sum of the order of confounded effectsA design with higher resolution is
View Full Document