HOW TO GET DATA WE CAN RELY UPON
A sample statistic from a simple random sample (SRS) has a predictable pattern of values in repeated sampling. This pattern is called the sampling distribution of the statistic. Knowledge of the sampling distribution allows us to make statements about how far the sample proportion p is likely to wander from the population proportion p owing to sampling variability.
Bias is consistent, repeated divergence of the sample statistic from the population parameter in the same direction. Lack of precision means that in repeated sampling, the values of the sample statistic are spread out or scattered. The result of sampling is not repeatable.
To obtain a stratified random sample:
1. Divide the sampling frame into groups, called strata, of units. The strata are chosen because we have a special interest in these groups within the population or because the units in each stratum resemble each other.
2. Take a separate SRS in each stratum and combine these to make up the stratified random sample.
Two basic types of error associated with any method of collecting sample data are:
1. Sampling errors which are caused by the act of taking a sample. They cause sample results to be different from the results of a census.
2. Non-sampling errors which are errors that are not related to the act of selecting a sample from the population and that might be present even in a census.
Non-sampling errors Include:
1. Missing data which is due to an inability to contact a subject or to the subject's refusal to respond.
2. Response errors which concern the subject's own response.
3. Processing errors which are mistakes on such mechanical tasks as doing math, coding, data assemble, etc.