Quant Sandbox
DerivativesPortfolio & RiskFixed IncomeCorporate FinanceProbability & MeasureStochastic ModelsMarket MicrostructureGuide
Stochastic Models
Random Walk
Random Walk labSymmetric Random WalkRescaled Random WalkStandard deviationCentral Limit Theorem
Brownian Motion
Brownian labDefining the Wiener processIncrement explorerJoint distributions and covarianceBrownian transformations and invarianceQuadratic variationBrownian bridgeRunning maximum and minimumReflection principleFirst passage timesHitting probabilities
Geometric Brownian Motion
LabDefinition: ABM vs GBMEuler–MaruyamaMean reversionJumpsCorrelated motions
Itô Process
LabItô integralItô's lemmaMartingalesGirsanov
Monte Carlo
LabVariance reductionFeynman–Kac
Connected Guides
  • Random walks and Brownian motion
  • The law of large numbers and the central limit theorem
  • Probability spaces, σ-algebras and random variables

© 2026 Quant Sandbox · A study aid for quantitative finance

Privacy & dataNo cookies

This site does not use cookies and asks for no personal data. It keeps a few small settings in your browser's local storage — your chosen theme and language, the sidebar layout, and your progress and answers in the Guides — so it remembers them on your next visit. This data never leaves your device; clearing your browser storage removes it. Inputs you change can also be captured in the page URL, so you can share or bookmark a specific setup. The site uses Vercel Web Analytics, a privacy-friendly, cookieless service that records only anonymous, aggregated usage (such as page views) without identifying you or tracking you across other sites.

Standard deviation

How fast does the typical deviation of a random walk grow with time?

Goal: estimate the spread from more and more paths and watch the empirical standard deviation settle onto the ±√n envelope.

Simulation controls

Simulated pathsAdd paths: the dashed empirical std moves closer and closer to ±√n.
5
2101001000
250
50500
7
19999
Axis scale
×4
216
Predict first

Use ×4 as many steps. By what factor does the typical spread of the walk grow?

Empirical vs theoretical std

Empirical std at n = 250
20.81
√n at n = 250
15.81
Max relative gap
55.9%
Fitted log–log slope (theory: 0.5)
0.524

More paths give a sharper estimate: the worst gap to √n shrinks roughly like 1/√(paths), and the fitted slope approaches 0.5.

Path cloud: ±√n and ±empirical std
5 paths
  • ±√n (theoretical std)
  • ±empirical std

The green ±√n curve is the theoretical standard deviation; the dashed curve is the std measured from the cloud at every step. With few paths the estimate is noisy; add paths and it settles onto √n.

Typical deviation vs number of steps
Linear
Empirical std√n law

On log–log axes every power law is a straight line whose slope is the exponent. The √n law has slope 1/2.