SI Session 3.1.21

R Studio

100

This command is what we use to add a fitted line to a scatterplot

abline

200

This is the command we use to write a simple regression model

lm

300

This is the place we tell R to look for our files

Working Directory

400

This statistic describes how our data is spread, and is NOT included in the "summary" command

Standard Deviation

500

This is our primary measurement for goodness of fit

R-Squared

Bivariate OLS

100

This character denotes an estimated term in our regression

^

200

The parameter that defines the relationship between X and Y

B1^

300

The "observed error" is another word for this

Residual

400

R-Squared and Standard Error both measure this quality

Goodness of fit

500

We use a value from this variable to input into our regression equation. Which variable does the resulting number represent?

Independent Variable, Dependent Variable

Data and Distributions

100

This is a graph or formula that describes the relative probability that a random variable is near a specified value

Probability Density

200

This bell-shaped curve indicates the probability of observing realizations of the random variable in any given range

Normal Distribution

300

This concept states that mean of a sufficiently large number of independent draws from any distribution will be normally distributed 

Central Limit Theorem

400

This type of variable takes on values in a range and with the probabilities defined by a distribution 

Random Variable

500

This is a variable that takes on any possible value over some range

Continuous Variable

Estimation

100

This coefficient is our closest estimation of B1. 

B1^

200

This regression term is included in the core model, but not in an estimated model.

Error Term

300

If B1^ is unbiased, it means that this condition holds

X is uncorrelated with the error

400

The distribution of an unbiased estimator is centered around this value

The true value

500

This statistic refers to the accuracy of a parameter estimate, which is determined by the width of the distribution of the parameter estimate

standard error

Miscellaneous

100

These are the two types of randomness we experience in our estimation process

Sampling Randomness, Modeled Randomness

200

If our sample size is large enough, B1^ and B0^ will be: 

Normally Distributed

300

This part of the regression captures everything else other than X that affects Y.

Error Term

400

A random variable is this if the variance differs for some observations.

Heterscedastic

500

A variable is this if all observations have the same variance. 

Homoscedastic