3.4 - 3.6 ~ margin of error and studies

how to find margin of error?

sd(2)

conclusion format

we expect the true proportion of - to be at most - from the estimate of (true proportion)

estimate of interval

true proportion + (moe) , true proportion - (moe)

undercoverage

occurs when some members of population are less likely to be chosen for the sample

nonresponse

when an individual chosen for the sample can’t be contacted or refuse to participate

response bias

consistent pattern of inaccurate responses to a survey question

confounding

when two variables are associated in a way that they cannot be distinguished from each other

control group

a group which provides a baseline to compare the effects of other treatments

placebo effect

some subects may act favorably to any treatment, even an inactive one

placebo

a treatment which has no active ingredient

double blind

neither subjects or the people that interact with them know which treatment the subjects got

single blind

either only the subjects or the people that interact with them don’t know which subjects got the treatment