Enter your data for Attribute Agreement Analysis

Stat > Quality Tools > Attribute Agreement Analysis

Enter your data

Select the option that best describes your data.

Data are arranged in an attribute column

Complete the following steps if your attribute data are in a single column of the worksheet.

  1. From Data are arranged as, select Attribute column and enter the column of data that you want to analyze.
  2. In Samples, enter the column that contains the sample identifiers.
  3. In Appraisers, enter the column that contains the appraiser identifiers.
In this worksheet, Appraiser contains the names of the appraisers, Sample contains the sample identifier, Rating contains the rating of each sample from each appraiser, and Standard contains the standard rating of each sample.
C1-T C2 C3 C4
Appraiser Sample Rating Standard
Simpson 1 2 2
Montgomery 1 2 2
Holmes 1 2 2
Duncan 1 1 2
Hayes 1 2 2

Data are arranged in multiple columns

Complete the following steps if your ratings from each appraiser are in separate columns of the worksheet.

  1. From Data are arranged as, select Multiple columns and enter the columns of data that you want to analyze.
  2. In Number of appraisers, enter the number of appraisers who rate the samples.
  3. In Number of trials, enter the number of times that each appraiser evaluates a sample.
  4. In Appraiser names (optional), you can enter the column that contains names of the appraisers. If you do not have a column of the appraiser names, you can type the names directly into the dialog box. Use quotation marks around each appraiser name, such as "Simpson".
    Note

    The order of the appraiser names must match the order in the worksheet.

In this worksheet, Part contains the sample identifier, Standard contains the standard rating of each sample, and columns C3–C7 contain the ratings of each sample by each appraiser.
C1 C2 C3 C4 C5 C6 C7
Part Standard Simpson Montgomery Holmes Duncan Hayes
1 2 2 2 2 1 2
2 -1 -1 -1 -1 -2 -1
3 0 1 0 0 0 0
4 -2 -2 -2 -2 -2 -2
5 0 0 0 0 -1 0

Known standard/attribute

Enter the column that contains the known reference rating for each sample. The column can contain either numeric or text attributes, but the data type must match the response type.

If you have a known reference value for each sample, you can assess the correctness of each appraiser's ratings across trials. If you select Categories of the attribute data are ordered, Minitab also provides Kendall's correlation coefficients.

Categories of the attribute data are ordered

Select to specify that the data have more than two levels and are ordinal. If your data are ordinal, Minitab provides both kappa statistics and Kendall's coefficients of concordance to evaluate the association between appraiser ratings.