1: Introduction to Stats and Reseach Design Flashcards
anecdotal evidence
based on haphazardly selected individual cases. These cases need not be representative of any larger group of cases (e.g. your young friend Ashley prefers Powerade over Gatorade so that means most young people do)
available data
data that were produced in the past for some other purpose but may help answer a present question
observational study
we observe individuals and measure variables of interest but do NOT attempt to influence responses (includes sample surveys)
if researchers (or govt, foundations) intervene in the lives of study participants by providing a treatment, but no randomization is done, the experiment is still an observational study
experimental study
deliberately impose some treatment on individuals and observe their responses
statistical inference
answers specific questions with a known degree of confidence
experimental units
individuals on which the experiment is done (humans = subjects)
treatment
a specific experimental condition
factors
explanatory variables
level of a factor
in a study that studies the joint effects of several factors, each treatment is formed by combining a specific value (level) of factors
experimental design
refers to choice of treatments and the manner in which the experimental units/subjects are assigned to treatments
matched pairs
each subject receives both treatments in a random order OR subjects are matched in pairs as closely as possible and one subject in each pair gets treatment
Basic Principles of Experimental Design
- Compare two or more treatments to control effects of lurking variables. 2. randomize - use impersonal chance to assign experimental units to treatments 3. repeat each treatment on many units to reduce chance variation in results
2 reqs of table of random digits
the digit in any position in the list has the same chance of being any one; the digits in different positions are independent in the sense that the value has no influence on the value of any other
block
group of experimental units or subjects that are known before the experiment to be similar in some way that is expected to affect the response to the treatments
voluntary response sample
consists of people who choose themselves by responding to a general appeal. VRS are biased b/c people w/ strong opinions are mostly likely to respond
simple random sample
SRS of size n consists of n individuals from the population chosen so that every set of n individuals has an equal chance to be the sample actually selected
needs a sampling frame.
divide the popln into non-overlapping subsets/strata
do SRS w/i each stratum
combine subsamples into 1 complete sample
probability sample
sample chosen by chance. we must know what samples are possible and what prob each possible sample has
stratified random sample
first divide popln into groups of similar indivs (strata). choose a separate SRS in each stratum and combine these SRSs to form the full sample
multistage sampling design
selects successively smaller groups within the popln in stages, resulting in a sample consisting of clusters of indivs. each stage may employ an SRS, stratified sample, or another type of sample
undercoverage
occurs when some popln groups in popln are left out of the process of choosing the sample
nonresponse
occurs when an indiv chosen for the sample can’t be contacted or doesn’t cooperate
response variable
what we want to explain (usually Y)
explanatory variable
candidate explanation (X)
lurking variable vs. confounding
lurking variable - a variable that is not among the explanatory or response variables but may influence the response variable
confounding - occurs when 2 variable are associated in such a way that their effects on a response variable can’t be distinguished from e/o
popln vs sample
population = entire group of individuals about which we want info
sample - part of popln from which we actually collect info
we collect data from a representative sample to make inferences about a population
