Quote:
Originally Posted by SteveEisenberg
See Slide 5 here:
This is how I was taught and what I believe. Standard statistical tests assume a near-infinte N to n ratio because anything else would add complexity without real-world significance.
. I just looked for it on the internet and did not find it. Can anyone who went further than I did in statistics quantify this?
It could make a good term paper topic in a liberal artsy statistical methods class. No need to credit me  |
Not having a background in statistical analysis other than Operational Risk Management, I can't comment on the math involved, but I
can point out that the Boolean expressions of the specific questions can have a variance impact on an extrapolated N to n ratio if the answers to those questions are too open to interpretation. For example, did the poll ask "Have you read an eBook in the last year?" or did it as "Have you read a paper book in the last year?" I kind of mentioned this, but not having the math background you do I was unable to express it as an equation. You're way better at that ("more gooder"?) than I am.
Looking at the other slides in that presentation, I don't see anything that really translates my point that how a query is worded can affect the statistical likelihood of certain answers. Can you see what I'm saying?