6-1-QSM754MINITABPOWERPOINTSLIDESV8（英文PPT133頁）

1、The National Graduate School of Quality Management v.8 1INTRODUCTION TO MINITAB VERSION 13The National Graduate School of Quality Management v.8 2Worksheet Conventions and Menu StructuresMinitab InteroperabilityGraphic CapabilitiesParetoHistogramBox PlotScatter PlotStatistical CapabilitiesCapability

2、 AnalysisHypothesis TestContingency TablesANOVADesign of Experiments (DOE) Minitab Training AgendaThe National Graduate School of Quality Management v.8 3 Worksheet Format and StructureSession WindowWorksheet Data WindowMenu BarTool BarThe National Graduate School of Quality Management v.8 4Text Col

3、umn C1-T(Designated by -T)Numeric Column C3(No Additional Designation) Data Window Column ConventionsDate Column C2-D(Designated by -D)The National Graduate School of Quality Management v.8 5Column Names(Type, Date, Count & AmountEntered Data for Data Rows 1 through 4Data Entry ArrowData Rows Ot

4、her Data Window ConventionsThe National Graduate School of Quality Management v.8 6 Menu Bar - Menu ConventionsHot Key Available (Ctrl-S)Submenu Available ( at the end of selection)The National Graduate School of Quality Management v.8 7 Menu Bar - File MenuKey FunctionsWorksheet File ManagementSave

5、PrintData ImportThe National Graduate School of Quality Management v.8 8 Menu Bar - Edit MenuKey FunctionsWorksheet File EditsSelectDeleteCopyPasteDynamic LinksThe National Graduate School of Quality Management v.8 9 Menu Bar - Manip MenuKey FunctionsData ManipulationSubset/SplitSortRankRow Data Man

6、ipulationColumn Data ManipulationThe National Graduate School of Quality Management v.8 10 Menu Bar - Calc MenuKey FunctionsCalculation CapabilitiesColumn CalculationsColumn/Row StatisticsData StandardizationData ExtractionData GenerationThe National Graduate School of Quality Management v.8 11 Menu

7、 Bar - Stat MenuKey FunctionsAdvanced Statistical Tools and GraphsHypothesis TestsRegressionDesign of ExperimentsControl ChartsReliability TestingThe National Graduate School of Quality Management v.8 12 Menu Bar - Graph MenuKey FunctionsData Plotting CapabilitiesScatter PlotTrend PlotBox PlotContou

8、r/3 D plottingDot PlotsProbability PlotsStem & Leaf PlotsThe National Graduate School of Quality Management v.8 13 Menu Bar - Data Window Editor MenuKey FunctionsAdvanced Edit and Display OptionsData BrushingColumn SettingsColumn Insertion/MovesCell InsertionWorksheet SettingsNote: The Editor Se

9、lection is Context Sensitive. Menu selections will vary for:Data WindowGraphSession WindowDepending on which is selected. The National Graduate School of Quality Management v.8 14 Menu Bar - Session Window Editor MenuKey FunctionsAdvanced Edit and Display OptionsFont Connectivity SettingsThe Nationa

10、l Graduate School of Quality Management v.8 15 Menu Bar - Graph Window Editor MenuKey FunctionsAdvanced Edit and Display OptionsBrushing Graph ManipulationColorsOrientationFontThe National Graduate School of Quality Management v.8 16 Menu Bar - Window MenuKey FunctionsAdvanced Window Display Options

11、Window Management/Display Toolbar Manipulation/DisplayThe National Graduate School of Quality Management v.8 17 Menu Bar - Help MenuKey FunctionsHelp and TutorialsSubject SearchesStatguide Multiple TutorialsMinitab on the WebThe National Graduate School of Quality Management v.8 18MINITAB INTEROPERA

12、BILITYThe National Graduate School of Quality Management v.8 19 Minitab InteroperabilityExcelMinitabPowerPointThe National Graduate School of Quality Management v.8 20 Starting with Excel.Load file “Sample 1” in Excel.The National Graduate School of Quality Management v.8 21 Starting with Excel.The

13、data is now loaded into Excel.The National Graduate School of Quality Management v.8 22 Starting with Excel.Highlight and Copy the Data.The National Graduate School of Quality Management v.8 23 Move to Minitab.Open Minitab and select the column you want to paste the data into.The National Graduate S

