Why throw away your non-normal research data using casewise, listwise,
or pairwise deletion to "fix" missing data problems? Or why "average it
away" with mean/median/mode replacement?
Discounted 4-session live online course instructing on the use of 4
different data imputation techniques suitable for data that is not
multivariate normal.
You receive training on the professional VIMGUI software (available
through R), as well as unrestricted, permanent use of the software
itself. VIMGUI supports the following contemporary data imputation
techniques: (1) Hot Deck imputation; (2) k-nearest neighbor; (3)
individual, regression-based imputation; and (4) iterative, model-based,
stepwise regression imputation (irmi algorithm).
Course registration includes R-Courseware community user account through
December of 2014. VIMGUI also provides extensive missing data
visualization capabilities so you can see the 'missingness' data
patterns to choose the most appropriate imputation approach.
If you want to learn how to perform statistical analyses; data analyses
and/or data mining; graphical presentations of data; and/or programming
with open-source R software for your school work or for your job, please
consider this opportunity.
Included R-Courseware user account has 1300+ analytics, statistical, and
data mining video and materials files on "hands on" research methods
techniques.
Visit
http://tinyurl.com/vimgui Geoff Hubona
