DataTerminology.comNEW
Also known as: Stochastic variable
A variable that maps outcomes of a random experiment to numerical values.
DESCRIPTION
A random variable associates each outcome in a sample space with a numeric value. Discrete random variables take countable values with a PMF; continuous ones have a PDF and CDF. Key properties include expectation, variance, and moments. They underpin probabilistic modeling, statistical inference, and machine learning likelihoods. Transformations and joint distributions enable modeling complex systems.
ALTERNATIVE DEFINITIONS
Wikipedia
A random variable is a variable whose possible values are numerical outcomes of a random phenomenon.
Concise, widely cited statistical definition.
NIST/SEMATECH e-Handbook of Statistical Methods
A random variable is a function that assigns a numerical value to each outcome in the sample space.
Emphasizes functional mapping from outcomes to numbers.
RELATED TERMS
Probability Distribution Discrete Random Variable Continuous Random Variable Expectation Variance Cumulative Distribution Function Probability Mass Function Portable Document Format Law of Large Numbers Dummy Variables
COMPETING TERMS
Deterministic Variable
RELATIONS
KNOWLEDGE AREAS
TARGET AUDIENCE
Data Scientist AI Engineer Data Analyst
EXTERNAL SOURCES
- Wikipedia - Random variable
- NIST - Handbook entry on random variables
- Khan Academy - Lessons on random variables
TOP QUESTIONS
What is the difference between discrete and continuous Random Variables?
Discrete variables take countable values with a PMF; continuous take uncountably many values described by a PDF and CDF.
Category: Misunderstanding
Why are Random Variables fundamental in ML?
They define probabilistic models, likelihoods, and loss functions, enabling inference and uncertainty quantification.
Category: Relevancy
How do I compute expectation of a Random Variable?
Sum or integrate x times its probability function: E[X] = Σ x p(x) or ∫ x f(x) dx.
Category: Requirements
What are common mistakes with Random Variables?
Confusing distribution of X with distribution of a function g(X), and misapplying independence assumptions.
Category: Mistakes
Can Random Variables be dependent?
Yes, dependence is common. Joint distributions capture relationships via covariance or copulas.
Category: Example
How to simulate a Random Variable?
Use inverse transform sampling, rejection sampling, or library RNGs parameterized by the desired distribution.
Category: Requirements
What is an indicator Random Variable?
It takes value 1 if an event occurs, 0 otherwise, simplifying probability calculations.
Category: Example
How do moments relate to Random Variables?
Moments (mean, variance, skewness, kurtosis) summarize distribution shape and dispersion.
Category: Example
What is the risk of assuming normality for a Random Variable?
Mis-specified models produce biased estimates and invalid intervals; assess distributional fit first.
Category: Risks