Know-How Exchange : Research/Metrics

Nicki,

There's an explanation on page 3 of the report that states: B-to-B Marketing in 2008: Trends in Strategies and Spending. Then there's an example on page 9.

From this, the interpretation is this:

For each of the survey questions, the authors compared the numbers resulting from the three segments (A = Revenues less than $20 million, B = revenues from $20 million to $499.9 million, C = revenues greater than $500 million) and tested to see if the difference was significant. So, on page 20, if you compare the percentage who said they use the tactic, email, (A: 86%, B: 83%, C: 85%), with a confidence of 95%, we can conclude there is no real difference. For the print advertising tactic (A: 40%, 64%, and 80%), B uses print more than A with a confidence of 95% and C uses print more than A and B with a confidence of 95%. That is, if we were to ask every company in the world this question and they all answered, we would be 95% confident that the data would show B segment businesses using print ads more than A and C using print ads more than both A and B - just as it has for the sample. We would also For executive events (A: 46%, B: 58%, C: 72%), C uses that tactic significantly more than A and B, but the difference between the use of this tactic between A and B is not significant, with a confidence of 95%. In other words, from the sample results, we can be 95% sure that if we asked all businesses and they all answered, C uses this tactic more than A and B, but we can't really say if A or B use this tactic more than the other.

I hope this helps!

Wayde

Confidence intervals don't tell the whole story. Read: https://en.wikipedia.org/wiki/Confidence_interval

Here's the relevant quotation:

"There is a difference in meaning between the common usage of the word 'confidence' and its statistical usage, which is often confusing to the layman. In common usage, a claim to 95% confidence in something is normally taken as indicating virtual certainty. In statistics, a claim to 95% confidence simply means that the researcher has seen something occur that only happens one time in twenty or less. If one were to roll two dice and get double six, few would claim this as proof that the dice were fixed, although statistically speaking one could have 97% confidence that they were. Similarly, the finding of a statistical link at 95% confidence is not proof, nor even very good evidence, that there is any real connection between the things linked."