R: Mining spatial, text, web, and social media data by Bater Makhabel

Author:Bater Makhabel
Language: eng
Format: epub
Publisher: Packt Publishing

The residual versus fitted plot shows the randomness in residual values as we move along the fitted line. If the residual values display any pattern against the fitted values, the error term is not probably normal. The residual versus fitted graph indicates that there is no pattern that exists among the residual terms; the residuals are approximately normally distributed. Residual is basically that part of the model which cannot be explained by the model. There are few influential data points, for example, 42nd, 39th, and 83rd as it is shown on the preceding graph, the normal quantile-quantile plot indicates except few influential data points all other standardized residual points follow a normal distribution. The straight line is the zero residual line and the red line is the pattern of residual versus fitted relationship. The scale versus location graph and the residuals versus leverage graph also validate the same observation that the residual term has no trend. The scale versus location plot takes the square root of the standardized residuals and plots it against the fitted values:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.