AP Stats - Chapter 4 Test

• The 1347 teachers who mail back the questionaire

• the 2500 teachers to whom you mailed the questionaire

• all members of the National Education Association

• all American school teachers

• all American school students

• The results of the survey are unreliable because response to the survey was voluntary

• The population is large enough to eliminate potential sources of bias in the design of the poll

• This is an example of a census because all students had an opportunity to vote.

• This is an example of cluster sampling, which is an effective way of voting

• The population is all students who voted in the election

• 117

• Bechhofer, Bechhofer again, and Taylor

• Bechhofer, Taylor, and Weiss

• Kesten, Kiefer, and Taylor

• Taylor, Weiss, and Ito

• mutlistage sample

• stratified sample

• cluster sample

• SRS

• convenience sample

• the placebo effect

• bias

• confounding

• an observational study

• stratification

• observational studies may have confounding variables, but experiments never do

• in an experiment, people must give their informed consent before being allowed to participate

• observational studies are always biased

• observational studies cannot have response variables

• an experiment imposes treatments on the subject, but an observational study does not

• eliminate grounds for malpractice suits

• ensure that subjects were randomly assigned to treatments

• eliminate a possible source of bias

• make sure nobody is harm

• prevent stratification of the experiment

• eliminate bias

• isolating the effect of the treatment variable by keeping all other variables the same in the treatment groups

• creating treatment groups that are as similar as possible

• reducing the impact of random variation arising from random assignment to groups

• ensuring that an experiment is conducted in a double blind fashion

• prevent the placebo effect

• allow double blinding

• eliminate the need for random assignment

• compensate for impact of other, unidentified variables on the response variable

• compensate for anticipated differences in the response variable for different values of a specified "blocking" variable

• systematic random sample

• convenience sample

• matched pair design

• randomized block design

• completely random design