HKUDS/Vibe-Trading · error · ValueError

estimation_window must be at least {MIN_ESTIMATION_OBSERVATI

Error message

estimation_window must be at least {MIN_ESTIMATION_OBSERVATIONS}, got {estimation_window}

What it means

event_study enforces that estimation_window (its length in periods) is at least MIN_ESTIMATION_OBSERVATIONS, the same floor estimate_market_model applies to finite observations. A shorter window cannot yield reliable alpha/beta or residual variance estimates.

Source

Thrown at agent/src/quantlib/eventstudy.py:351

    Returns:
        An :class:`EventStudyResult`. Events that cannot be measured -- unknown
        symbol, event date before the frame starts, not enough estimation rows,
        an all-NaN window -- appear in ``dropped`` with a reason instead of
        being silently skipped.

    Raises:
        ValueError: If the window bounds are inconsistent, ``estimation_gap`` is
            negative, ``model`` is unknown, the market series does not cover the
            frame's index, or no event at all could be measured.
    """
    start, end = event_window
    if start > end:
        raise ValueError(f"event_window start must be <= end, got {event_window}")
    if estimation_gap < 0:
        raise ValueError(f"estimation_gap must be >= 0, got {estimation_gap}")
    if estimation_window < MIN_ESTIMATION_OBSERVATIONS:
        raise ValueError(
            f"estimation_window must be at least {MIN_ESTIMATION_OBSERVATIONS}, "
            f"got {estimation_window}"
        )
    if model not in NORMAL_RETURN_MODELS:
        raise ValueError(f"model must be one of {NORMAL_RETURN_MODELS}, got {model!r}")
    if not events:
        raise ValueError("events is empty")

    index = returns.index
    missing_market = index.difference(market_returns.index)
    if len(missing_market):
        raise ValueError(
            f"market_returns is missing {len(missing_market)} label(s) present in "
            "returns; align them before calling"
        )
    market_aligned = market_returns.reindex(index)

    relative_days = list(range(start, end + 1))

View on GitHub (pinned to 80ffdda44c)

Solutions

Raise estimation_window to at least MIN_ESTIMATION_OBSERVATIONS (check the constant in agent/src/quantlib/eventstudy.py).
If history is genuinely short, event_study cannot run; use a different benchmark or drop the event.

Example fix

# before
result = event_study(..., estimation_window=20)
# after
from quantlib.eventstudy import MIN_ESTIMATION_OBSERVATIONS
result = event_study(..., estimation_window=max(MIN_ESTIMATION_OBSERVATIONS, 20))

Defensive patterns

Strategy: validation

Validate before calling

from quantlib.eventstudy import MIN_ESTIMATION_OBSERVATIONS
assert estimation_window >= MIN_ESTIMATION_OBSERVATIONS

Prevention

Import the constant rather than hard-coding the floor.
Ensure the returns history extends at least estimation_window + gap + |window start| periods before each event.

When it happens

Trigger: Passing estimation_window=10 when the minimum is larger (e.g. 30), often while tuning for short-history assets or trying to speed up tests.

Common situations: Optimising runtime by shrinking windows, backtesting newly listed tickers with limited history, or a config default copied from another library with a lower floor.

Related errors

AI-assisted analysis of HKUDS/Vibe-Trading@80ffdda44c (2026-08-28). Data as JSON: /api/errors/874138b15e5becd8. Report an issue: GitHub.