Under Score Training Data and Score Validation Data, select all options to produce all four reports in the output. When this option is selected, the variance-covariance matrix of the estimated regression coefficients is displayed in the output. Under Residuals, select Unstandardized to display the Unstandardized Residuals in the output, which are computed by the formula: Unstandardized residual = Actual response - Predicted response. Standardized residuals are obtained by dividing the unstandardized residuals by the respective standard deviations. Under Residuals, select Standardized to display the Standardized Residuals in the output. When this option is selected, the ANOVA table is displayed in the output. When this option is selected, the fitted values are displayed in the output. Leave this option unchecked for this example. If Force constant term to zero is selected, there is constant term in the equation. Select OK to advance to the Variable Selection dialog. If the number of rows in the data is less than the number of variables selected as Input variables, XLMiner displays the following prompt.
MEDV).Ĭlick Next to advance to the Step 2 of 2 dialog. On the XLMiner ribbon, from the Data Mining tab, select Predict - Multiple Linear Regression to open the Multiple Linear Regression - Step 1 of 2 dialog.Īt Output Variable, select MEDV, and from the Selected Variables list, select all remaining variables (except CAT. Select a cell on the Data_Partition worksheet. On the XLMiner ribbon, from the Data Mining tab, select Partition - Standard Partition to open the Standard Data Partition dialog. For more information on partitioning a data set, see the Data Mining Partition section. To partition the data into Training and Validation Sets, use the Standard Data Partition defaults with percentages of 60% of the data randomly allocated to the Training Set, and 40% of the data randomly allocated to the Validation Set. A portion of the data set is shown below. On the XLMiner ribbon, from the Applying Your Model tab, select Help - Examples, then Forecasting/Data Mining Examples to open the Boston_Housing.xlsx from the data sets folder. This variable will not be used in this example. MEDV, which has been created by categorizing median value (MEDV) into two categories: high (MEDV > 30) and low (MEDV < 30). In addition to these variables, the data set also contains an additional variable, Cat.
A description of each variable is given in the following table. You can also create a scatter plot of these residuals.The following example illustrates XLMiner's Multiple Linear Regression method using the Boston Housing data set to predict the median house prices in housing tracts. For example, the first data point equals 8500. The residuals show you how far away the actual data points are fom the predicted data points (using the equation). For example, if price equals $4 and Advertising equals $3000, you might be able to achieve a Quantity Sold of 8536.214 -835.722 * 4 + 0.592 * 3000 = 6970. You can also use these coefficients to do a forecast. For each unit increase in Advertising, Quantity Sold increases with 0.592 units. In other words, for each unit increase in price, Quantity Sold decreases with 835.722 units.
The regression line is: y = Quantity Sold = 8536.214 -835.722 * Price + 0.592 * Advertising. Most or all P-values should be below below 0.05. Delete a variable with a high P-value (greater than 0.05) and rerun the regression until Significance F drops below 0.05. If Significance F is greater than 0.05, it's probably better to stop using this set of independent variables. If this value is less than 0.05, you're OK. To check if your results are reliable (statistically significant), look at Significance F ( 0.001).
0 kommentar(er)