14、chool of Quality Management v.8 24 Move to Minitab.Select Paste from the menu and the data will be inserted into the Minitab Worksheet.The National Graduate School of Quality Management v.8 25 Use Minitab to do the Analysis.Lets say that we would like to test correlation between the Predicted Worklo

15、ad and the actual workload.Select Stat Regression. Fitted Line Plot.The National Graduate School of Quality Management v.8 26 Use Minitab to do the Analysis.Minitab is now asking for us to identify the columns with the appropriate date.Click in the box for “Response (Y): Note that our options now ap

16、pear in this box.Select “Actual Workload” and hit the select button.This will enter the “Actual Workload” data in the Response (Y) data field.The National Graduate School of Quality Management v.8 27 Use Minitab to do the Analysis.Now click in the Predictor (X): box. Then click on “Predicted Workloa

17、d” and hit the select button This will fill in the “Predictor (X):” data field.Both data fields should now be filled.Select OK.The National Graduate School of Quality Management v.8 28 Use Minitab to do the Analysis.Minitab now does the analysis and presents the results.Note that in this case there

18、is a graph and an analysis summary in the Session WindowLets say we want to use both in our PowerPoint presentation.The National Graduate School of Quality Management v.8 29 Transferring the Analysis.Lets take care of the graph first.Go to Edit. Copy Graph.The National Graduate School of Quality Man

19、agement v.8 30 Transferring the Analysis.Open PowerPoint and select a blank slide.Go to Edit. Paste Special.The National Graduate School of Quality Management v.8 31 Transferring the Analysis.Select “Picture (Enhanced Metafile) This will give you the best graphics with the least amount of trouble. T

20、he National Graduate School of Quality Management v.8 32 Transferring the Analysis.Our Minitab graph is now pasted into the powerpoint presentation. We can now size and position it accordingly. The National Graduate School of Quality Management v.8 33 Transferring the Analysis.Now we can copy the an

21、alysis from the Session window.Highlight the text you want to copy.Select Edit. Copy. The National Graduate School of Quality Management v.8 34 Transferring the Analysis.Now go back to your powerpoint presentation.Select Edit. Paste. The National Graduate School of Quality Management v.8 35 Transfer

22、ring the Analysis.Well we got our data, but it is a bit large.Reduce the font to 12 and we should be ok. The National Graduate School of Quality Management v.8 36 Presenting the results.Now all we need to do is tune the presentation.Here we position the graph and summary and put in the appropriate t

23、akeaway. Then we are ready to present.The National Graduate School of Quality Management v.8 37Graphic CapabilitiesThe National Graduate School of Quality Management v.8 38 Pareto Chart.Lets generate a Pareto Chart from a set of data.Go to File Open Project. Load the file Pareto.mpj.Now lets generat

24、e the Pareto Chart.The National Graduate School of Quality Management v.8 39 Pareto Chart.Go to:Stat Quality ToolsPareto Chart.The National Graduate School of Quality Management v.8 40 Pareto Chart.Fill out the screen as follows:Our data is already summarized so we will use the Chart Defects table.

25、Labels in “Category”Frequencies in “Quantity”.Add title and hit OK.The National Graduate School of Quality Management v.8 41 Pareto Chart.Minitab now completes our pareto for us ready to be copied and pasted into your PowerPoint presentation.The National Graduate School of Quality Management v.8 42

26、Histogram.Lets generate a Histogram from a set of data.Go to File Open Project. Load the file 2_Correlation.mpj.Now lets generate the Histogram of the GPA results.The National Graduate School of Quality Management v.8 43 Histogram.Go to:Graph HistogramThe National Graduate School of Quality Manageme

27、nt v.8 44 Histogram.Fill out the screen as follows:Select GPA for our X value Graph VariableHit OK.The National Graduate School of Quality Management v.8 45 Histogram.Minitab now completes our histogram for us ready to be copied and pasted into your PowerPoint presentation.This data does not look li

28、ke it is very normal.Lets use Minitab to test this distribution for normality.The National Graduate School of Quality Management v.8 46 Histogram.Go to:Stat Basic StatisticsDisplay Descriptive Statistics.The National Graduate School of Quality Management v.8 47 Histogram.Fill out the screen as follo

