ST
StateTrace
Visual Quant & Low-Latency Systems Lab
GitHub
Curriculum/bootstrap-resampling

Bootstrap Resampling

statistics·L0 · atom·stub

Resample observations with replacement to estimate the sampling distribution of any statistic — no closed-form standard error, no normality assumption, no i.i.d. assumption (with block-bootstrap variants for time series). The L0 atom underneath every modern non-parametric inference in finance.

Prerequisites(root concept)
Bridges
  • block-bootstrapmodel to implementation
    Time-series violate the i.i.d. assumption of classical bootstrap. The Politis-Romano stationary bootstrap (1994) draws blocks of consecutive observations to preserve local dependence structure.
  • closed-form-seshared failure mode
    Closed-form standard error for Sharpe assumes normality and i.i.d. returns. Both assumptions are violated in financial data; bootstrap-based confidence intervals are reliably wider than the closed-form lie and reliably tighter for the truth.
Status

This concept is a node in the curriculum DAG. The full lab — page blocks, done state, references — has not been authored yet. The relations above describe where it sits in the graph.

Author at: content/concepts/bootstrap-resampling/card.ts