Report Example: Gage R&R ANOVA Report - BPI Consulting

Report Example: Gage R&R ANOVA ReportDate: 7/18/2018Gage: My GageCharacteristic: LengthOperators: 3Parts: 10Trials: 3Description of OutputProcess Sigma: 2.5USL: 3LSL: -3Analyzed by: BillPrint out of information entered by the userANOVA Table with 492.29179.4060.4349.8181.5840.01990.0460p Value0.0000.0000.974Source: the source of the variation.df (degrees of freedom): a measure of how much information you have for each SS.SS (sum of squares): a measure of variation of squared deviations around an average.MS (mean square): estimate of the variance for the source based on the degrees of freedom.F: the statistic is used to determine whether the sources of variation are statistically significant.p-value: is the probability that the source of variation is not statistically significant.Sources with low p values have a statistically significant impact on the results.Red p values are less than 0.05.The Analysis of Variance table is given; thesources are defined below the table. Thecolumn to focus on is the p Value column.Values less than 0.05 are considered statisticallysignificant and are turned red. This tableincludes the interaction term (Operator*Part)If the p value for the interaction term is greaterthan the value entered by the user, it is removedfrom the calculations.Significance level (alpha) to remove interaction term 0.05.Operator*Part interaction is not significant and is removed in the calculations below.ANOVA Table without 5840.0400p Value0.0000.000If the interaction term is removed from thecalculations, the Analysis of Variance table isremade without the interaction term.% Contribution Based on VarianceSourceGage tTotal VarianceVariance% 50.82%6.15998.54%6.250100.00%Each source's variance is calculated and the %contribution of each source is determined. The% contribution is the % of the total variance.Table provides the % variance due to each source based on the total variance.Total variance based on process sigma entered by user.AIAG Guidelines for Gage R&R:% Gage R&R& 1%: measurement system is acceptable.% Gage R&R 1% to 9%: measurement system may be acceptable for some applications.% Gage R&R 9%: measurement system is not acceptable.If the process sigma is entered by the user, it isused to determine the total variance. If not, theparts used in the study are used to determinethe total variance.AIAG guidelines are used to determine if themeasurement system is acceptable.% Based on Standard DeviationSourceGage rtPart-to-PartTotal 2.4822.500Study Var(6SD)% Study 5.0099.27%100.00%% 16%250.00%Table gives the % of spread consumed by each source based on the total variation.Total variation based on process sigma entered by user.AIAG Guidelines for Gage R&R:% Gage R&R& 10%: measurement system is acceptable.% Gage R&R 10% to 30%: measurement system may be acceptable for some applications.% Gage R&R 30%: measurement system is not acceptable.The standard deviation from each source iscalculated. The study variation is calculated as 6times the standard deviation. The % of totalstudy variation is calculated for each source.If the process sigma is entered by the user, it isused for the total variation standard deviation.If not, the parts used in the study are used todetermine the total variation standard deviation.AIAG guidelines are used to determine if themeasurement system is acceptable.Number of Distinct CategoriesNDC represents the ability of the measurement systems to distinguish between parts.AIAG Guidelines: NDC greater than or equal to 5.The number of distinct categories is the numberof data classifications that can be reliablydistinguished by the resolution of the testmethod.

The number of distinct categories is the numberof data classifications that can be reliablydistinguished by the resolution of the testmethod.Number of Distinct Categories (NDC) 11Variance Components Chart248.2%300%250%200%99.3%98.5%%% Contribution150%% Study Var% Tolerance (SV/Tol)The % of variance and variation are plotted foreach source. This is a chart of the results in thetwo tables 00%0%Gage r-Part Control ChartsAverageX̅ Chart for Operator-Part Averages2.521.510.50-0.5-1-1.5-2UCLAvgLCL1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10ABOperator-Part NumberCThe X̅ chart is a plot of the subgroup averagesfor the operator-part number combinations.The first subgroup is made up the results thatOperator "a" got for part 1. This operator ranthis part three different times (the number oftrials).The average and control limits are calculatedand added to the chart. The control limits onthis chart depend on the average range from therange chart (see below).RangeR Chart for Operator-Part Ranges1.210.80.60.40.20UCLAvg1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10AControl Chart CalculationsX̿X̅ Chart0.00144R ChartR̅0.342BOperator-Part NumberThe R chart is a plot of the range of values withineach operator-part number subgroup. Eachrange value is a measure of the repeatability ofthe test method. The average range and controllimits are calculated and added to the chart.CLCL X̿ - A2R̅-0.348UCL X̿ A2R̅0.351LCL D3R̅-UCL D4R̅0.880The control chart calculations are given.where A2, D3, and D4 are control chart constants depending on subgroup size.A21.023D3-X̅ Chart AnalysisThe X̅ chart shows the average value for each operator for each part.D42.574The X̅ chart is analyzed. The control limits onthis chart are based on the average range fromthe range chart. This average range representsmeasurement variability. If the test method isgood, the measurement variability should besmall. So, the average range should be smalland the control limits should be tight around theaverage. The more out of control points the

