Homework 2: Beginning to Learn Flashcards

Vocabulary flashcards derived from lecture notes on probability, distributions, and the properties of estimators.

Random sampling

The key idea that one draw from a population does not depend on another.

Infer

The process of learning about the underlying data-generating process from the data we observe.

Frequentist approach to probability

A definition of probability as the number of times an event occurs out of an infinite number of random trials.

Law of Large Numbers (Relative Frequency)

The idea of relative frequency converging to the true probability.

Lognormal distribution

A model often used for earnings data because earnings distributions tend to be skewed right.

Estimand

The thing we want to learn about.

Estimator

The thing we compute to learn about the estimand.

Estimate

The result given by an estimator for a given set of data.

Unbiased

A state where $E(\text{estimator})$ equals the thing we want to learn about.

Bias

A potential result of sample selection if the data does not represent the population we want to learn about.

Conditional expectation

The method used to compare earnings of women and men by estimating earnings given gender.

Expected value

A weighted average of all the random variable's possible outcomes.

Law of Large Numbers (Sample Size)

The principle that sample averages tend to the population mean as sample size grows.

Indicator variable expected value

For a variable taking values $1$ and $0$, this is equivalent to the probability that the random variable equals $1$.

LIE (Law of Iterated Expectations)

The law stating that the expected value of the CEF of $Y$ given $X$ is the expected value of $Y$.