I'm really struggling in class and this study guide was freaking crucial. Really needed help, and Sarah delivered. Shoutout Sarah, I won't forget!
Types of study Designs
- experimental study researchers assign subjects
to experimental conditions & then the response / outcome of interest is observed - experimental' conditions can be called the atments
+ Observational study researchers observe both response and explanatory variable w/o assighing a treatment (non-experimental)
X can study effect of explanatory variable on
response variable more accurately in
experimental Study - How to select partipants * Want participants to be a representative
sample of population so results can be generalized to population We also discuss several other topics like What is audience-centered process?
If you want to learn more check out How do i find the derivative of a function?
If you want to learn more check out How do you find the minimum and maximum value of a data set?
-Bias = present when results of sample arent
representative of population
sampling bias (coverage bias) - result from sample method * sample may not be random
* sample doesnt rep pop (undercoverage) Nonresponse blas - subjects refuse to participate X different characteristics of subjects * generates missing data if subjects choose If you want to learn more check out How do you find the slope of a curve at a point?
not to answer some questions
| Response bias - subjects give inaccurate data
x subjects may lie - questions subjective reading!
Study Design (cont)
confounding vanable - Athind variable that
allects both the explanatory and lesponse variable amakes it seem like there is a connection x in observational studies, association doernt If you want to learn more check out Define resonance.
EX - Spanking de low IQ , contounding could be:
- parent 1Q/ environment, affluence, etc....
Key concepts in Experimental Design
control - compare treatment of interest to control group 2 Randomize-randomly assign subjects 3 Replicate - collect sufficiently large sample size 4 Block - account for variabler known/suspected to
affect response of interest
A comparing results between treatment a control group
allows us to determine it an intervention was elective We also discuss several other topics like What are the types of statements and how they differ?
Terminology tplacebo- Pake treatment, often used as control group tplacebo ellect - show change despite being on placebo -blinding experimental units do not know which
group they're in de it double-blind - both experimental units an experimenter
do not know the group assignments multifactor experiments - Categorical explanatory variables in an experiment may be refiered to as
factors - sometimes its of interest to test the effects of multiple factors