Ch. 11 – 13 - Gathering Data
Def’n: An observational study is a study where a researcher observes characteristics of
subjects in samples from populations of interest.
A retrospective studyis an observational study in which subjects are selected and
then their previous conditions/behaviours are determined.
A prospective study is an observational study in which subjects are followed to
observe future outcomes. No treatments are deliberately applied.
expenriment is a study where a researcher applies different treatments to
different subjects and observes the outcomes. A controlled clinical trial is a type of
1. Infer to a larger population (Population)
2. Factor causes change in response (Causal)
Yes Both inferences Causal
Random are possible inferences
Assignment? Population Neither is
No inferences possible
Both types of study allow for population inferences, but only a properly designed (and
randomized) experiment allows for causal inferences to be valid. Experiments are not
Def’n: A sampling frame is the list of subjects in the population from which the sample
A random sample is a sample drawn in such a way that each element of the
population has a chance of being selected. If chances are all the same Æ SRS of size n
Ex11.1) A deck of cards: picking a card is a simple random sample. Moreover,
placing the card back in the deck is a sample with replacement. Otherwise, there is
sampling without replacement.
Other sampling methods:
- stratified random sample: divide population into strata, SRS from each stratum.
- cluster random sample: divide population into large # of clusters, select SRS of clusters.
- systematic sample: select individuals systematically from a sampling frame.
- convenience sample: select individuals who are conveniently available.
- voluntary response sample: collect data from individuals who volunteer