>>>
http://www.bls.gov/cps/cps_htgm.htm>>>
>>>Interesting how the BLS calls 60,000 households each month and from the gathered data defines the number of people employed or unemployed. That seems to give it a less than personal feeling for reality. One persons reality may differ from the BLS.
>>
>>Just looked it up and there are about 115,000,000 households in the US. Found a sample size calculator online and it says that the confidence interval for 60,000 out of 115,000,000 is 0.4 at the 95% level. That is, that 95% of the time, the number they publish based on that survey is within 0.4% of accurate. That's pretty good. Switching to the 99% confidence level, the interval goes to 0.53%. Again, pretty good.
>>
>>Tamar
>
>I think that in order for the Confidence level Calc to be reliable, you have to assume the sample was completely random. IOW, if the sample was skewed, i.e. just call households in Scarsdale, NY, that would definitely skew the results.
True. I was assuming that the folks doing the study have a clue. My main reason for posting was to point out that 60,000 was actually quite a large sample size for this study.
Tamar