Ch7 8 Flashcards
“to a certain degree”, do not randomly assign subjects
Quasi Experiment Designs
When random assignment is not possible, we should select subjects in some way that makes 2 groups as comparable as possible
Non-equivalent group designs
examining series of observations on some variable over time
Time series designs
series of observations is compared before & after some intervention is introduces
Simple interrupted time series
selecting part of a population
sampling
method of selection in which each member of a population has a known chance/ probability of being selected
Probability Sampling
those selected are not typical or representative of larger population they have been chosen from
Bias
Likelihood that any given element will be selected is Not Known
Non-Probability Sampling
ex: list of 10000 elements and we want sample of 1000
Systematic Sampling example
rather than selecting our sample from total population
stratified sampling
Purposely produce samples not representative of population on some variable
Disproportionate Stratified Sampling
Initial sampling of groups of elements (clusters) followed by selection of elements w/in each selected cluster
Multistage cluster sampling
select sample based on knowledge of population & research goals
Purposive (aka judgmental Sampling)
Begins w/table describing characteristics of target population we wish to represent, assign all persons in a given cell a weight appropriate to their portion of total population
Quota samping
Surveys among students in class
Reliance on available subjects