36 terms

APstats Chapter Five - Producing Data

STUDY
PLAY
voluntary response sample
sampling design where individuals can choose on their own whether to participate in the sample; DANGER - will usually produce biased result
undercoverage
occurs when some groups in the population are left out of the process of choosing the sample; DANGER - will usually produce biased result
nonresponse
occurs when an individual chosen for the sample can't be contacted or refuses to participate; DANGER - will usually produce biased result
response bias
a systematic pattern of incorrect responses
sampling frame
a list of individuals from whom the sample is drawn; preferably, the entire population
sample
items selected from a population, and examined in order to gather information/data
population
the ENTIRe group of individuals we want information about
matched pairs design
common form of blocking for comparing just two treatments by matching pairs of similar experimental units
block design
the random assignment of units to treatments carried out separately within groups of experimental units that are expected BEFORE the experiment to systematically affect the response to the treatments (contrasted with completely randomized design)
double-blind experiment
neither the subject nor those who measure the response variable know which treatment an experimental unit received
hidden bias
unobserved variables that may cause bias in the measurement of the response variable
replication
using enough experimental units to reduce chance variation
statistically significant
an observed effect so large that it woud rarely occur by chance; this does not mean that the effect is large enough to be important
completely randomized experiment
when all experimental units are allocated at random among all treatments (as contrasted with a block design)
randomization (in an experiment)
relying on chance to make assignments to treatment groups; the assigment does NOT depend on any characteristic of the experimental unit and does NOT rely on the judgment of the experimenter in any way
control group
the group that receives no treatment (or a sham treatment)
systematic random sample
a type of probability sampling method in which sample members from a larger population are selected according to a random starting point and a fixed periodic interval
observational study
we observe individuals and measure variables of interest but do not attempt to influence the responses
experimental units
the individuals on which the experiment is done
subjects
when the experimental units are humans (or anthropomorphized)
factor
the explanatory variable (there may be several) in an experiment
level
the specific treatment value (there may be several) of an experiment's factor
placebo effect
a favorable response to a dummy treatment — an experimental result caused by expectation alone
strata
groups of individuals that are similar in some way that is important to the response
stratified random sample
after dividing the population into STRATA, a separate simple random sample (SRS) occurs in each stratum and them combined into the full sample
probability sample
a sample chosen by chance; after knowing what samples are possible and what chance (probability) each possible sample has
table of random digits
a long string of digits 0-9 with two properties: (1) each entry is equally likely to be any of the ten digits, and (2) the entries are independent of each other (the knowledge of one part of the table gives no information about any other part)
simple random sample
individuals chosen from a population in such a way that every SET of that size has an equal chance to be the sample actually selected
SRS
simple random sample
biased
any method or practice that systematically favors certain outcomes
convenience sampling
choosing individuals who are easiest to reach
randomization (in a survey)
relying on chance to select a sample from the population; the selection does NOT depend on any characteristic of the individuals and does NOT rely on the judgment of the selector in any way
control
the overall effort to minimize variability in the way that experimental units are obtained and treated
sampling
involves studying a part in order to gain information about the whole
census
an attempt to contact every individual in a population in order to gain information
cluster sampling
after dividing the population into groups or clusters, some of these are randomly selected; then ALL individuals in the chosen clusters are selected to be in the sample