Multi-Collinearity Test

In statistical modeling, we often encounter the issue of multi-collinearity phenomena among the explanatory variables. Our objective here is to uncover a strong relationship of collinearity among the explanatory variables, and determine whether one or more variables can be linearly predicted from the others with non-trivial accuracy.

NumXL provides an intuitive interface to help Excel users conduct multi-collinearity test using several methods. In this tutorial, we’ll demonstrate the steps to construct a mult-collinearity test of hypothesis using NumXL functions in Excel.

  1. Select an empty cell to store the test table
  2. Locate the Statistical Test (STAT TEST) icon in the toolbar (or menu in Excel 2003) and click on the "multi-collinearity" test icon in the list down-arrow.
    Locate and click on the mult-collinearity test icon in NumXL toolbar
  3. The Multi-collinearity Test dialog box appears. Select the “Input Data” range for the explanatory variable. Each column represents a separate variable. The “Output” field is set by default to the current selected cell in your worksheet.
    Select the input data cells range in The multi-collinearity test dialog/wizard
  4. Selecting the input data cell range will enable the “Options” and “Missing Values” tabs. Click the “Options” Tab.
  5. Select the mult-collinearity tests to include in the output table.
    Options tab in the mult-collinearity Test dialog in NumXL
    Note: Initially, all tests are selected as shown above.
  6. If your data include one or more intermediate observations with missing values, click the “Missing Values” tab.
  7. Initially, missing values are dropped from the sample data. If you wish to change this behavior/treatment, select an alternative method.
    Missing Values tab in the mult-collinearity test in NumXL
  8. Now, Click “OK” to generate the output table.
  9. The normality test wizard generates the output table as shown below:
    The output table for the multi-collinearity test in Excel using NumXL Wizards and functions

Note: This multi-collinearity test function and wizard is available starting with version 1.60.

 

Have more questions? Submit a request

0 Comments