Exam 1

1. Metainformation

   Tag	Value
   file	Assumptions_uu-Residuals-801-en_uu-Residuals-801-en
   name	uu-Residuals-801-en.Rmd
   section	Inferential Statistics/Regression/Residuals
   type	string
   solution	Partially
   Type	Interpreting output
   Program	SPSS
   Language	English
   Level	Statistical Literacy

   Question

   Included in this question is part of the SPSS output from a multiple regression model from a dataset from the US National Center of Educational Statistics. This dataset is called High School Beyond and has data on variables related to students’ academic achievement. Specifically, the outcome variable for the regression model is “Math Score” which is predicted from “Locus of Control”, “Self-Concept”, and “Reading Score”.

   Using only the information given below, provide information on three different types of outliers. For each type of outlier, give (1) the type of outlier; (2) which part of the output or which graph you used; and (3) whether there is cause for concern and why.

   

   
   

   Solution

   $x$-space: Mahalanobis distance: $17.8>16$ therefore concern about outliers in $x$-space.

   $y$-space: Standardized residuals $>3.3$ or $<-3.3$: This is not the case, therefore no concern.

   $xy$-space: Cook’s distance $>1$: This is not the case, therefore no concern.