The X̅ chart is analyzed. The control limits onthis chart are based on the average range fromthe range chart. This average range representsmeasurement variability. If the test method isgood, the measurement variability should besmall. So, the average range should be smalland the control limits should be tight around theaverage. The more out of control points thebetter.The control limits on the X̅ chart are based on the average range.The average range is representative of measurement error.The X̅ chart control limits represent the variation obscured by measurement error.The relative utility of the measurement system increases:* The more out of control points there on are on the X̅ chart.* The further the out of control points are away from the control limits.22 out of 30 points are out of control on the chart.The R chart is analyzed. This checks theconsistency between the operators. Thereshould be no out of control points. If there are,the reason should be found and eliminated andthe study repeated.R Chart AnalysisThe R chart shows the results for the repeated measurements for each operator for each part.It is a check of the consistency of the measurement process between the operators.There is 1 out of control point on the R chart; the ranges are not consistent.The reason for the out of control point should be corrected and the study repeated.The study should contain sufficient data(degrees of freedom). This is checked here.There are 54.7 degrees of freedom associated with the average range.It is recommended to have at least 10 degrees of freedom.ANOM Charts for Bias and RepeatabilityAverageMain Effects (0.05 ANOME) .200-0.250-0.300A (0.190)UCLAvgLCLB (0.068)The Analysis of Main Effects (ANOME) Chartcompares the overall averages for the operator.The average for each operator is plotted. Theoverall average is plotted along with the ANOMEupper and lower limits on the chart.C (-0.254)OperatorRangeMean Range (0.05 ANOMR) A (0.184)UCLAvgLCLB (0.513)The Analysis of Mean Ranges (ANOMR) Chartcompares the average range between operators.The average range for each operator is plotted.The overall average and the ANOMR upper andlower limits are added to the chart.C (0.328)OperatorANOM CalculationsMain EffectsMean RangeX̿0.00144LCL X̿ - ANOME0.05R̅-0.0700UCL X̿ ANOME0.05R̅0.0729R̅0.342LCL LMR0.05R̅0.234UCL UMR0.05R̅0.455where ANOME, LMR, and UMR are scaling factors that depend on the amount of data.ANOME0.05LMR0.050.2090.685Main Effects Chart AnalysisThis chart plots the average part values for each operator.The purpose of the chart is to check for operator bias.Points beyond the control limits are indications that bias exists.The ANOME and ANOMR calculations are given.UMR0.051.331The main effects chart is analyzed. There aredifferences (bias) in the operators if some of thepoints are beyond the limits.There is evidence of detectable bias between the operators.Review the ANOME chart for the differences.Mean Range Chart AnalysisThis charts plot the average range values for each operator.The purpose of the chart is to see if the test-retest error is the same for each operator.Points beyond the control limits are indications that differences in repeatability exist.There is evidence of differences in the test-retest error between the operators.Review the ANOMR chart for the differences.The mean range is analyzed. There aredifferences in repeatability if some of the pointsare beyond the limits.

Data TableOptional Data TableRun .82.122.19-1.68-1.62-1.50.04-0.11Comment

-0.46-0.56-0.491.771.451.87-1.49-1.77-2.16

R Chart for Operator-Part Ranges Control Chart Calculations X ̅Chart X̿ LCL ̿- A 2R UCL X̿ A 2R̅ 0.00144 -0.348 0.351 R Chart R̅LCL D 3 UCL 4 0.342 - 0.880 where A 2, D 3, and D 4 are control chart constants depending on subgroup size. A 2 D 3 D 4 1.023 - 2.574 X̅Chart Analysis The X̅ chart shows the average value for each .