Skip to main content
No. of Recommendations: 0
misc wrote:
>> (1) the size of the sample (a "random
list" and a one time sample)>>

Yes, I chose 20 stocks from a list of 100 which means a sample of one of five for the population. I'm no statistician, but I think that's pretty responsible/reliable sampling for one time sample.

Actually, that's not necessarily the case.

It's not uncommon to read about opinion polls which sample "only" thousands of people and purport to represent the opinions of the nation to within three percent. People often wonder how the networks can make broad claims about the outcome of elections based on a small percentage of the actual votes, for example. The key is not just the sample size, it's the way that the sample was chosen. A good sample is statisically representative of the larger population. If it isn't, you can't assign meaning to your results. It could be that you are accurate, or it could be that you've picked the data points which are way out at the extremes. You just don't know.

To make this more concrete, consider a poll of the opinions of the people in your city in which 20% of the populace is studied. Would you say that such a poll is accurate? What if you later found out that, through some quirk, 90% of those polled were registered libertarians? What if 75% or those surveyed were among the top 25% of wage earners? What if 93% lived in the suburbs rather than the city?

Similarly, we might ask questions about the 20% of timeliness one stocks you chose. What is the average market cap of your sample versus that of all 100 stocks? Maybe you just picked 20 of the smallest stocks in the group. What industries are represented in your sample, and in what proprortions? Perhaps you have an overage of stocks from industries that have performed poorly since the rankings. What's the average EPS growth rate of your sample versus the larger group? Maybe you picked companies whose earnings aren't growing as well as the rest of the group. Relative strength? Maybe you've picked the poorly performing stocks from the larger population (a.k.a. the "Network Associates Syndrome").

Of course, once you start thinking seriously about how you would answer all of these questions, you realize that it's easier to just look at all 100 stocks. ;-)

--
FreeFlyingFool
Print the post  

Announcements

What was Your Dumbest Investment?
Share it with us -- and learn from others' stories of flubs.
When Life Gives You Lemons
We all have had hardships and made poor decisions. The important thing is how we respond and grow. Read the story of a Fool who started from nothing, and looks to gain everything.
Contact Us
Contact Customer Service and other Fool departments here.
Work for Fools?
Winner of the Washingtonian great places to work, and Glassdoor #1 Company to Work For 2015! Have access to all of TMF's online and email products for FREE, and be paid for your contributions to TMF! Click the link and start your Fool career.