Ch 7 - Designing experiments Flashcards
The individuals in an experiment are the
experimental units.
If they are human, we call them subjects.
The explanatory variables in an experiment are often called
factors.
A treatment is
any specific experimental condition applied to the subjects.
If an experiment has several factors, a treatment is a combination of specific levels of each factor.
Experiments compare the response to a given treatment versus to:
another treatment
the absence of treatment (often called a control)
a placebo (a fake treatment)
randomize and replication
Experiments use replication: several or many individuals are studied.
Experiments randomize the assignment of subjects to treatments.
inventing experimental design
importance of design
Placebo effect
negative placebo effect
Bias is
a particularly challenging problem when dealing with human subjects because
(1) of the placebo effect,
(2) of human bias, conscious or unconscious, on the experimenter side.
Bias is fixed/mitigated with
A double-blind experiment - neither the subjects nor the experimenter(s) know which individuals received which treatment until the experiment is completed.
However, subjects must be informed that they will get one of a number of treatments, and must consent to that condition (it would be unethical otherwise).
Random sampling is
meant to gain information about the larger population from which we sample.
Lack of realism
Q Is the treatment appropriate for the response you want to study?
Design issues
Lack of realism
Bias
In a completely randomized experimental design
individuals are randomly assigned to groups, then the groups are randomly assigned to treatments.
In a block design
subjects are divided into groups, or blocks, prior to the experiment to test hypotheses about differences between the groups.
Matched pairs designs
1) Choose pairs of subjects that are closely matched (like twins, 2 siblings, or 2 pups of the same litter). Within each pair, randomly assign who will receive which treatment.
OR
2) give both treatments to a single person over time, in random order. In this case the “matched pair” is just the same person at different points in time.
Ethics and experimentation
Top (pulse rates): Stratified/block design, by gender (male and female)
Middle (Cow): Only one random sample of 60 cows, each examined twice (before and after): Matched pairs design
Bottom (sickle cell): Completely randomized design (patients randomly assigned to the two treatments)
