77 terms

population

a set of individuals about which we want to know something

enumeration

what we do to count a population

census

a complete head count of the population; measures everyone in the population

survey

an analysis of a (representative) subset of the population to estimate values of the whole

proxy

something that allows you to estimate a value or count indirectly

sample

a (representative) subset of the population

sampling

the act of selecting a sample

statistic

the value of a variable of interest measured from a sample

parameter

the value of a variable of interest concerning the population (estimated by a statistic)

one-sample estimation

using a single sample of a population to estimate parameter values

two-sample estimation/capture-recapture

using a two-sample method to estimate the size of the population by determining the proportion of the population that was captured in the first sample and recaptured in the second using proportion

measurement problem

the issues associated with estimating the value of a population parameter

poll

typically a survey that 1) chooses a sample which is representative, 2) measures the individuals in the sample, 3) makes inferences about the population

sampling proportion

the ration n/N: the number of people with a particular answer divided by the number of people in the sample

sampling bias

using a sample that is not representative of the population in some relevant way

selection bias

a sample has a built-in tendency to over-include or under-include a particular group in the population

target population

the population about which the results of a poll applies

sampling frame

is the (usually a) list of the population from which a sample is drawn

convenience sample

a sample drawn not because its representative, but because it is convenient for the researcher(s)

response rate

the percentage of people selected for a sample that actually respond to the survey

non-response bias

a bias in a data set because some people selected for the study chose not to respond

quota sampling

a systematic effort to force the sample to be representative of relevant subjects of a population through the use of quotas (similar to probability sampling)

(simple) random sampling

everyone in the population has an equal chance of being selected

stratified sampling

divides the population into relevant groups, and then a random sample is selected from within each group.

strata

the groups (or layers) within a stratified sample

correlation

measures the relationship between the values of a pair of variables

causation

one event causes another

clinical study

an experimental study used to determine if a treatment causes a particular result

confounding variables

a variable that may also effect the result of a study

controlled study

an experimental study where one of the treatment groups uses a placebo to help control for confounding variables

randomized controlled study

an experimental design that uses controls and randomly assigns subjects to treatment groups

placebo effect

the benefits achieving through believing that one is being treated even if the "treatment" is inert

placebo

an inert substance that has no effect on a response variable

blind study

the subjects of a study do not know what treatment they are receiving by researchers do

double-blind study

the subjects of study do not know what treatment they are receiving and neither do any of the researchers interacting directly with the subjects

data set

a collection of values for one or more variables

data point (datum)

each value in a data set

discrete variable

a variable with numerical outcomes that can only take on integer values

continuous variable

a variable with numerical outcomes that can take on any value within a range (including fractions and decimals)

bar graph

pictogram

line graph

frequency table

a table used to organize data into the counts (frequencies) in each category or class

histogram

pie graph/pie chart

mean

average

percentiles

P% is below the given value

median

the middle value (50% above, 50% below)

first quartile

the value where 1/4 (25%) of the data is below that value, and 3/4 (75%) is above

third quartile

the value where 3/4 (75%) of the data is below that value and 1/4 (25%) is above

5-number summary

minimum, first quartile, median, third quartile, maximum

box plot

range

the difference between the minimum and maximum values

standard deviation

a measure of spread of a distribution (average deviation from the mean)

variance

the standard deviation squared

interquartile range

the difference between the third quartile and the first quartile

random experiment

an activity or process whose outcome cannot be predicted ahead of time

sample space

the set of all possible outcomes of a random experiment

event

a subset of a sample space

simple event

a single element in a sample space

compound event

a set of elements in a sample space

impossible event

an event that cannot occur, and even not in the sample space

certain event

an event that must occur

counting

the process of determining the number of elements in a set

permutation

a list of ordered events where repetition is not allowed//the count of such events

combination

a list of unordered events where repetition is not allowed//the count of such events

probability assignment

a function that assigns valid probabilities (between 0 and 1) to a set of events

equiprobable space

a probability assignment where all events are equally likely

complementary events

a pair of events that divide the sample space into two sets: those in event A, and all others not in A

independent events

the outcome of event A does not influence the probability of event B

odds for (an event)

the proportion of elements in event A divided by the proportion of elements not in event A

odds against (an event)

the proportion of elements not in event A divided by the proportion of elements in event A

weighted average//expected value

a mean calculated by considering the frequency of events at each value

fair game

a game where the expected value is 0 for all players

explanatory variable

the variable in an experiment that is being manipulated to (maybe) cause the result

response variable

the variable that is measured at the end of an experiment that is thought to be caused by the explanatory variable

block design

a study design where participants are broken up into groups (typically demographic groups like race, gender, or some other behavior), and then where each group is divided into treatment and placebo groups for the experiment. This is done to help control for possible confounding variables.