Value at Risk (VaR)

Last updated:

The maximum loss expected at a given confidence level. The regulator's favorite, despite its flaws.

Quick Answer

What is Value at Risk (VaR)?

Value at Risk (VaR) is the maximum loss expected over a given time horizon at a given confidence level, under normal market conditions. A 1-day 95% VaR of −$3,000 means there is a 95% chance daily losses will be no worse than $3,000 (and a 5% chance they will be worse). VaR is the dominant regulatory risk measure but has known weaknesses.

P(Loss > VaR_α) = 1 − α

Formula

P(Loss > VaRα) = 1 − α
α = confidence level (e.g. 95%) · VaRα = the α-quantile of the loss distribution

VaR is the threshold loss such that the probability of exceeding it is 1 − α. Computed via historical simulation, parametric (Gaussian), or Monte Carlo methods.

Intuition — what is this number telling you?

VaR is widely criticized for two reasons. First, it does not tell you how bad the bad days are — only their threshold. Two portfolios with identical VaR can have very different Expected Shortfall (CVaR) in the tail. Second, VaR is not "subadditive" — combining two portfolios can in theory increase total VaR, which is mathematically incoherent. Most modern risk frameworks (Basel III for banks) prefer CVaR.

Worked example

Step-by-step

Your portfolio's daily returns over the past 1000 days, sorted from worst to best, have the 50th worst at −2.3%.

Daily 95% VaR (historical method) = −2.3%. With a $100k portfolio, that translates to −$2,300.

Meaning: 5% of days (50 of 1000) had losses worse than −2.3%, but we cannot tell from VaR alone how much worse.

What's a good Value at Risk (VaR) value?

VaR is asset-class-dependent. Daily 95% VaR for the S&P 500 is roughly −1.5% to −2%; for crypto it can exceed −5%; for cash it is essentially 0.

Calculate your Value at Risk (VaR) free

Upload a brokerage CSV (IBKR, Schwab, Fidelity, Robinhood, Coinbase, Kraken, Binance…) and get your Value at Risk (VaR) computed on your real holdings — alongside 70+ other portfolio metrics. No signup, runs in your browser.

Open the Value at Risk Calculator →

Related metrics

CVaR (Conditional Value at Risk)  ·  Expected Shortfall  ·  Kurtosis  ·  CDaR (Conditional Drawdown at Risk)  ·  Standard Deviation

Frequently asked questions about Value at Risk (VaR)

What confidence level should I use?

95% is standard for daily VaR. 99% for stress scenarios. 99.9% for tail-event modeling. Lower confidence (90%) is rarely used in practice.

How is VaR calculated?

Three methods: historical (sort actual returns), parametric (assume normal distribution), or Monte Carlo. Foliolytic uses historical by default and provides parametric as comparison.

Why is CVaR preferred?

VaR does not tell you how bad the tail is. CVaR (Expected Shortfall) averages losses beyond VaR — capturing severity. Basel III favors CVaR.

Does Foliolytic compute VaR?

Yes — at 95%, 99%, and 99.9% confidence in the tail risk section.

See Value at Risk (VaR) on your real portfolio

Upload your brokerage CSV — Foliolytic computes Value at Risk (VaR) plus 70+ other metrics using real historical prices, real Treasury yields, and real CPI data. Free, no signup, your data stays in your browser.

Analyze your portfolio free →