June 23, 2007
Six Sigma: Data Stratification Model
We have all been there from one time to another in a large meeting room, hearing a problem from everyone’s perspective. Needless to say, when you are in the mix, it is good to start analyzing. To gain an understanding of what is going on with the process, lets start with the basics: who, what, when and where. Answering these questions in detail is the data stratification model, and it clarifies the collected information to reveal the root cause of the problem.
Six sigma teams use the data stratification model whenever data is collected. Because it quickly clarifies who is associated with the problem, what type of problem is occurring, when the problem is happening, and where the problem is occurring. The purpose of the model is to help the team clarify the problem and its impact. The information is also very useful when analyzing the problem to find the root cause.
The process of data stratification is to break it down into layers (AKA strata). The questions who, what, when, and where represent the layers.
- The who layer – The question who is intended to define who is associated with the process problem. This information could be further subdivided by:
- Vendor
- Department
- Individual
- Customer Type
- The what layer – The question what defines the type of problem which is occurring. This information can be further categorized by:
- defect category
- type of complaint
- reason for a complaint.
- The when layer – The question when is pretty much self explanatory it clarifies when. This information can be further clarified by:
- time of day
- day of week
- month of year
- fiscal quarter.
- Shift
- The where layer – The where question clarifies where a problem occurs. This can be clarified by:
- facility
- region
- location on product
- location in service.
By asking the key questions from the data stratification model, the who, what, when, and where of a process problem are further brought into focus.
While process data may not be available to answer all the model's questions, the team should nevertheless consider using the model whenever it collects data. Answering only some of the questions can still greatly benefit an investigation. Here is an example, for quantifying the problem surrounding OR charges.
Data Stratification – Late OR Charges |
||
Factors |
Definitions |
Examples |
Who: |
The question "Who?" is intended to define the person or organizational entity that is associated with the process problem. |
|
What: |
The question "What?" is intended to define the type of problem that is occurring in the process. |
|
When: |
The question "When?" is intended to define the time frame in which the problem is occurring in the process. |
|
Where: |
The question "Where?" is intended to define the location in which the problem is occurring in the process. |
|
HIMSS Sample RFP Documents
ICD-10 is in the distance
Deming's Adaption of the 14 Points for Medical Service
Do we have the right mix of projects?
Priorization: The art of choosing what not to do
The key elements in establishing a PMO
The Code Yellow Required meeting
August 2008
July 2008
May 2008
April 2008
March 2008
February 2008
January 2008
December 2007
November 2007
October 2007
September 2007
August 2007
July 2007
June 2007
May 2007
April 2007
March 2007
February 2007
January 2007
December 2006
November 2006
August 2006
June 2006
May 2006
April 2006
March 2006
February 2006
January 2006
November 2005
October 2005
September 2005
August 2005
June 2005
May 2005
April 2005
March 2005
February 2005
January 2005
December 2004
November 2004
October 2004
September 2004
August 2004
July 2004
June 2004
May 2004
April 2004
March 2004
February 2004
January 2004
December 2003
November 2003
October 2003
Joel on Software
David Ross
Edward Prevost
Martin Fowler
The Health Care Blog
The Tales of Hoffman
The Business Word
Medical Rants
Christina's Considerations
Paul Levy
HIS Talk
Appropriate IT
Candid CIO
RSS feed




