XLSTAT: Durbin-Watson Test in Excel

 

Background

The Durbin-Watson test is a statistical measure used to detect autocorrelation in the residuals of a regression model, particularly in time series data.

 

Dataset for Example

The attached data have been obtained in Lewis T. and Taylor L.R. (1967). Introduction to Experimental Ecology, New York: Academic Press, Inc.. They concern 237 children, described by their gender, age in months, height in inches (1 inch = 2.54 cm), and weight in pounds (1 pound = 0.45 kg).

We have run a simple linear regression between the height and the weight to get the residuals.

 

Setting Up

• Open XLSTAT.

• Click on the Time series analysis menu and select the Durbin-Watson test feature:

• Once you've clicked on the button, the dialog box appears.

In the General tab:

• Select the data on the Excel sheet.

• In this case, use the residuals from the linear regression between Height and Weight as the dependent variable.

• Select Height as the explanatory variable.

• Since the column headers were selected, activate the Variable labels option.

In the Options tab:

• Set the significance level of the test (default is usually 5%).

• Set the order (number of lags) for the test.

• In this example, leave the default values for both parameters.

• Click on the OK button to launch the computations.

• The results are displayed on a new Excel sheet.

 

Interpreting the Results

The first results displayed are the statistics for the residuals. Next the results of the Durbin-Watson test and a short interpretation are displayed.

Since the p-value is greater than the significance level (5%), the null hypothesis cannot be rejected.