click below
click below
Normal Size Small Size show me how
STA CHAPTER 4
| Question | Answer |
|---|---|
| Sampling frames | A list from where individuals are drawed from a sample |
| Frame error | Not an accurate or complete representation of the population |
| 6 Non-Sampling errors | 1. Under-coverage 2. Erroneous inclusions 3. Multiple inclusions 4. Processing errors 5. Response error 6. Non-response |
| Under-coverage | If the sampling frame leaves out certain groups of people even random samples from that frame will be biased!! |
| Under-coverage example | Using telephone directories to poll, but leaving out people with only cell-phones. Leaves out youth |
| Erroneous inclusions | Occurs if the frame includes individuals that are not in the population of interest. Invalid units |
| Erroneous inclusions example | Residents who moved out of sampled states |
| Multiple inclusions | occur if some population members appear more times in the sampling frame so that they have a higher chance of being sampled |
| Multiple inclusions example | Using households with multiple email addresses |
| Processing errors | mistakes in mechanical tasks such as doing math or entering responses into a computer |
| Processing errors examples | Typing in "100" instead of "10" |
| Response error | When a subject gives an incorrect response |
| Response error example | A person lying about use of drugs |
| Non-response | The failure to obtain data from an individual selected for a sample |
| Non-response example | If a survey respondent skips the income question |
| Most challenging non-sampling error? | Non-response |
| The announced margin of error for a sample survey only covers | RANDOM SAMPLING ERROR So this is things like under-coverage, non response. and everything discussed earlier |
| What else has an influence on answers? | Wording |
| Probability Sample | A sample chosen by chance |
| Probability Sample example | Random # generator |
| How to choose a Stratified Random Sample (SRS) | 1. Divide sampling frame into distinct groups of individuals (STRATA) 2. Choose strata according to any special interest you have in a certain group with in pop. 3. Take a separate SRS in each stratum and combine these to make up the complete sample |