How To Think Statistically With Six Sigma

The data gathering exercise results in quantitative dataeither dependent orindependent
in abundance. How you want to analyze it depends3. What are my anticipations about the statements on
broadly on your plan to arrive at the solution.data that I will be able to make?a. Define the sample
Nevertheless, it depends on three fundamentaldata but without generalizing to the larger batch sizei.
questions. But as a precursor to these questions, oneDiscuss each factor such as distribution, central
must keep in mind that the larger purpose of usingtendency and variation in the context of a single
wide ranging interacting data is to understand thevariable.ii. Discuss the relationship between two or
processes, problems and the best possible solutions asmore variables if that is the case.b. Now, moving away
applied to Six Sigma implementation.a bit, generalize the samples to the batch size from
Six Sigma: Statistical Thinkingwhich they were drawn. The process of statistical
Statistical thinking involves the tendency to want toinference or hypothesis testing, as this is called, relies
study the complete contextual situation when a wideon the probability theory to determine the risk of an
ranging statistical inputs and control factors of severalinaccurate generalization.i. For a single variable, discuss
natures may be interacting simultaneously to producethe various factors inthe same way as in the above
a particular output.case.ii. For two or more samples discuss the
To understand the principle better, one can begin withdifferences between them concerning whether they
the one factor at a time (OFAT) theory, which refersare independent or dependent?iii. Relationship between
to the natural tendency of the investigator to changetwo variables and again the relationship shared
only one factor at a time and 'record' the results until allbetween more variables.
other factors are tested this way. The results need toIn continuance with the discussion, the choice for
be put in place in the natural logical manner that wouldadopting the appropriate statistical technique and going
have occurred had the study been conducted in theahead with the task on hand rests with the answers
opposite of OFAT.to the above questions. Nevertheless, the philosophy
The Fundamental Questionof effective statistical thinking and action on a further
As we discussed earlier, there are three fundamentalcourse is better based on the following guiding
questions that need to be addressed in the order thatprinciples:
the data is analyzed.1. In a system all reactions occur in interconnected
1. Whether the level of the measurement of theprocesses
variables is known? If yes;a. Nominal or Crude Ordinalb.2. Variation is part and parcel of all processes
Good Ordinal or Interval or Ratio3. The key to success lies in understanding and
2. Size of the sample is another consideration. Whatreducing variations
kinds and how many of them are being considered?a.Statistical thinking succeeds in paving the way for a
One sample onlyb. Two samples; Specify eitherholistic approach to the deployment of Six Sigma. It
dependent or independentc. Multiple samples; Specifycan't be thought of in isolation.