Upgrade to remove ads
Only $35.99/year

Stat Test Unit 4

Terms in this set (34)

Population
the entire group of individuals about which we want information about in a statistical study
Sample
a subset of the population from which we actually collect data
Census
collects data from every individual in the population
Bias
when the results systemically do not represent the population as a whole
Convenience Sample Bias
when the sample is gathered from a convenient group that all have one thing in common; not random (ex: all the people at the galleria)
Voluntary Response Bias
occurs when individuals are able to choose whether they participate; bias will be in favor of the opinion of those who volunteer (ex: strong opinions usually against the idea that wish to share)
Nonresponse Bias
occurs when there is a lack of participation in a self-selected sample from certain segments of a population, when a person refuses to participate in a survey, or when a respondent omits questions when answering a survey
Undercoverage Bias
occurs when certain members of the population cannot possibly be chosen in a sample (ex: survey calling people's home phones, leaving out young people, homeless people, etc)
Response Bias
occurs when there is a systematic pattern of inaccurate answers to a survey question (ex: lying, skewing results, being asked how much money you make)
How wording of a question can affect bias?
can cause people to respond to a survey inaccurately (ex: do you AGREE that...)
How to represent the population as a whole with a sample?
No possibility of favoritism by the sample or self-selection of respondents; random sample
When describing randomization be sure to include:
- how to assign values to individuals (rolling a dice, flip a coin)
- selection process (what to do with repeats)
- when to stop
Simple Random Sample
A sample of size n selected from the population in such a way that each possible sample of size n has an equal chance of being selected.
Cluster Sample
chosen by classifying the population into groups of individuals that are located near each other; then assign each cluster a number and choose a like 2 random clusters; all individuals in the chosen cluster are included in the sample
Advantages vs Disadvantages of Cluster Sample
convenient but has the possibility of misrepresenting the population by leaving out individuals that could affect the results of the experiment
Stratafied Random Sample
chosen by classifying the population into groups of similar individuals, called stratum then choosing a simple random sample of individuals from each stratum
What makes a good experiment?
...
Observational Study vs Experiment
observational study observes individuals and measures variables of interest but does not attempt to influence the responses; experiment deliberately imposes some treatment on individuals to measure their responses
4 Characteristics of a Good Experiment
Comparison (treatment vs no treatment), Random Assignment, Control, Replication (doing each treatment to more than one subject)
Ways to Make a Good Experiment Even Better
use a control group, use a placebo, make experiment blind, make experiment double blind
Placebo Effect
experimental results caused by expectations alone; any effect on behavior caused by the administration of an inert substance or condition, which the recipient assumes is an active agent
Explanatory Variable
A variable that helps explain or influences changes in a response variable.
Response Variable
A variable that measures an outcome of a study.
Factors
different categories of the explanatory variable
Factor Levels
specifics about these factors (ex: factors are who get money and how much; factor levels are you get money or someone else gets money, $5 or $20)
Experimental Units
who or what the experiment is performed on; subjects
Treatments
procedures applied to each experimental unit
Confounding Variable
a factor other than the independent variable that might produce an effect in an experiment; 3rd variable with underlying effects (lurking if you cant identify it)
Completely Randomized Design
the treatments are assigned to all the experimental units completely by chance
Randomized Block Design
if you recognize that some of the experimental units are similar in way that may affect their response to the treatments; group the experimental units into blocks based on this similar characteristics; randomly assign experimental units to treatments within each block; compare results for each block separately
Match Pairs Design
a type of randomized block design used when there are many confounding variables, comparing experiment results to itself or into pairs of similar units; only one pair is randomly assigned the treatment
When can you conclude causation?
if individuals are randomly selected and treatments are randomly assigned groups; ensuring only differences are due to chance
Challenges of Establishing Causation (ethical dilemma ex: does smoking cause cancer)
-association is strong
-association is consistent
-larger values of explanatory variable are associated with stronger responses
-alleged cause precedes the effect in time
-alleged cause is plausible
Statistical Significance
when the percentage of chance is very small and the results are extremely convincing
Other sets by this creator