ToolUse WhenExampleData FormatYXsp < 0.05 indicates
ANOVADetermine if the average of a group of data is different than the average of other (multiple) groups of dataCompare multiple service centers to determine if one or more performs differently.Response data must be stacked in one column, and the individual points must be tagged in another.Variable or ContinuousAttributeAt least one data group has a different mean than one other group.
Box & Whisker PlotCompare the median and variation between groups of data. It also identifies outliers.Compare pallet weights using different scales.Response data must be stacked in one column, and the individual points must be tagged in another column.Variable or ContinuousAttributeN/A
Cause & Effect Diagram/      FishboneBrainstorming possible sources of variation for a particular effectPotential sources of variation in gage r&rInput ideas in the proper column heading for the main branches of the fishbone.  Type effect in the pulldown windowAllAllN/A
Chi-Square (data summarised in table)Determine if one set of defectives data is different than other sets of defectives data.Compare DPMOs of Product Quality Complaints between 1210’s and 1208’sInput two columns; one contains the number of non-defective, and the other contains the number of defective onesAttributeAttributeAt least one group is statistically different.
Chi-Square (raw data)Determine if one set of defectives data is different than other sets of defectives data.Compare DPMOs of Product Quality Complaints between 1210’s and 1208’sInput two columns; one contains the number of non-defective, and the other contains the number of defectiveAttributeAttributeAt least one group is statistically different.
Dot PlotQuick graphical comparison of two or more processes’ variation or spreadCompare the length of service of employees by countryInput multiple columns of data of equal lengthVariable or ContinuousAttributeN/A
General Linear ModelsDetermine if the difference in categorical data between groups is real when taking into account other variables x’s Determine if height and weight are significant variables between two groups when looking at payResponse data must be stacked in one column, and the individual points must be tagged in another column.  Other variables must be stacked in separate columns.Variable or ContinuousAttribute/
Variable
At least one data group is different from at least one other group.
HistogramView the data distribution (spread, mean, mode, outliers, etc.)View the distribution of YInput one column of dataVariable or ContinuousAttributeN/A
Test for Equal VariancesDetermine if the variation in one group of data is different than the variation in other (multiple) groups of dataCompare the variation between teams of operatorsResponse data must be stacked in one column, and the individual points must be tagged in another column.Variable or ContinuousAttribute(Use Levene’s Test)  At least one group of data is different than at least one other group [1]
Kruskal-Wallis TestDetermine if the medians of non-normal data are differentCompare the medians of cycle time for different delivery methodsResponse data must be stacked in one column, and the individual points must be tagged in another column.Variable or ContinuousAttributeAt least one median is different
Mood´s Median TestDetermine if the medians of non-normal data are differentCompare the medians of cycle time for different delivery methodsResponse data must be stacked in one column, and the individual points must be tagged in another column.Variable or ContinuousAttributeAt least one median is different
Multi Vari Analysis (See also Run Chart / Time Series Plot)It helps identify the most important types or families of variationCompare within the piece, piece to piece or time to time of conditioning palletsResponse data must be stacked in one column, and the individual points must be tagged in another column in time order.Variable or ContinuousAttributeN/A
Notched Box PlotCompare the median of a given confidence interval and variation between groups of dataCompare different nail drilling patterns to see if the median and spread of the diameters are the sameResponse data must be stacked in one column, and the individual points must be tagged in another column.Variable or ContinuousAttributeN/A
One-sample t-testDetermine if the average of a group of data is statistically equal to a specific targetThe manufacturer claims the average number of cookies in one lb. package is 250.  You sample 10 packages and find that the average is 235.  Use this test to disprove the manufacturer’s claimInput one column of dataVariable or ContinuousN/ANot equal
ParetoCompare how frequently different causes occurDetermine which defect occurs the most often for overall customer complaints Input two columns of equal lengthVariable or ContinuousAttributeN/A
Process MappingCreate a visual aid for each step in the process being evaluatedMap Service Center area with all rework loops and inspection points Use rectangles for process steps and diamonds for decision pointsN/AN/AN/A
RegressionDetermine if a group of data incrementally changes with another groupDetermine if a conditioning output changes with the temperature in the buildingInput two columns of equal lengthVariable or ContinuousVariable or ContinuousA correlation is detected
Run Chart/Time Series PlotLook for trends, outliers, oscillations, etc.Determine if a conditioning output changes with temperature in the building over timeInput one column of data.  You must also input a subgroup size (1 will show all points)Variable or ContinuousN/AN/A
Scatter PlotLook for correlations between groups of variable dataDetermine if the output of Service Centers is differentInput two or more groups of data of equal lengthVariable or ContinuousVariable or ContinuousN/A
Two-sample t-testDetermine if the average of one group of data is greater than (or less than) the average of another group of dataDetermine if the average delivery time of a transporter is different from anotherInput two columns of equal lengthVariable or ContinuousVariable or ContinuousThere is a difference in the means
[1] Levene´s test is valid for any continuous data, normal and not normal

Leave a Reply