Business Results/ Sigma level

Calculations

Process performance metrics

Typical example to illustrate the several measures
used in Six Sigma
A process produces 40,000 pencils. Three types
of defects that can occur
Their numbers are:
Blurred printing: 36
Wrong dimensions: 118
Rolled ends : 11
Total number of defects = 36+118+11 =165

DPU/ DPMO

DPU (Defects per unit) = (#defects) /

(#units) = 165/40000 = 0.004125
DPMO (Defects per million opportunities)
Formula for DPMO = (#defects x 1,000,000) /
(total number of opportunities)

Here we need to know the number of ways

each defect can occur on each item.

Blurred printing can happen only one way (pencils slip in the
fixture).
Number of opportunities for this case =40,000x1 =40,000
Three independent places where dimensions are checked and
so in that case the opportunities for this batch are = 3 x
40,000 =120,000
Rolled ends can occur at the top and bottom and in this case
opportunities are = 2 x 40,000 = 80,000
Total number of opportunities are 40,000 + 120,000 +
80,000 = 240,000
Formula for DPMO = (#defects x 1,000,000) / (total number
of opportunities)
= 165,000,000/ 240,000 = 687.5

DPO/DPMO
DPO =

# of defects
(#of units) x (#of opportunities)
E.g., #of units = 330
# of opportunities (type of defects) = 7
# total number of defects = 59
DPO = 59/ 330 x7 = 0.025
DPMO = DPO x 106
=0.025x1,000,000=25,000
In the earlier pencil example
DPMO = 165x 100,000/(40,000 X6)=687.5

RTY/PPM

Throughput yield, Also called yield

This is given by the formula = e - DPU
In the present case,
throughput yield = e -0.004125 = 0.996
Rolled through put yield (RTY)
This applies to a series of processes and is
found by multiplying the individual process
yields
If a panel goes through four processes whose
yields are .994, .987, .951 and .990
RTY = .994 x .087 x .951 x.990 = .924

Normally when referring to defects we try

to indicate in PPM (Parts per million)

PPM = DPU x 1,000,000

In the present case it is = 0.004125 x 1,000,000 = 4125

It is also referred to as contaminants.

E.g., 0.23 grams of insect parts are found

in 25 kgs of a product:
PPM = 0.23 x 1,000,000 /25,000 = 9.2
ppm

COPQ/Sigma Levels

Cost of Poor Quality (COPQ)

This is helpful in prioritizing projects in
terms of their impact on the enterprise
in terms of money.
It should include costs involved in rework, warranty, late deliveries,
customer dissatisfaction some of the
main things one should always consider.

Sigma Levels

E.g., Tolerance for a part are given as 5.000 + 0.012 (4.98 to

5.012)
Data from a particular shift indicates that the process mean is
5.000 and standard deviation = 0.004

+ 3 fits inside the tolerance = + 0.012

Capability calculations will show

Cp = Cpk =1

Traditional way you would use standard normal table to determine

the area under the normal curve between +3.

From experience the mean could shift and for Six Sigma
process, it is allowed to shift to +1.5 or yield is 0.9332
Suppose the variation has reduced to =0.002 and area
under a normal curve is to the right of - 4.5

This turns out to be 0.9999966

The defect level = 1-0.99999966 =0.0000034 or 3.4 ppm.

This is the often quoted as defect level for Six Sigma

processes.
Easy way is to refer the Sigma table given to all and go by
different criteria data you have to assign the Sigma levels for
your process.

Safe is to first look for the % yield or

success to find out the process sigma.
If you are sure about the different ways
defects could occur and perceived in your
organization calculate DPMO.
Still I would advice cross-check with
Sigma other method.
If you want to know the throughput yield,
use the formula involving DPU.

Another Example:
Your department performed 535 specific operations last month. Of
these, 43 were defective (they fell outside the acceptable range of
outcomes). This means that 492 of the operations were
successful.
The yield was: 492 535 = 91.9%
Referring to Table 1, we discover that this outcome represents
Sigma somewhere between 2.5 and 3.
If you were able to reduce the number of defects by half, ending
up with 21, your acceptable outcomes would then grow to 514 out
of 535 operations, and your yield would increases well:
The yield is 514 535 = 96.1%
Now the Sigma is between 3 and 4, a significant improvement. Of
course, if you cut defects in half, you are going to know your
outcomes have improved, so what purpose does Six Sigma
provide beyond the obvious scorekeeping?

As the preceding example demonstrates, improvement in

quality can be specifically measured.
In practice, you may be dealing with a much greater volume of
outcomes, and the incremental rate of success is likely to be
smaller than that shown in the example;
and Six Sigma is far more than a measuring system.
It is a way of doing things, a change in cultural attitude that is
designed to create a company-wide team in practical terms.
As far as the scorekeeping aspects of Six Sigma go, if you
begin with an assumption that a change in procedures will
produce an expected change in outcomes, you can then
compare actual to projected results to judge the success of
your work.
Key Point What makes Six Sigma different from most other
quality control programs? It is more than just a way to
improve performance; it is a method for changing the
corporate culture, from top to bottom.

An operation can be any function you perform

delivery of goods, telephone contact,
balancing accounts, or executing a repair, for
example.
Any operation is measurable in Sigma terms.
The desired outcome represents satisfaction of
the customers expectation, and any time that
expectation is not met, the outcome is defective.
While measuring results is a crucial part of the
process, you will be more concerned with how
Six Sigma is applied and what role you and
other employees will perform within that
process.

