Statistics 140 Exam #2

Front 1

random

Back 1

an outcome is random if we know the possible values it can have, but not which particular value it will be, all values are equally possible outcomes

Front 2

simulation

Back 2

models a real world situation by using random-digit outcomes to mimic the uncertainty of a response variable of interest

Front 3

response variable

Back 3

values of the response variable record the results of each trial with respect to what we were interested in

Front 4

sample survey

Back 4

a study that asks questions of a sample drawn from some population in the hope of learning something about the entire population, ex. election polling

Front 5

bias

Back 5

any failure in representing the whole population is bias, common errors include: voluntary, nonresponse, response bias, undercoverage

Front 6

randomization

Back 6

best defense against bias, each individual is given a fair, random change of selection

Front 7

census

Back 7

a sample that consists of the entire population

Front 8

simple random sample (SRS)

Back 8

made of randomly selected individuals. Each individual in the population has the same probability of being in the sample. All possible samples of size n have the same chance of being drawn.

Front 9

stratified random sample

Back 9

a sampling design in which the population is divided into several subpopulations, or strata, and random samples are drawn from each stratum

Front 10

voluntary response bias

Back 10

when individuals choose to participate, it is immediate bias

Front 11

nonresponse bias

Back 11

when a large fraction of those sampled fails to respond, those who do respond are likely to not represent the entire population

Front 12

undercoverage

Back 12

parts of population are not represented

Front 13

response bias

Back 13

Fancy term for lying when you think you should not tell the truth, or forgetting. This is particularly important when the questions are very personal (e.g., “How much do you drink?”) or related to the past.

Front 14

question wording

Back 14

to prevent bias, wording in survey questions must be neutral and clear

Front 15

observational study

Back 15

a study based on data in which no manipulation of factors has occurred

Front 16

experimental study

Back 16

a study wherein factors are manipulated to create treatments, subjects are randomly assigned to treatments and the responses are compared across treatment levels

Front 17

retrospective study

Back 17

looking back at outcomes

Front 18

prospective study

Back 18

subjects are followed to observe future outcomes

Front 19

factor

Back 19

a variable whose levels are controlled by the experimenters, experiments aim to discover the effects that the differences in factor levels may have on the responses of experimental units

Front 20

experimental units

Back 20

individuals on whom an experiment is performed, called subjects or participants when human

Front 21

levels/treatment of a factor

Back 21

the different levels of a single factor that is controlled

Front 22

control group

Back 22

assigned to a baseline treatment level, a default treatment which is well known, or a null, placebo treatment, their responses provide a base for comparison

Front 23

single and double blinding

Back 23

two groups of individuals in an experiment: those who could influence the results (subjects, technicians) and those who could influence the results (judges, physicians, etc.) if one group is blinded (single), if both (double)

Front 24

placebo

Back 24

a treatment with no known effect, given so all subjects experience the same conditions, can cause placebo effect

Front 25

blocking/stratified

Back 25

when groups of experimental units are similar, it can be a good idea to group them, this can clarify the responses better

Front 26

confounding

Back 26

when the levels of one factor are associated with the levels of another factor in a way that their effects cannot be separated, the two factors are confounding

Front 27

independent

Back 27

events are independent if knowing that one event occurs does not change the probability that the other occurs

Front 28

probability

Back 28

the likelihood of an event occurring, a number between 0 and 1, to calculate: for A and B to occur, p(A) x p(B), for either A or B to occur, p(A) + p(B)

Front 29

tree diagram

Back 29

shows sequences of events in branches

Front 30

sampling distribution of a statistic

Back 30

tend to be normal distribution about the normal model, follow the 68-95-97.7 rule

Front 31

central limit theorem

Back 31

most samples are located around 50% mark, and hover around the true value

Front 32

sampling error/variability

Back 32

the amount of variability expected to occur from one sample to another

Front 33

confidence interval

Back 33

the extent of the interval on either side of the statistic value is the margin of error, the confidence interval is the estimate +/- margin of error

Front 34

95% confidence

Back 34

95% of samples of equal size will produce confidence intervals that capture the true proportion

Front 35

p

Back 35

true proportion

Front 36

p̂

Back 36

sample-based estimate of the proportion

Front 37

q

Back 37

1-p

Front 38

q^

Back 38

1-p̂

Front 39

parameter vs. statistic

Back 39

a Parameter is a number describing a characteristic of a Population whereas a Statistic is a characteristic of a Sample