29、ws:Select GPA for our Variable.Select Graphs.The National Graduate School of Quality Management v.8 48 Histogram.Select Graphical Summary.Select OK.Select OK again on the next screen.The National Graduate School of Quality Management v.8 49 Histogram.Note that now we not only have our Histogram but

30、a number of other descriptive statistics as well.This is a great summary slide.As for the normality question, note that our P value of .038 rejects the null hypothesis (P.05). So, we conclude with 95% confidence that the data is not normal.The National Graduate School of Quality Management v.8 50 Hi

31、stogram.Lets look at another “Histogram” tool we can use to evaluate and present data.Go to File Open Project. Load the file overfill.mpj.The National Graduate School of Quality Management v.8 51 Histogram.Go to:Graph Marginal PlotThe National Graduate School of Quality Management v.8 52 Histogram.F

32、ill out the screen as follows:Select filler 1 for the Y Variable.Select head for the X VariableSelect OK.The National Graduate School of Quality Management v.8 53 Histogram.Note that now we not only have our Histogram but a dot plot of each head data as well.Note that head number 6 seems to be the s

33、ource of the high readings.This type of Histogram is called a “Marginal Plot”.The National Graduate School of Quality Management v.8 54 Boxplot.Lets look at the same data using a Boxplot.The National Graduate School of Quality Management v.8 55 Boxplot.Go to:Stat Basic StatisticsDisplay Descriptive

34、Statistics.The National Graduate School of Quality Management v.8 56 Boxplot.Fill out the screen as follows:Select “filler 1” for our Variable.Select Graphs.The National Graduate School of Quality Management v.8 57 Boxplot.Select Boxplot of data.Select OK.Select OK again on the next screen.The Natio

35、nal Graduate School of Quality Management v.8 58 Boxplot.We now have our Boxplot of the data.The National Graduate School of Quality Management v.8 59 Boxplot.There is another way we can use Boxplots to view the data.Go to:Graph Boxplot.The National Graduate School of Quality Management v.8 60 Boxpl

36、ot.Fill out the screen as follows:Select “filler 1” for our Y Variable.Select “head” for our X Variable.Select OK.The National Graduate School of Quality Management v.8 61 Boxplot.Note that now we now have a box plot broken out by each of the various heads.Note that head number 6 again seems to be t

37、he source of the high readings.The National Graduate School of Quality Management v.8 62 Scatter plot.Lets look at data using a Scatterplot.Go to File Open Project. Load the file 2_Correlation.mpj.Now lets generate the Scatterplot of the GPA results against our Math and Verbal scores.The National Gr

38、aduate School of Quality Management v.8 63 Scatter plot.Go to:Graph Plot.The National Graduate School of Quality Management v.8 64 Scatter Plot.Fill out the screen as follows:Select GPA for our Y Variable.Select Math and Verbal for our X Variables.Select OK when done.The National Graduate School of

39、Quality Management v.8 65 Scatter plot.We now have two Scatter plots of the data stacked on top of each otherWe can display this better by tiling the graphs.The National Graduate School of Quality Management v.8 66 Scatter plot.To do this:Go to WindowTile.The National Graduate School of Quality Mana

40、gement v.8 67 Scatter plot.Now we can see both Scatter plots of the dataThe National Graduate School of Quality Management v.8 68 Scatter plot.There is another way we can generate these scatter plots.Go to:Graph Matrix Plot.The National Graduate School of Quality Management v.8 69 Scatter Plot.Fill

41、out the screen as follows:Click in the “Graph variables” blockHighlight all three available data setsClick on the “Select” button.Select OK when done.The National Graduate School of Quality Management v.8 70 Scatter plot.We now have a series of Scatter plots, each one corresponding to a combination

42、of the data sets availableNote that there appears to be a strong correlation between Verbal and both Math and GPA data.The National Graduate School of Quality Management v.8 71Minitab Statistical ToolsThe National Graduate School of Quality Management v.8 72PROCESS CAPABILITY ANALYSISThe National Gr

43、aduate School of Quality Management v.8 73Lets do a process capability study.Open Minitab and load the file Capability.mpj.The National Graduate School of Quality Management v.8 74SETTING UP THE TEST.Go to Stat Quality Tools. Capability Analysis (Weibull).The National Graduate School of Quality Mana

