How do I transform variables?

(Difference between revisions)
 Revision as of 03:14, 17 February 2008 (view source)Doug (Talk | contribs)← Older edit Latest revision as of 20:54, 7 September 2009 (view source)Doug (Talk | contribs) (One intermediate revision not shown) Line 1: Line 1: - asdfadsf + *'''How do I transform variables?''' - + *#There are different types of transformations based upon the type of non-normality. So the first step is to identify the type of non-normality, and then identify which transformation is used for that type of non-normality. The Tabachnick & Fidell book "Using Multivariate Statistics" in section 4.16 (pp. 82-82) provides detailed information about each type of non-normality and the corresponding mathematical transformation. - + *#The second step is to use statistical software to create the newly transformed variable using the appropriate mathematical formula, such as using the "Compute" function in SPSS. - + *#The final step is to check the normality of the newly created variable. See [[How do I determine whether my data are normal?]] If the variable is normal, then you can start conducting statistical analyses using that variable. If the variable is still non-normal, then try other related transformations. - + - + - + - + - + - + - + - + Line 18: Line 10: ---- ---- - ◄ Back to [[Research_Tools |Research Tools mainpage]] + ◄ Back to [[Analyzing Data]] page

Latest revision as of 20:54, 7 September 2009

• How do I transform variables?
1. There are different types of transformations based upon the type of non-normality. So the first step is to identify the type of non-normality, and then identify which transformation is used for that type of non-normality. The Tabachnick & Fidell book "Using Multivariate Statistics" in section 4.16 (pp. 82-82) provides detailed information about each type of non-normality and the corresponding mathematical transformation.
2. The second step is to use statistical software to create the newly transformed variable using the appropriate mathematical formula, such as using the "Compute" function in SPSS.
3. The final step is to check the normality of the newly created variable. See How do I determine whether my data are normal? If the variable is normal, then you can start conducting statistical analyses using that variable. If the variable is still non-normal, then try other related transformations.

◄ Back to Analyzing Data page