STATISTICS - EXAM 2

Correlation

r that measures the direction + strength of the linear relationship between two quantitative variables (unitless)

Explanatory Variable

A variable that may explain/influence changes in a response variable

Linear Relationship

When the data on a graph forms a straight line

Negative Association

One variable increases while the other decreases leading to a “negative” direction

Positive Association

Both variables tends to increase with one another in a “positive” direction

Response Variable

A variable that measure the outcome of the study (y)

Scatterplot

A visual measurement between two variables

Strength of a Relationship

Determined by how close the points in a scatterplot lie to a simple form like a line (weak, moderate, strong)

Ecological Correlation

Correlation based on averages rather than individuals

Extrapolation

Using a regression line to make predictions far outside the range of x values that you used to obtain the line (often inaccurate predictions)

Influential

Something that removing would significantly change the result of the calculation

Intercept

Denoted by a in the straight line equation, it is the value of y when x = 0

Least-Squares Regression Line

The line that makes the sum of the squares of the vertical distances of the data points from the line as small as possible

Lurking Variable

An outside factor that may influences changes that are not under observation

Regression Line

A straight line that describes how a response variable y changes as en explanatory variable x changes

Residual

The difference between an observed value vs. predicted value (Y-Ŷ)

Residual Plot

A scatterplot of the regression residuals against the explanatory variable

Slope

Denoted by b in the straight light equation (y = a + bx) the amount by which y changes when x increase by one unit

Bias

Systematic errors in the way a sample represents a population

Nonresponse

Individuals chosen for a sample that can’t be contacted or refuse to respond

Population

The entire group of individuals we want information about

Sample

Part of the population that we actually collect information about (received responses). Used to draw conclusions about the entire population

Sample Survey

A survey conducted on a sample/portion of the population being studied. Based conlcusions about the population based on the data from the sample

Sampling Design

Describes exactly how to choose a sample from the population

Simple Random Sample

SRS, the sample size n consists of n individuals from the population consisted of individuals are each equally likely to be chosen by chance (gamble/dice roll)

Stratified Random Sample

Sample of separate SRSs chose for different strata of a population (groups of indidivudlas that are similar in some way that is important to the response)

Table of Random Digits

Long string of digits ranged from 0-9 (each entry is equally likely to be any of the 10 digits from the table)

Undercoverage

When some portion of the population is left out of the process of choosing a sample

Voluntary Response Sample

A sample composed of individuals who choose to respond due to strong opinions (biased)

Block

A group of individuals that are known before the experiment to be similar in some way that is expected to affect the response to the treatments

Block Design

Design of an experiment where the random assignment of individuals to treatments is carried out specifically within each block

Completely Randomized Design

All subjects are allocated at random among all the treatments

Confounded

When two variables (explanatory or lurking) effects cannot be distinguished from one another (in other words we don’t know what exactly are causing the responses)

Double Blind Experiment

When both the subjects and those who interacts with the subjects are unaware of which treatment is being received/given

Experiment

A study that imposes some sort of treatment on individuals to observe their responses/changes (purpose to study whether the treatment causes a change in the response also consists of a control typically)

Factors

Explanatory variables in an experiment

Matched-Pairs Design

One type of block design that combines matching with randomization. (pair up and then randomize the treatment per each subject in a pair) Each subject receives both treatments in a random order, or the subjects are matched in pairs as closely as possible, and one subject in each pair receives each treatment

Observational Study

A study that simply observes individuals without influencing any factors surrounding what is being studied

Randomized Comparative Experiment

An experiement that uses both comparison of two+ treatments and random assignment of subjects to treatments

Statistical Significance

When an observed effect is so large that it would rarely occur by chance

Subjects

Individuals being studied in an experiment particularly people

Treatment

Any specific experimental condition applied to the subjects. If an experiment has more than one factor, this is a combination of specific values of each factor