Regression - Diagnostic - Plot - Normal Q-Q

From Q
Jump to: navigation, search

A Normal Quantile-Quantile chart. This reveals departures from the normality assumption. Where the residuals are normally distributed, the points on the line will form an approximately straight line running from the bottom-left to the top-right. Shapes other than a straight line indicate that the normality assumption may not have been satisfied. See this answer on Cross Validated for more information.

Example

An example Q-Q plot output from running this QScript on a linear regression model is shown below.

Acknowledgements

Uses plot.lm and/or plot.glm function from the stats R package.

Code

includeWeb("QScript R Output Functions");

main();

function main() {

    // The following 2 variables contain information specific to this diagnostic.
    var required_class = "Regression";
    var output_name_suffix = "normal.qq";
    
    var item = checkSelectedItemClass(required_class);
    if (item == null)
        return false;
    var r_name = stringToRName(item.referenceName);

    // The following lines contain the R code to run
    var expression = "plot(" + r_name + ", which = 2)"

    return createROutput(item, expression, output_name_suffix);
}