0% found this document useful (0 votes)
25 views5 pages

UPDATED - Black Belt Cheat Sheet - 17NOV2017

Uploaded by

Lili
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
25 views5 pages

UPDATED - Black Belt Cheat Sheet - 17NOV2017

Uploaded by

Lili
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Graphical Analysis Guide

X data
Continuous Discrete
• Scatter Plots • Historgrams
• Matrix Plots • Dotplots
Continuous

• Boxplots
• Multi-Vari
Y data

• Histograms • Tables
• Dotplots • Pareto Charts
Discrete

• Boxplots

26 www.6sigmaPH.com
Statistical Analysis Guide

IF HYPOTHESIS TESTING STEPS:


p < 0.05, reject Ho, & accept Ha X
p _> 0.05, cannot reject Ho 1. Identify your Y and X(s)
(inputs) 2. Identify data type of Y and X(s)

Continuous Discrete 3. Check for normality (Y and Xs) if not


(Groups) normal:
a. collect more data
t-test b. transform using Box Cox (Minitab)
c. Look for 6 causes
Regression Paired t-test d. Use non parametric tests
Continuous
ANOVA 4. Check for special causes. If with
Part 1: Comparing 3 or more group special cause/s investigate, address
averages & ANOM
Part 2: Comparing varations between
special causes.
Y groups
5. Identify what statistical tool to use
(Outputs) 6. Identify Ho and Ha

Logistic 7. Compute for p value using Minitab


Discrete Regression Chi-square
DATA NOT NORMAL, and you need
normal data to perform a tool?
1. Collect more data
2. Check 6 sources of non normality
3. Transform Data using BoxCox
4. Use the alternative tests/ non
parametric

127 www.6sigmaPH.com
Statistical Tests for Non Normal Data

127 www.6sigmaPH.com
Examples
The type of data you have or will collect determines what tools you can use.

X data
Continuous Discrete
Scatter Plot Stratified Frequency Plots or
Continuous

Mult-Vari Charts

X1

X2
Y data

X3
Stratified Frequency Plots Table of Results
Discrete

Factor A present?
Factor B present? Yes No
Ya Yes
6 12
Yb
No 11 31

24 www.6sigmaPH.com
Examples
X data
Continuous Discrete
Theory: The more time spent on the Theory: The higher the level of
phone with the customer, the larger the approval needed, the longer it takes to
sales close the sale
Continuous

Y = $ Amount of purchase Y = Time to close the sale

X = Amount of time spent with a X = Level of approval needed


customer
Y data

Theory: The more time spent with Theory: Experienced sales staff will
acustomer, the more likely it is we will sell more types of products than
make a sale inexperienced sales staff
Discrete

Y = Make the sale? Yes or No Y = Types of products sold

X = How much time spent with a X = Experience level of a salesperson


customer?

25 www.6sigmaPH.com

You might also like