1, How to take sample: -Simple random sample: A sampl drawn so that every possible sample of the size we plan to draw has an equal chance of being selected. As well, each combination of individuals has an equal chance of being selected.

- Stratified: Divide the population into groups of similar individuals (called strata) and take SRS from each group. Strata are homogeneous within and heterogeneous between.

-Cluster: Within a cluster, we have a range of people which reflects the whole population and all clusters are similar. We sample everyone in a cluster. Clusters are homogeneous between and heterogeneous within.

-Systemetic:Used a fixed interval to select numbers from sampling frame.

-Multistage:Combineseveral method

2, Sample size does not depend on population size.

3, Sampling errors: difference between parameters and statistics due to random process. It is a legitimate difference, not really an error. It depends on sample size. If sample sizes increases, sampling error decreases.

4, Non sampling errors: not depend on sample size, due to bad sampling method.

-Undercoverage bias: some parts of population are less representative than they should be.

-Voluntary response bias: Respondents choose to participate. Even if the sampling frame is of interest, voluntary response samples are often biased towards those with strong feelings, esp from those with strong negative opinions. All who do respond are counted so its usually biased.

-Non voluntary response bias: may select sample appropriately but individuals who don’t response may have common characteristics and