States vocabulary

Question Answer
Observational study a study based on data with no manipulation used
retrospective study subjects are selected and than their previous conditions or behaviors are determined. Not based on random sampling Focus on estimating differences between groups or associations between variables
prospective study subjects are followed to observe future outcomes. No treatment are applied. Not an experiment. Focus on estimating differences among groups during the study
experiment manipulates factor levels to create treatments, randomly assigns subjects to these treatments levels. Compares the responses of subject groups across treatments levels.
random assignment an experiment must assign experimental units to treatment groups at random.
factor a variable whose levels are controlled by the experimenter.
response a variable whose values are compared across different treatments.
experimental units individuals on whom an experiment is performed. Can be called subjects or participants
level the specific values that the experimenter chooses for a factor
treatment the process, intervention, or other controlled circumstance applied to randomly assigned experimental units. the Explanatory variable
Principles of experimental design Control, Randomize, Replicate, Block
Control make conditions as similar as possible for all treatment groups.
Randomize equalize the effects of unkown or uncontrollable source of variation
Replicate over as many subjects as possible. Results from a single subject are just anecdotes.
Block the only difference in the control group and the experimental group is the 1 thing we are testing.
statistically significant when an observed difference is too lrge for us to believe that it is likely to have occured naturally.
control group the experimental units assigned to a baseline treatment level.
Blinding don't let the patient know if they are in the control group or the experimental group.
single-blind, double blind these are two main classes of individuals who can affect the outcome of an experiment: those who could influence the results (subjects, technicians). Those who evaluate the results (juges, physicians)
placebo effect people think they feel differently just because they know they are being tested
2 ways to replicate use several subjects, or replicate the entire experiment on another group
extraneous factors factors that are not being experimented with but may be influencing the outcome. Eliminate this by blocking.
confounded variables factors that can't be distinguished between which one is affecting the outcome.
placebo a treatment known to have no effect.
match reduces unwanted variation
2 types of designs completely randomized design, and randomized block design
completely randomized design all experimental units have an equal chance of receiving any treatment
randomized block design the randomization occurs only within blocks