Vol. 12, No. 7 July 2010

 Contents
 FMEA: A chance to prevent failures rather than cleaning up after them Quality Quiz: With a video! Data in everyday life Six Sigma Bytes and pieces FYI: Current releases
 Send Quality eLine to a friend! Just type in your friend's email below:
 Software

Quality Quiz from Professor Cleary

Congratulations:
"B" is correct.

If Quinn Quip had listened to the introductory lecture in his first statistics class, he might have heard about the rationale for taking samples, which involves more than simply pursuing a census of all members of a group. This rationale is based on a number of considerations:

1. A sample is less consuming than a census.
2. A sample costs far less than a total census.
3. A sample is far easier to undertake.

Next, he might have learned about the two types of samples: nonprobability samples and probability samples. A list of these follows:

 Probability samples Nonprobability samples Simple random sample Judgment sample Stratified sample Quota sample Cluster sample Convenience sample Sequential sample

When Quip refers to a “simple random sample,” he is referring to a probability sample. In a simple random sample, every member of the population has an equal likelihood of being selected for the sample.

If Quip wants to estimate the average age of those who live in Quincy, he realizes (after last month’s experience) that if he takes a simple random sample of 42, he will undoubtedly achieve the accuracy that he desires.

What he might consider is assigning each person in the population of 1,000 a number, from 000 to 999. Using a table of random digits, he would then select 42 people for his sample.

What he will undoubtedly learn (along with his boss, Russ T. Buckett) is that there is no such thing as a “quadruple binomial sample”—a phrase that leaped into his mind on the basis of the complexity of the fireworks he had purchased for the Fourth of July.

Next month, we’ll consider the other approaches to nonprobabilistic sampling. Stay tuned.