44、gement v.8 75Select “Torque” for our single data column.Enter a lower spec of 10 and an upper spec of 30. Then select “OK”.SETTING UP THE TEST.The National Graduate School of Quality Management v.8 76Note that the data does not fit the normal curve very well.Note that the Long Term capability (Ppk)

45、is 0.43. This equates to a Z value of 3*0.43=1.29 standard deviations or sigma values.This equates to an expected defect rate PPM of 147,055.INTERPRETING THE DATA.The National Graduate School of Quality Management v.8 77HYPOTHESIS TESTINGThe National Graduate School of Quality Management v.8 78Load

46、the file normality.mpj.Setting up the test in MinitabThe National Graduate School of Quality Management v.8 79Checking the Data for Normality.Its important that we check for normality of data samples.Lets see how this works.Go to STAT. Basic Statistics. Normality Test.The National Graduate School of

47、 Quality Management v.8 80Set up the TestWe will test the “Before” column of data.Check Anderson-DarlingClick OKThe National Graduate School of Quality Management v.8 81Analyzing the ResultsSince the P value is greater than .05 we can assume the “Before” data is normalNow repeat the test for the “Af

48、ter” Data (this is left to the student as a learning exercise.)The National Graduate School of Quality Management v.8 82Checking for equal variance.We now want to see if we have equal variances in our samples.To perform this test, our data must be “stacked”.To accomplish this go to Manip Stack Stack

49、 Columns.The National Graduate School of Quality Management v.8 83Select both of the available columns (Before and After) to stack.Type in the location where you want the stacked data. In this example we will use C4.Type in the location where you want the subscripts stored In this example we will us

50、e C3.Select OK.Checking for equal variance.The National Graduate School of Quality Management v.8 84Now that we have our data stacked, we are ready to test for equal variances.Go to Stat ANOVA. Test for equal Variances.Checking for equal variance.The National Graduate School of Quality Management v.

51、8 85Setting up the test.Our response will be the actual receipt performance for the two weeks we are comparing. In this case we had put the stacked data in column C4.Our factors is the label column we created when we stacked the data (C3).We set our Confidence Level for the test (95%).Then select “O

52、K”.The National Graduate School of Quality Management v.8 86Here, we see the 95% confidence intervals for the two populations. Since they overlap, we know that we will fail to reject the null hypothesis.The F test results are shown here. We can see from the P-Value of .263 that again we would fail t

53、o reject the null hypothesis. Note that the F test assumes normalityNote that we get a graphical summary of both sets of data as well as the relevant statistics. Analyzing the data.Levenes test also compares the variance of the two samples and is robust to nonnormal data. Again, the P-Value of .229

54、indicates that we would fail to reject the null hypothesis.Here we have box plot representations of both populations.The National Graduate School of Quality Management v.8 87Lets test the data with a 2 Sample t Test- -Under Stat Basic Statistics. We see several of the hypothesis tests which we discu

55、ssed in class. In this example we will be using a 2 Sample t Test.Go to Stat. Basic Statistics. 2 Sample t.The National Graduate School of Quality Management v.8 88Since we already have our data stacked, we will load C4 for our samples and C3 for our subscripts.Setting up the test.Since we have alre

56、ady tested for equal variances, we can check off this boxNow select Graphs.The National Graduate School of Quality Management v.8 89Setting up the test.We see that we have two options for our graphical output. For this small a sample, Boxplots will not be of much value so we select “Dotplots of data

57、” and hit “OK”. Hit OK again on the next screen.The National Graduate School of Quality Management v.8 90In the session window we have each populations statistics calculated for us.Note that here we have a P value of .922. We therefore find that the data does not support the conclusion that there is

58、 a significant difference between the means of the two populations. Interpreting the results.The National Graduate School of Quality Management v.8 91The dotplot shows how close the datapoints in the two populations fall to each other. The close values of the two population means (indicated by the r

59、ed bar) also shows little chance that this hypothesis could be rejected by a larger sample Interpreting the results.The National Graduate School of Quality Management v.8 92Paired Comparisons In paired comparisons we are trying to “pair” observations or treatments. An example would be to test automa

60、tic blood pressure cuffs and a nurse measuring the blood pressure on the same patient using a manual instrument. It can also be used in measurement system studies to determine if operators are getting the same mean value across the same set of samples. Lets look at an example: 2_Hypothesis_Testing_Shoe_wear