AP Statistics Unit 3

random

random

nobody can guess the outcome before it happens. when we want things to be fair, usually some underlying set of outcomes will be equally likely (although in many games, some combinations of outcomes are more likely than others).

stimulation

mimics reality by using random numbers to represent the outcomes of real events.

trial

the sequence of several components representing events that we are pretending will take place

response variable

trial's outcome

population

the entire group of individuals or instances about whom we hope to learn

sample

a representative subset of a population, examined in hope of learning about the population

bias

when sampling methods either over or under emphasize some characteristic of the population

randomizing

protects us from the influences of all the features of our population by making sure that, on average, the sample looks like the rest of the population.

sample size

the number of individuals in the sample that is important.

census

attempting to survey the entire population

population parameter

mathematical measures taken from the entire population like the population mean and standard deviation

representative

we want the statistics we compute from a sample to reflect the corresponding parameters accurately.

randomization

the random selection of subjects used to reduce bias in either surveys or experiments

sample statistics

mathematical measures taken from a sample of the population of interest like the sample mean and sample standard deviation

simple random sample

abbreviated SRS, this requires that every item in the population has an equal chance to be chosen and that every possible combination of items has an equal chance to exist. No grouping can be involved.

sampling frame

a list of individuals from which the sample is drawn

sampling variability

Samples drawn at random generally differ one from another. Each draw of random numbers selects different people for our sample. These differences lead to different values for the variables we measure

stratified random sample

population is divided into homogenous groups and then a random sample is drawn from each group

cluster sample

population is split into parts or clusters usually based on geography and then entire clusters are selected randomly and sampled

multistage sample

sampling schemes that combine several different sampling methods at different stages

systematic sample

a sample is drawn from the population by following a systematic plan to give every object in the population an equal chance to be chosen but all possible groups can not be formed

voluntary response sample

a large group of individuals is invited to respond, and those who choose to respond are counted

voluntary response bias

The sample is not representative, even though every individual in the population may have been offered the chance to respond, which invalidates the survey.

convenience sample

a poor way to collect a sample - do what is convenient for the surveyor, data is usually very biased

undercoverage

some portion of the intended population is either unrepresented or under-represented

nonresponse bias

bias created when people who are randomly selected refuse to particiapte in the sample

response bias

anything in the survey design that influences the responses from the sample

factor

an experimenter must identify at least one explanatory variable

levels

The specific values that the experimenter chooses for a factor

treatment

The combination of specific levels from all the factors that an experimental unit receives

matched design

when our data values are not independent of one another and are related somehow to one subject - it is a form of blocking

observational study

a study based on data where no manipulation of factors has been employed, we simply observe what has or will happen

experiment

a study where there is a definite random assignment of subjects to treatments

treatment

the process, intervention, etc that is applied to each subject in an experiment

principles of experimental design

control, randomize, replicate, block

control group

a group created the provide a basis for comparison usually either an old or placebo treatment

single blind

when the subjects in an experiment do not know if they are in the treatment or control group

double blind

when the subjects as well as those evaluating the result of an experiment do not know which subjects are in the treatment or control groups

placebo

a fake treatment often given to the control group to help prevent the placebo effect (subjects improving by the power of suggestion)

blocking

subjects or experimental units are grouped together homogeneously because of some charcteristic they have in common that is believed might effect the experiment

confounding

when the results of an experiment can be determined because a variable has not be accounted for and has interferred with your results

prospective study

a study where we collect data as it happens

retrospective study

a study where we collect data from events that have happened in the past