CAEECentre for Automotive Embedded Engineering · HSR Layout, Bengaluru
Module 15 of 20 · Intermediate

Random Variables and Probability Distributions

A random variable assigns a number to each random outcome. Its distribution describes possible values, likelihood, centre and spread.

Intermediate65 min study timePrerequisite: Probability fundamentals
Module learning progress0 of 3 stages

1 · Why this mathematics matters

Describe uncertain measurements, noise amplitudes and component distributions.

2 · Prerequisites and learning approach

Prerequisites: Probability fundamentals. Begin with the physical meaning, identify every symbol and unit, study the fixed-scale graph, then solve and verify the examples.

3 · Symbols and units

Xrandom variable
fX(x)probability density
μmean
σstandard deviation

4 · Concepts and textbook formulas

1. PMF, PDF and CDF

Discrete variables use a probability mass function; continuous variables use a density. The CDF gives probability below a threshold.

PMF, PDF and CDF equation

How to read it: identify the output quantity first, then the variables, parameters, units and assumptions. Test zero, unity and limiting values before using the equation in a design.

2. Expectation and variance

Expectation is the long-run mean. Variance measures squared spread about the mean.

Expectation and variance equation

How to read it: identify the output quantity first, then the variables, parameters, units and assumptions. Test zero, unity and limiting values before using the equation in a design.

3. Gaussian distribution

Many accumulated disturbances and manufacturing variations are approximately Gaussian.

Gaussian distribution equation

How to read it: identify the output quantity first, then the variables, parameters, units and assumptions. Test zero, unity and limiting values before using the equation in a design.

4. Common distributions

Bernoulli models one success/failure trial, binomial counts successes and exponential models memoryless waiting time.

Common distributions equation

How to read it: identify the output quantity first, then the variables, parameters, units and assumptions. Test zero, unity and limiting values before using the equation in a design.

5 · Step-by-step worked examples

Example 1: Foundation

For a normal variable with mean 10 and sigma 2, approximately 68 percent lies between 8 and 12.

Verification: check the unit, sign, order of magnitude and physical trend.

Example 2: Uniform quantisation

Given: An ideal quantisation error is uniform from -Delta/2 to Delta/2.

Uniform quantisation solution equation

Engineering meaning: The variance predicts the RMS quantisation-noise level.

Example 3: Gaussian yield

Given: A parameter has mean mu and standard deviation sigma.

Gaussian yield solution equation

Engineering meaning: The three-sigma interval is a useful first estimate of manufacturing spread.

6 · EE/ECE applications

  • thermal noise amplitude — use the governing equation to predict parameter sensitivity, confirm a simulation and interpret measured behaviour.
  • Monte Carlo variation — use the governing equation to predict parameter sensitivity, confirm a simulation and interpret measured behaviour.
  • ADC quantisation error — use the governing equation to predict parameter sensitivity, confirm a simulation and interpret measured behaviour.
  • reliability lifetime — use the governing equation to predict parameter sensitivity, confirm a simulation and interpret measured behaviour.

7 · Common mistakes

  • Treating a probability density value as a probability.
  • Ignoring distribution tails in tolerance analysis.

8 · Practice problems

  1. Standardise a Gaussian measurement using a z-score.
  2. Estimate the fraction of components inside a tolerance band.
Verification habit: predict the direction of change before calculating, then check units, sign, limiting cases and engineering reasonableness.