Summary of issues involved
Sampling
- population
and sample
- sample
vs. census
- representative sample? Watch:
- voluntary
response
- convenience
sampling
- nonresponse
- wrong
answers
- ‘silly’
answers
- subjective
aspects
- etc, etc,etc,!!!
- sampling
techniques
- SRS
(simple random sample)
- stratified
sample
- cluster
sample
DOE (Design of Experiments)
- sampling
vs. DOE
- causality
- confounding? Avoid
by
1. control
group
2. random
assignment
1. representative?
2. realistic?
3. hidden
bias
1. CRD
(Completely Randomized Design)
2. RCBD
(Randomized Complete Block Design)
Measuring
- validity
and reliability
- nominal,
ordinal, interval/ratio
- check
for
- internal
consistency
- exaggerated
precision
- right
context
- location:
mean, median, mode
- scale:
sample variance, IQR (inter quartile range)
- correlation: sample (rank) correlation coefficient ;
interpretation: use square!
Literature:
Moore, D.S. (1985).Statistics: concepts and controversies. Freeman, New York
(CBa 517.3 m078)