Experiments vs. Observational Studies Experiments vs. Observational Studies (Cont.)

Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

Experiments vs.

Observational Studies
In an experiment investigators apply
treatments to experimental units (people,
animals, plots of land, etc.) and then
proceed to observe the effect of the
treatments on the experimental units.

Experiments vs. Observational


Studies (cont.)
In an observational study investigators
observe subjects and measure variables
of interest without assigning treatments to
the subjects. The treatment that each
subject receives is determined beyond the
control of the investigator.

In a randomized experiment investigators


control the assignment of treatments to
experimental units using a chance
mechanism (like the flip of a coin or a
computer's random number generator).

For example, suppose we want to study the


effect of smoking on lung capacity in women.
1

Experiment

Observational Study

Find 100 women age 20 who do not currently


smoke.

Find 100 women age 30 of which 50 have


been smoking a pack a day for 10 years
while the other 50 have been smoke free
for 10 years.

Randomly assign 50 of the 100 women to the


smoking treatment and the other 50 to the no
smoking treatment.
Those in the smoking group smoke a pack a day
for 10 years while those in the control group remain
smoke free for 10 years.
Measure lung capacity for each of the 100 women.
Analyze, interpret, and draw conclusions from data.
3

Measure lung capacity for each of the 100


women.
Analyze, interpret, and draw conclusions
from data.
4

Fishers Hypothesis

Fishers Hypothesis (cont.)

Suppose there is a gene that causes smoking to


appear to be a very pleasurable experience.
Suppose the same gene also causes
emphysema, lung cancer, throat cancer, etc.
People who have the gene will be more likely to
smoke than people who do not have the gene.
People who have the gene will be more likely to
get emphysema, lung cancer, throat cancer, etc.

So is it really smoking that causes health


problems? Maybe it is just the gene?
A confounding variable is related both to
group membership and to the outcome of
interest. Its presence makes it hard to
establish the outcome as being a direct
consequence of group membership.

Always Randomize if Possible


Consider a field experiment intended to
compare the yield of two corn varieties
(A and B).
Suppose the field is divided into 20 plots that
run from one end of the field to the other.
Is there anything wrong with the following
assignment of varieties to field plots?
ABABABABABABABABABAB
7

You might also like