So the idea of Six Sigma is much more than the

latest approach to quality control; it represents a
change in philosophy that affects everyone.
It is designed to bring everyone into a single team
with the same overall goals. So many corporate
employees especially in large organizationshave
a sense of isolation
or view their relatively small department as a realm
unto itself. Six Sigma encompasses the entire
corporation as a single team and is aimed at
removing that sense of isolation.

Key Point
Cost savings are an important aspect of quality
control, but they are only one aspect;
a permanent, effective, and rewarding quality
program requires more work.
So many quality programs have been devised,
named, and put into effect over many years.
Most fail after a while because employees lose
faith in those programs. It becomes obvious to
employees that quality control really represents
managements attempt to cut costs and expenses
and get more work from its labor force.

In other words, the program applies to the

worker but there is no change in
management itself. If the final result of a
quality program is to achieve increased
efficiency, and that results in layoffs, who
benefits?
With Six Sigma, everyone is involved and
everyone is expected to change (for the
better) as part of one overall team. The
purpose is not assigned to the rank and
file, but is shared from top to bottom.

Calculate Process Sigma first

How to Calculate Process Sigma

Consider a power company for
illustration purposes: A power
company measures their
performance in uptime of available
power to their grid. Here is the 5
step process to calculate your
process sigma.

Steps involved

Step 1: Define Your Opportunities

An opportunity is the lowest defect noticeable by a customer .
This definition, of course, is debatable within the Six Sigma
community.
"Typically, most products (and services) have more than one
opportunity of going wrong.
For example, it is estimated than in electronics assembly a
diode could have the following opportunities for error: 1)
Wrong diode and 2) wrong polarity (inserted backwards), so
for each assembly shipped, at least two defect opportunities
could be assigned for each diode.
Apparently, some manufacturers of large complex equipment
with many components prefer to [count two opportunities in
this case]. This approach dilutes Six Sigma metrics."

Many Six Sigma professionals support the counter

point. I always like to think back to the pioneer of
Six Sigma, Motorola. They built pagers that did not
require testing prior to shipment to the customer.
Their process sigma was around six, meaning that
only approximately 3.4 pagers out of a million
shipped did not function properly when the
customer received it. The customer doesn't care if
the diode is backwards or is missing, just that the
pager works.
Returning to our power company example, an
opportunity was defined as a minute of uptime. That
was the lowest (shortest) time period that was
noticeable by a customer.

Step 2: Define Your Defects

Defining what a defect is to your customer is not
easy either. You need to first communicate with
your customer through focus groups, surveys, or
other voice of the customer tools. To Motorola pager
customers, a defect was defined as a pager that did
not function properly.
Returning to our power company example, a defect
is defined by the customer as one minute of no
power. An additional defect would be noticed for
every minute that elapsed where the customer
didn't have power available.

Step 3: Measure Your Opportunities and Defects

Now that you have clear definitions of what an opportunity
and defect are, you can measure them.
The power company example is relatively straight forward,
but sometimes you may need to set up a formal data
collection plan and organize the process of data collection.
Returning to our power company example, here is the data
we collected:
Opportunities (last year): 525,600 minutes
Defects (last year): 500 minutes

Step 4: Calculate Your Yield

The process yield is calculated by
subtracting the total number of defects
from the total number of opportunities,
dividing by the total number of
opportunities, and finally multiplying the
result by 100.
Returning to our power company example,
the yield would be calculated as:((525,600
- 500) / 525,600) * 100 = 99.90%

Step 5: Look Up Process

Sigma
The final step (if not using the
Process Sigma Calculator) is to
look up your sigma on a sigma
conversion table, using your
process yield calculated in Step 4.

Customer CTQs - Defining

Defect, Unit and Opportunity

Start With The Customer

Before you can define your process defects, units and
opportunities, you need to understand the needs of your
customers.
Voice of the Customer (Customer Needs, eSurveys, Focus
Groups, Surveys) is the process of gathering customer
comments/quotes and translating them into issues and
specifications.
From these comments, issues and specifications come the
customer CTQ (Critical To Quality) a product or service
characteristic that must be met to satisfy a customer
specification or requirement.

The traditional calculation method

results in the following Z-scores for error
free processes:
0 percent error-free yield = negative
infinity Z-score
50 percent error-free yield = 1.5 Z-score
99.99966 percent error-free yield = 6.0
Z-score
100 percent error-free yield = positive
infinity Z-score

Figuring the sigma for most processes is pretty easy. A

calculator is helpful, but no advanced math is needed.
What is needed is basic data and definitions for the
following:
The unit, or item being delivered to the customer
The requirements that make the unit good or bad for
the customer
The number of requirements, or defect opportunities, for
each unit
For example, in the pizza business, our unit is a pizza! We
determine the four main requirements:
correct ingredients, hot, on time, and undamaged.
These four requirements are also the four defect
opportunities for each pizza.

We collect data on 500 delivered pizzas and find that 25 were late,
10 were too cold, 7 were damaged, and 16 had wrong ingredients.
To calculate sigma, we take the total number of defects counted,
divide by the total number of units, and multiply by the number of
defect opportunities:
(25+10+7+16)
500 x 4
This gives us 58 / 2000, or 0.029;
opportunity (DPO).

we call this defects per

As we explained earlier, we usually consider 1 million opportunities,

so
that would be 29,000 defects per million opportunities (DPMO).
Now all you do is look up that DPMO number in a table to find what
sigma it represents.
In this case, the pizza process is performing at about 3.3 sigma.