Too Much Data, Too Little, or Just Enough? Ask Minitab's Power and Sample Size ...

State College, Pa. (PRWEB) May 28, 2011

Gathering data for statistical analysis is like tasting fine wine-it's important to get just the right amount. With wine, too small a sip prevents the accurate assessment of a subtle bouquet, but too large a sip overwhelms the palate. Similarly, gathering too little data limits the reliability of an analysis, but gathering too much data wastes resources.

An excessively large or small sip of wine isn't the end of the world, but the stakes are higher people who need to analyze data . Fortunately, Minitab 16 Statistical Software's Power and Sample Size tools can determine exactly how much data is needed to be sure about the results of an analysis.

Minitab's Power and Sample Size tools help users make sure they collect enough data to conduct a reliable analysis, while avoiding wasting resources by collecting more data than they need. Minitab can also asses the statistical power of tests that have already been run and estimate the sample size needed to obtain a specific margin of error.

Statistical power is the likelihood that a test will identify a significant difference or effect when one truly exists. Testing critical airplane parts, for example, demands a higher degree of certainty than testing DVD players.

Minitab helps balance the need for statistical power with the expense of gathering data by answering this question: How much data do you need? This deceptively simple question takes many forms:

-- How many samples are needed to determine if the average thickness of paper differs from one supplier to another?

-- How many voters should be sampled to be 95% confident that the proportion supporting a candidate is within 3% of its true value?

-- How many times should an experiment be replicated to have at least an 85% chance of detecting the factors that significantly affect a manufacturing process?

In most cases, people want to collect just enough data to ensure they have sufficient power to draw sound conclusions. Minitab Statistical Software includes tools to estimate sample size and power for the following statistical tests :

-- Sample Size for Estimation -- General Full Factorial Design

Minitab's power and sample size capabilities also allow users to examine how different test properties affect each other. For example, a user who needs to perform a two-sample t-test can calculate:

-- Sample sizes-the number of observations in each sample.

Select The Right Improvement Projects | Soarent Vision

By George Lee Sye

Lean Six Sigma is really a business improvement strategy.  And let’s face it; most companies are doing business improvement in one form or another.  Where they often fall short is in one of the most important aspects of success – business improvement project identification.

What I’ve found is that the vast majority of companies have similar approaches to business improvement. To understand what I mean take a look at this example.

The following is a list of business improvement projects for a medium sized clothing business.

IMPROVEMENT PROJECT LIST

Expand the warehouse and implement a bar coding system Renegotiate ‘per unit’ supply rates from the suppliers of blank shirts Implement a ‘cascading’ based system of performance management Negotiate a new freight contract Introduce the PASS safety system across all warehouses Replace key access with proximity card system Distribute a quarterly company newsletter Individually cling wrap dress shirts Negotiate a corporate alliance with the Zenith Hotel chain

What do you make of that list?

Notice it’s simply a list of solutions. Each idea is a way of solving some perceived problem. For example renegotiation of unit supply rates is a solution for the problem of increasing costs to produce a unit of whatever it is they manufacture.

In the absence of an improvement strategy like Lean Six Sigma, this tends to be the way business improvement is approached.

Ideas for making the business better, in solution form, are identified and undertaken as improvement projects. Managers genuinely believe they are doing business improvement and have no idea why you would want to add a Lean Six Sigma methodology to it.

I’ve even seen a situation like this where one manager believed the company was already doing Lean Six Sigma.

So What’s Missing?

The major shortfall with this approach is many opportunities for genuine performance improvement are missed because SOLUTIONS ARE NOT KNOWN. This approach produces a list of improvement ideas that answer one question:

‘What can we DO to improve our business?’

In the case of our clothing manufacturer, this question might generate ideas like these.