1.4 Experimental Design Flashcards
What are three key elements of a well-designed experiment?
control, randomization & replication
confounding factor
occurs when an experimenter cannot determine the difference between the different factors effecting the variable, making it hard to tell what is truly causing the observed outcome.
placebo effect
subject reacts favorably to a placebo but was given a fake treatment
blinding
subjects do not know whether they are receiving a treatment or a placebo
double-blind experiment
neither the experimenter no the subjects know whether the subjects are receiving the treatment or placebo
randomization
process of randomly assigning subjects to different treatment groups
completely randomized design
subjects are randomly assigned to different groups
what are blocks?
groups of subjects with similar characteristics
randomized block designs
Subjects grouped into blocks based on a characteristic (age, gender, etc), then within the blocks are randomly assigned to different treatment groups
matched-pairs design
Two subjects with similar characteristics matched together
one assigned as the treatment group & the other = control group
replication
repetition of an experiment under the same or similar conditions
census
count or measure of an entire population
sampling
count or measure of a part of the population and is more commonly used in statistical studies
what is one technique to guard against a sampling error?
Use a random sample
what is a stratified sample?
A “sample” of each strata of the population
what is a cluster sample?
divide the population into groups called clusters
select all of the members in one or more (but not all) of the clusters
care must be taken to ensure that the members of clusters have similar characteristics
systematic sample
Every person in a population is assigned a # and then at regular intervals a person is chosen for the study
what is a convenience sample?
common use is randomly stopping people in shopping malls to ask them questions
What is important to remember in a stratified sample?
Strata used must be in proportion to actual % of occurrences in population
What to remember about systematic samples?
Regular patterns in data will skew results