Re: Sample size - How big should it be?

Stan Brown wrote:
Sun, 27 Jan 2008 08:41:02 GMT from Rob <user@xxxxxxxxxxx>:
Rob <user@xxxxxxxxxxx> wrote in news:TEEmj.7232$421.4228@news-
server.bigpond.net.au:

How do you decide how big your sample should be?

Ok I have k = N/n
OK lets say I was doing an employee survey total population 1000 (N)

Using a random number generator I pick a sample of (n)? employees to survey.

Still not sure what k is meant to be.

I got my sampling mixed I was describing the Systematic Sample N=64 n=8 k=8 You randomly select the first person sampled and then pick every 8th person after that.

A sample based on a random number generator I suspect would produce a better sample.

How do I work out what size my sample I would need to get a representative sample? What is considered to be significant?

Is this course work?


No, unfortunately, I am working from a good book (Statistics for Managers using Microsoft Excel) trying to build on some very basic statistics from a Biology degree many moons ago.

If so, it looks like right now you're in the sampling-and-descriptive-statistics portion of the course, and your question will be answered in the inferential-statistics portion.

Briefly, "representative" and "significant" are matters of degree. You have to decide up front what an acceptable significance level is. (5% and 1% and 0.1% are common choices, but not the only ones.) Or if you're trying to estimate a quantity, you decide up front what margin of error you can accept and what level of confidence you need. Either way, once those decisions are made then there's a formula that tells you how big a sample you need.

For a simple employee survey what would you think is reasonable?


(The formulas also require you to know something about your population -- often this is obtained through a small pilot study.)


Thanks for that. It is so obvious now! If the standard deviation is high you would need a larger sample.

You can try and predict what it the standard deviation going to be but you really have to wait till the end of the survey to work it out for sure.

While I have you - if I don't use random sample ie. I invite everybody in the company to take part in an anonymous online survey and only take the people that reply. How do I determine if my results are meaningful?

That one's easy: they're not. All the statistical techniques you will learn depend on having a good random sample. If you have a self-
selected sample, there's an excellent chance they are not representative of the population.

Side question here - When dealing in surveys aren't the samples always to some extent, self selected anyway?

Not every one is going to respond to a survey. You can't force them and if you could they might give false information just to get rid of you.

I mean if 1% reply I would say the result do not mean much.

Not necessarily. Presidential polls typically sample about 1000 voters, which is well under 1% of all voters, yet they are accurate to within ±3%. When testing yes/no data, what matters is how many are in the sample and not what percent of the population is in the sample.

If 100% reply then I could be confident of the response. How do I
determine what size sample is big enough.

Tell us more about what you're trying to measure, and what significance level or confidence level you're shooting for.

I don't know. In scientific papers they aim for 95% confidence interval that is the only number I have been exposed to. I suspect that they do not use such a high confidence level in other fields but I have no idea really.
.

Relevant Pages

  • Re: Sample size - How big should it be?
    ... OK lets say I was doing an employee survey total population 1000 ... You have to decide up front what an acceptable significance level is. ... voters, which is well under 1% of all voters, yet they are accurate ... significance level or confidence level you're shooting for. ...
    (sci.stat.edu)
  • Re: Linux Market share?
    ... >>random computer users and you have a valid statistical sampling. ... Perhaps this is why I said to survey *random* computer users. ... 90% confidence level of being accurate to within 1%. ...
    (alt.os.linux.suse)
  • Re: Anyone good at statistics...??
    ... Just wondering about all those surveys that ask hundreds or thousands of people what they think of Darwinism, Creationism, etc: I'm told that when the figures are extrapolated to produce an estimate for the entire population, there's some kind of 'confidence level' that can be calculated from the size of the sample. ... Hoe does the 'three-ness' of your survey show up in your final results? ... Margin of Error and Confidence Levels Made Simple ... For sample sizes way below that, the usual assumption of normality no longer holds. ...
    (talk.origins)
  • Re: How to figure the significance level or p value of a survey?
    ... significance level or p value for such a survey? ... [numerous questions, ... Department of Mathematics and Statistics ... I gather it would be that the results of the given survey are not ...
    (sci.stat.math)
  • Re: Anyone good at statistics...??
    ... people what they think of Darwinism, Creationism, etc: ... there's some kind of 'confidence level' that can be calculated ... Hoe does the 'three-ness' of your survey ... Margin of Error and Confidence Levels Made Simple ...
    (talk.origins)