Upgrade to remove ads
Only $2.99/month

Unit 3 Vocab (Chapters 10 - 12)

Terms in this set (51)

OBSERVATIONAL STUDY
A study based on data that has not had any factors manipulated
RETROSPECTIVE STUDY
An observational study when subjects are selected and then their history is looked at
PROSPECTIVE STUDY
An observational study when subjects are selected and then they are followed and observed
EXPERIMENT
It manipulates factor levels to create treatments and compare results of different treatment groups
RANDOM ASSIGNMENT
Placement into a treatment group must be random for experiment to be valid
FACTOR
A variable that's levels are manipulated by the experimenter. Experimenters try to see what the difference is (if there is one) between the levels.
EXPERIMENTAL UNITS
Individuals on whom the experiment is preformed (subjects or participants)
LEVEL
The specific values that the experimenter chooses for a factor
TREATMENT
The process, intervention, or other controlled circumstance applied during an experiment
4 PRINCIPALS OF EXPERIMENTAL DESIGN
Control, Randomize, Replicate, Block
CONTROL
Control aspects of the experiment that we know may have an effect on the response, but they are not the factors being study
RANDOMIZE
Subjects are placed into treatment groups to help even out effects that can't be controlled
REPLICATE
Experiments conducted once are not enough, you have to conduct it the entire experiment again.
BLOCK
Used to reduce the effects of identifiable difference of the subjects (separate the subjects into those groups first)
COMPLETELY RANDOM DESIGN
all experimental units have an equal chance of receiving any treatment
STATISTICALLY SIGNIFICANT
When an observed difference is too large for us to believe it is likely to have occurred naturally.
CONTROL GROUP
The experimental units assigned to a baseline treatment level, typically either the default treatment (usually the placebo)
BLINDING
Any individual associated with an experiment who is not aware of how subjects have been allocated to treatment groups
SINGLE-BLINDED
When one group (those that could influence the results or those that evaluate the groups) is blinded
DOUBLE-BLINDED
When both groups (those that could influence the results or those that evaluate the groups) are blinded
PLACEBO
A treatment known to have no effect, administered to one group so that all groups experience the same conditions (sugar pill)
PLACEBO EFFECT
Tendency of many human subjects to show a response, even though they have taken a placebo
BLOCKING
When groups of experiment are similar, put them together into groups before assigning treatment
RANDOMIZED BLOCK DESIGN
Subjects are randomly assigned to treatments within their blocks
CONFOUNDING
When the levels of one factor are associated with the levels of another factor in a way that can not be seperated
POPULATION
The entire group of individuals or instances about whom we hope to learn about.
SAMPLE
A representative subset of a population.
SAMPLE SURVEY
A study that asks questions of a sample drawn form a population.
MATCHING
An attempt to try and force a sample to resemble attributes of its population.
SAMPLE SIZE
The number of individuals in a sample. The number matters, not the fraction of the population.
CENSUS
A sample that consists of the entire population.
POPULATION PARAMATER
A numerically valued attribute of a model for a population. (what we want to learn about the population)
STATISTIC
Values calculated for sampled data that can estimate a population parameter. (what we learn from the sample)
REPRESENTATIVE
When the statistics computed accurately reflect the corresponding population parameters.
SIMPLE RANDOM SAMPLE
Each person/place/thing has an equal chance of being selected.
SAMPLING FRAME
A list of individuals from whom the sample is drawn.
SAMPLING VARIABILITY
The natural tendency of randomly drawn samples to differ. A natural result of random sampling.
STRATIFIED RANDOM SAMPLE
When a population is divided into several homogeneous subpopulations.
CLUSTER SAMPLE
A sampling design when population is divided into clusters, then cluster(s) are chosen at random and a census is taken from the cluster(s)
MULTISTAGE SAMPLE
A sampling method that chooses more than 1 method.
SYSTEMATIC SAMPLE
A sample drawn by selecting individuals a specific way from a sampling frame. (Every 10th person)
CONVENIENCE SAMPLE
A sample of easily available.
VOLUNTARY RESPONSE BIAS
Bias introduced to a sample when individuals choose on their own whether to participate in the sample.
UNDERCOVERAGE
When sampling a population and a part of the population is not represented like it is in the actual population.
NONRESPONSE BIAS
Bias that occurs when a large portion of those sampled fail to respond.
RESPONSE BIAS
Anything in a survey design that influences responses (wording of questions).
RANDOM
When you know what the outcomes could be, but not which particular values will happen.
SIMULATION
Models random events by assigning random numbers to specific outcomes
SIMULATION COMPONENT
The most basic situation in which something happens at random.
OUTCOME
The individual result of a component.
TRIAL
The sequence of several components representing events that we are pretending will take place.
THIS SET IS OFTEN IN FOLDERS WITH...