One purpose of using random probability sampling methods is to apply a variety of statistical techniques to estimate the confidence one can have that the characteristics of a sample accurately reflect the study population. Sampling error is a random product of sampling. However, when random sampling methods are used it is possible to compute how much the sample-based estimate of the characteristic will vary from the study population by chance because of sampling. The larger the sample size and the less variability of the characteristic being measured, the more accurate a sample-based estimate will be. Sampling error can be defined as the variation around the true population value that results from random sample differences drawn from the population.
The standard error of mean is the most commonly used statistic to describe sampling error :
SE = [s2/n]0.5
Where: s2 is the variance derived from the sample
n is the sample size
and [sum]0.5 is the square root of the product
Alternatively, the standard error of mean is more easily computed from a proportion statement, since the variance of a proportion is expressed as p[1-p]: the standard error of mean of a proportion is computed from: [p(1-p)/n]0.5.
The standard error of mean is the most commonly used statistic to describe sampling error :
SE = [s2/n]0.5
Where: s2 is the variance derived from the sample
n is the sample size
and [sum]0.5 is the square root of the product
Alternatively, the standard error of mean is more easily computed from a proportion statement, since the variance of a proportion is expressed as p[1-p]: the standard error of mean of a proportion is computed from: [p(1-p)/n]0.5.
Thanks
0 comments:
Post a Comment