Question
click below
click below
Question
Normal Size Small Size show me how
ap statistics vocab
all vocab for the quiz
Question | Answer |
---|---|
population | the entire group of individuals that we want information about |
sample | a part of a population that we actually examine in order to gather information about the entire population |
statistical inference | coming to a conclusion about an entire population based on sample |
terms associated with sampling | involves studying a part to gain information about the whole (often very accurate) |
sample design | the method used to choose the sample from the population (poor sample design can produce misleading conclusions) |
voluntary response sampling | (often biased) people choose to be in a sample. This technique usually involves outgoing people with strong opinion, usually negative ones |
convenience sampling | (often biased) chooses individuals that are easiest to reach |
cluster sampling | when a population falls into naturally occuring subgroups, each having similar characteristics. 1) divide the population into groups/clusters 2)select ALL members of one or more clusters |
systematic sampling | a sample in which each member of a population is assigned a number. Members of a population are ordered in same way. Sample members are selected at regular intervals from a starting number |
confounding | variables are confounded when their effects on a response variable cannot be distinguished from each other |
bias | the design of a study is biased if it systematically favors certain outcomes (does not have to be intentional for it to occur, however a good experimental designer must avoid it at all costs) |
simple random sampling | choosing "n" individuals from a population in such a way that every set of "n" individuals has an equal chance of being in sample actually selected |
census | a survery that attempts to contact every individual in an entire population |
survey | a series of questions that attempts to gather information about a population or sample |
table of random digits | a long string of the digits 0,1,2,3,4,5,6,7,8,9 where each entry is equally likely to be any of these ten digits and entires are independent of each other |
probability sample | a sample chosen by chance. We must know what samples are possible and what chance or probability each possible sample has |
stratified random sample | 1)divide population into groups of similar individuals(strata) 2)then choose separate SRS in each stratum 3)combine the SRS from all strata to form the overall sample |
multistage sample design | choose the sample in stages. 1)break population up into groups 2)randomly select a certain number of groups 3)from those groups selected, then randomly pick sample from each |
undercoverage | occurs when some groups in the population are left out of the process of choosing a sample |
nonresponse | occurs when an individual chosen for the sample can't be contacted or does not cooperate |
response bias | respondents lying, usually about illegal or unpopular behavior |
wording of questions | confusing or leading questions can introduce bias |
sampling size | usually large samples are more accurate than smaller samples (relatively speaking) |
sampling frame | a list of all individuals from a population from which a sample is chosen. This should be ENTIRE population, but in practice, this is difficult |
observational study | observes individuals and measures variables, but does not attempt to influence the responses (usually poor way to find EFFECT of one variable on another) |
experiment | imposes a treatment on individuals to observe their responses. 1)randomization 2)control group 3)impose a treatment 4)replication |
experimental units | the individuals on which an experiment is done. They are "subjects". A specific experimental condition applied to the units is called a treatment. |
treatment | the specific experiment condition applied to the unit |
factor | the explanatory variable in an experiment. At times there can be many factors |
level | the specific value of the each factor |
placebo effect | a placebo is a dummy treatment. Most subjects respond favorably to ANY treatment, even a "fake" one. The response to the dummy treatment is known as the placebo effect. |
control group | the group of subjects that receive the fake treatment (placebo). The control group helps to alleviate confounding effects of the placebo effect |
matching | trying to ensure that the experimental group and control group are matched (have the same type of subjects) |
completely randomized design | when all experimental units are allocated at random among all treatments. This helps average out the effects of chance in sample that are large enough |
statistical significance | an observed effect too large to attribute to just chance (did change occur because of the actual treatment imposed or was it just chance?) |
replication | repeating each treatment on a large enough number of experimental units or subjects |
principals of experimental design | 1)control: the effects of confounding variables on the response variable 2)randomize: use impersonal chance to assign experimental units to treatments 3)replication: each treatmenton many units to reduce chance variation in results |
hidden bias | taking care that all experimental units or subjects are treated in exactly the same way. If not hidden bias could occur |
blind experiment | the subjects do not know what treatment they receive |
double blind experiment | not only does the patient not know what treatment they are receiving, but the person administering the treatment and/or the person recording the results does not know which treatment is being administered |
block design | a block is a group of subjects that are simliar in ways that are expected to affect the response to treatments |
matched pairs design | design that compares two treatments. -each block consists of two units or subjects closely mathced -subject: are assigned randomly to treatments and results are compared |