The key to getting your message across or allowing others to understand your results (business, medical, technical, etc) is data visualization. The key is to "say it with charts" and show instead of telling.

1. Using Charts to Present Your
Results to Non-Statisticians
Often the most effective
way to describe, explore,
and summarize a set of
numbers…
—even a very large set—
is to look at pictures of
those numbers.
-Edward Tufte

2. Say It With Charts

3. Say It With Statistical Charts

4. Which Chart Tells the Best Story?

5. Chart Junk
Graphical excellence gives
the viewer the greatest
number of ideas in the
shortest time with the least
ink in the smallest space.
-Edward Tufte

6. Cute or Clear?

7. What Does a p-value Look Like?

8. What Does a p-value Look Like?

9. What Does a p-value Look Like?

10. Complexity

11. Clarity

12. What’s Important?

13. Pareto Charts Can Tell You

14. Is This Acceptable Performance?

15. No! You Need Statistical Alarms

16. Statistical Process Control
in a Nutshell
Reality: Every Process Varies
Goal: Reduce Variation in Products and Services
Types of Variation
•Special Cause Variation
(something changed)
•Common Cause Variation
(normal variation)

17. SPC in a Nutshell
It’s possible to calculate statistical limits
for any type of data and any pattern of variation.
Using these “control” limits, it’s possible to create rules to
detect special causes of variation whenever a process shifts.

18. Statistics or Charts?
• Normality?
• Means?
• Variances?

19. Reducing Variation
Before After

20. Reducing Variation
Use Histograms to show reduction in variation
Before After

21. http://www.visual-literacy.org/periodic_table/periodic_table.html

22. Periodic Table of Visual Methods
http://www.visual-literacy.org/periodic_table/periodic_table.html

23. QI Macros SPC Software for Excel
www.qimacros.com
Data Analysis & Projects
Lean Six Sigma Demystified
www.lssyb.com