Back to Blog

Value at Risk (VaR): Measuring Portfolio Risk

Value at Risk (VaR) is the most widely used risk metric in finance. It tells you the maximum amount you can expect to lose over a specific time period with a given confidence level. Banks, hedge funds, and professional traders rely on VaR to understand their risk exposure and make informed decisions.

What is Value at Risk?

VaR answers a simple question: "What is the worst loss I can expect under normal market conditions?" It provides a single number that summarizes your portfolio's risk exposure.

VaR Definition: A 95% daily VaR of $5,000 means there is only a 5% chance of losing more than $5,000 in a single day under normal market conditions.

VaR has three components:

Three Methods to Calculate VaR

There are three main approaches to calculating VaR, each with its own strengths and weaknesses.

1. Historical VaR

Uses actual historical returns to estimate potential losses. Simply sort your historical returns from worst to best and find the loss at your confidence percentile.

Calculation: For 95% VaR with 100 days of data, the VaR is the 5th worst daily return.

Pros: No assumptions about distribution, captures actual market behavior

Cons: Limited by available history, assumes future resembles past

2. Parametric (Variance-Covariance) VaR

Assumes returns follow a normal distribution and uses statistical parameters.

Formula: VaR = Portfolio Value x Z-score x Standard Deviation

Pros: Quick to calculate, works well for large portfolios

Cons: Assumes normal distribution, which underestimates tail risk

3. Monte Carlo VaR

Simulates thousands of possible future scenarios using random sampling.

Process: Generate thousands of simulated returns, then find the loss at your confidence percentile.

Pros: Can model complex positions and non-normal distributions

Cons: Computationally intensive, depends on model assumptions

Parametric VaR Calculation Example

Let us calculate VaR for a $100,000 portfolio using the parametric method.

Given:

Calculation:

This means there is a 95% probability that the portfolio will not lose more than $2,467.50 in a single day.

Converting VaR Across Time Periods

To convert daily VaR to other time periods, use the square root of time rule:

Time Scaling Formula: VaR(T days) = VaR(1 day) x sqrt(T)

Example: Converting our $2,467.50 daily VaR to other periods:

Historical VaR Example

Let us calculate historical VaR using 100 days of portfolio returns.

Process:

Example data (sorted worst returns):

For a $100,000 portfolio: Historical 95% VaR = $100,000 x 2.6% = $2,600

Understanding Confidence Levels

The confidence level determines how extreme the loss estimate is:

Confidence LevelZ-ScoreInterpretation
90%1.28Exceeded 1 in 10 days
95%1.645Exceeded 1 in 20 days
99%2.33Exceeded 2-3 times per year

VaR for Options Portfolios

Options add complexity because their risk changes as the underlying moves. For options, consider:

Example: You own 10 call options with delta of 0.50 on a $100 stock. Delta-equivalent exposure = 10 x 100 x 0.50 = $500 worth of stock. Apply VaR calculation to this adjusted exposure.

Limitations of VaR

VaR is useful but has important limitations:

Conditional VaR (CVaR)

Conditional VaR, also called Expected Shortfall, addresses a key VaR limitation by measuring the average loss when VaR is exceeded.

CVaR Definition: If 95% VaR is $2,500, CVaR answers: "When we do lose more than $2,500, how much do we lose on average?"

CVaR is always larger than VaR and provides a more complete picture of tail risk.

Practical VaR Application

Here is how to use VaR in your trading:

Monitor Your Portfolio Risk

Pro Trader Dashboard helps you track your positions and understand your risk exposure across your entire portfolio.

Try Free Demo

Summary

Value at Risk is an essential tool for understanding portfolio risk. Whether calculated historically, parametrically, or through Monte Carlo simulation, VaR gives you a concrete number representing your maximum expected loss at a given confidence level. While it has limitations, especially during extreme market events, VaR remains the industry standard for risk measurement. Combine it with CVaR and stress testing for a more complete picture of your risk exposure.

Learn more about Monte Carlo simulation or tail risk hedging.