Ch.4 Stats Vocab

population

the entire group of individuals we want information about

census

collects data from every individual in the population

sample

subset of individuals in the populations that data is actually collected from

population parameter

characteristic of the population

observational studies surveys

collecting data without interfering

ex: observation, survey, interviews, reviewing records

experiments

when we impose a treatment to people animals, or objects to observe the response

representative

similar to the population that is being attempted to observe in terms of a specific characteristic

• allows us to make generalizations about the population

sample survey

study that collects data from a sample that is chosen to represent a specific population

bias

systematic error in a study’s design, data collection, or analysis that leads to unrepresentative results; results are often skewed in one direction

convenience sample

choosing individuals from the population who are easy to reach

voluntary response sampling

allows people to choose to be in the sample by responding to a general invitation

simple random sample (SRS)

a sample of a certain size “n” is chosen so that every individual in the group of “n” has an equal chance to be selected as the sample

• minimize bias

• allow for valid statistical inference

• better for when the population is estimated to have similar values

random sampling

using a chance process to determine which members of a population are included in the sample

variable

an attribute that can take different values for different individuals

categorical variable

assigns labels that place each individual into a particular group

quantitative variable

takes number values that are measurements

discrete variable

a quantitative value with a fixed set of possible values with gaps in between them

continous variable

a quantitative variable that can take any value in an interval on the number line

distribution

describes the values the variable takes and how often it takes those values

descriptive statistics

process of exploratory data analysis

inferential statistics

the process of drawing conclusions that go beyond the data at hand

statistics

describe a sample’s characteristic

strata

groups of individuals in a population who share characteristics

• groups = associated with different variables of the study

stratified random sampling

selects a sample by choosing an SRS from each stratum and combining the SRSs into one sample

• works best when individuals in each group are similar & there are differences between groups

• provides more precise estimates

cluster

group of individuals in the population in similar proximity/location

cluster sampling

selects a sample by randomly choosing clusters and including each member of the selected clusters in the sample

• works best when indivuals of each cluster are very different

• practical reasons: saves money + time

systematic random sampling

ordered arrangement of the population by randomly selecting one of the first “k” individuals and choosing every “kth” individual afterward

• useful for certain contexts where unknown amount of individuals will be surveyed

multi-stage

several methods of grouping to select successively smaller groups

sampling error

difference between the mean values of the sample and the mean values of the entire population

• aka Variation in Sampling

Non-sampling error

problems like choosing the wrong people, letting bias enter, or failing to expect participants will self-select correctly

undercoverage

some of the population has a lower chance of responding or is complelely excluded for some reason

nonresponse bias

some of the individuals selected for the sample never give a response

response bias

when responders don't answer truthfully, possibly due to multiple concerns

• question wording bias

• asking sensitive questions

• trying to please the interviewer

• confusing question wording

• being asked to self report

can be fixed by testing survey questions first

sample frame error

the wrong subpopulation is used to select a sample, an unrepresentative population is selected

response variable

measures an outcome of a study

explanatory variable

helps explain or predict changes in a response variable

retrospective

observational study that examines existing data for a sample of individuals

prospective

observational studies that track individuals into the future

confounding/lurking variables

effects are on a response variable are not distinguished from one another

• impacts both explanatory and response variables

high-end outlier

x > Q3 + 1.5*IQR

low-end outlier

x < Q1 - 1.5*IQR

placebo

a treatment with no active ingredient, but otherwise like other treatments

factors

when there is more that one explanatory variable

levels

variation in each factor

control group

a group used to provide a baseline for comparing effects of other treatments

placebo effect

the fact that some subjects in an experiment will respond favorably to any treatment, even inactive treatments

single-blind experiment

either the subjects don’t know which treatment they are receiving or the people who interact with them and the measure the response variable don’t know which subjects are receiving which treatment

double-blind experiment

neither subjects nor those who interact with them and measure the response variable know which treatment a subject received

well-designed experiment

includes: comparison, randomization, control, replication

random assignment

experimental units are assigned to treatments using a chance process

control

keeping other variables constant for all experimental units

replication

using enough experimental units to distinguish a difference in the effects of the treatment from chance variation due to the random assignment

completely randomized design

the experimental units are assigned to the treatments completely by chance

randomized block design

random assignment of experimental units to treatment is carried out separately within each block

• like stratifying but for experiments

block

group of experimental units that are known before the experiment to be similar in some way that is expected to affect the response to the treatment

matched pairs design

special form of blocking; compares two treatments w/ a block size of two

• similar experimental units are paired and treatments are assigned randomly OR given both treatments in random order

statistically significant

a result not attributed to chance

• three parts: replication, randomization, control

extraneous variable

a variable that is not one of the explanatory variables in the study

• typically does impact the response variable