Enter Values

$
Total portfolio market value
%
Daily standard deviation of returns
Higher confidence = larger VaR estimate
trading days
1 day (trading), 10 days (Basel), 252 days (1 year)
%
Mean daily return (0.04% daily ≈ 10% annual)
VaR Formula
VaR = V × zα × σ × √T
V = Portfolio value | zα = z-score | σ = Daily vol | T = Days
Ryan O'Connell, CFA
Calculator by Ryan O'Connell, CFA

Risk Metrics

Value at Risk (VaR) $24,675.00 Moderate Risk
Expected Shortfall (CVaR) $30,939.00 Moderate Risk
VaR % 2.47%
ES % 3.09%
z-Score 1.645
Annual Vol 23.81%

Formula Breakdown

VaR = V × zα × σ × √T
ES = V × σ × √T × φ(z) / (1 − α)

Risk Level Guide

VaR % of Portfolio Risk Level Description
< 2% Low Risk Conservative risk exposure
2% – 5% Moderate Risk Typical risk level
5% – 10% Elevated Risk Above-average risk exposure
> 10% High Risk Significant portfolio risk

Heuristic thresholds for educational purposes. Actual risk tolerance varies by investor and asset class.

Model Assumptions
  • Assumes normally distributed returns (parametric/variance-covariance method)
  • Single-asset portfolio (or portfolio treated as single position with given volatility)
  • Constant volatility over the time horizon
  • Square root of time scaling (assumes independent, identically distributed returns)
  • No leverage or non-linear positions (linear model)

For educational purposes. Not financial advice. Market conventions simplified.

Understanding Value at Risk and Expected Shortfall

Video Explanation

Video: Value at Risk Explained

What is Value at Risk?

Value at Risk (VaR) is a statistical measure that estimates the maximum potential loss of a portfolio over a specified time period at a given confidence level. It answers the question: "How bad can things get under normal market conditions?"

For example, a 95% one-day VaR of $100,000 means there is a 5% chance of losing more than $100,000 in a single trading day. VaR is a quantile of the loss distribution — it is not the maximum possible loss.

Parametric VaR Formula
VaR = V × zα × σ × √T
V = portfolio value, z = z-score, σ = daily volatility, T = days

VaR vs Expected Shortfall

Value at Risk

Threshold measure
"How bad can things get?" Gives the loss level that will not be exceeded with probability α.

Expected Shortfall

Tail average
"If things do get bad, how much do we lose?" Average loss in the worst (1−α) scenarios.

The Three VaR Methods

  • Parametric (this calculator): Assumes normal distribution. Fast, closed-form solution using z-scores and standard deviation.
  • Historical Simulation: Uses actual past returns. No distributional assumptions, but limited by available data. See Hull Chapter 22.
  • Monte Carlo Simulation: Generates thousands of random scenarios. Flexible but computationally intensive.

Regulatory Context

Bank regulators historically used 99% 10-day VaR for market risk capital (Basel I–III). Basel IV (FRTB) switched to 97.5% Expected Shortfall, recognizing that ES is a coherent risk measure that better captures tail risk and respects diversification benefits.

Frequently Asked Questions

Value at Risk (VaR) is a quantile-based risk measure that estimates the maximum potential loss of a portfolio over a specified time period at a given confidence level. For example, a 95% one-day VaR of $1 million means there is a 5% probability that the portfolio will lose more than $1 million in a single trading day. Importantly, VaR is not the maximum possible loss — it is a threshold that losses are unlikely to exceed under normal market conditions.

VaR tells you the loss threshold at a given confidence level, while Expected Shortfall (ES), also called Conditional VaR (CVaR), tells you the average loss when that threshold is exceeded. ES is considered a superior risk measure because it is "coherent" — it satisfies subadditivity, meaning diversification never increases risk under ES. VaR can violate this property, which is why Basel IV (FRTB) switched to 97.5% ES for market risk capital requirements.

A 95% VaR of $500,000 means you are 95% confident that portfolio losses will not exceed $500,000 over the specified time horizon. Equivalently, there is a 5% chance of losing more than $500,000. This does not tell you how much you could lose in that worst 5% — for that information, you need Expected Shortfall, which measures the average loss in those tail scenarios.

The three main VaR calculation methods are: (1) Parametric (variance-covariance) — assumes returns are normally distributed and uses standard deviation and z-scores for a closed-form solution; (2) Historical simulation — uses actual past returns to build the loss distribution without assuming any particular distribution; (3) Monte Carlo simulation — generates thousands of random scenarios using assumed return distributions to estimate the loss distribution. This calculator uses the parametric method.

Regulators prefer Expected Shortfall because it is a "coherent" risk measure that satisfies subadditivity — the ES of a combined portfolio is never greater than the sum of the individual portfolio ES values. VaR can violate this property, potentially penalizing diversification. ES also captures the severity of tail losses, not just whether they exceed a threshold. The Basel IV Fundamental Review of the Trading Book (FRTB) switched from 99% VaR to 97.5% ES for calculating market risk capital.

The square root of time rule scales one-day VaR to multi-day VaR by multiplying by √N (the number of days). For example, 10-day VaR is approximately 3.16 times the one-day VaR. This rule assumes returns are independent, identically distributed (i.i.d.) with zero mean. The rule breaks down when returns exhibit autocorrelation, volatility clustering, or mean reversion — which is common in practice over longer horizons.
Disclaimer

This calculator is for educational purposes only and uses the parametric (normal distribution) method. Actual portfolio risk involves additional factors including fat tails, volatility clustering, correlation breakdowns during crises, and non-linear exposures. For professional risk management, use historical simulation or Monte Carlo methods with validated models. This tool should not be used for trading or capital allocation decisions.

Course by Ryan O'Connell, CFA, FRM

Value at Risk (VaR) Course

Master Value at Risk from theory to implementation. Covers parametric, historical, and Monte Carlo VaR methods with hands-on Excel exercises using real market data.

  • Parametric, Historical & Monte Carlo VaR methods
  • Expected Shortfall (CVaR) and backtesting
  • EWMA & GARCH volatility estimation
  • Hands-on Excel exercises with real market data