The Test Bench › gate

Does Up/Down Volume (Nasdaq A-D volume) actually work?

MARGINAL

Real but small -- not worth what it costs to run.

The claim

A chart-based signal that times the market — StockCharts / breadth-volume chartists

What we did

Tested against Buy & hold SPY, same window, 2011-2026, prior-day, OOS 2018+.

The result

Result: -0.01 dSharpe (vs buy-hold); OOS +0.29 unsupported

EMA21 & EMA50 above zero: dSharpe -0.01 (no full-sample edge); 'climbing' filter -0.27; OOS +0.29 a period artifact

Verdict

The Nasdaq up/down-volume breadth panel (EMA21 & EMA50 of net up-down volume) as a long/cash gate. 'Both EMAs above zero' has no full-sample edge (dSharpe -0.01) -- it's simply long 61% of the time, tracking the index. The flattering OOS +0.29 isn't supported by the full sample (in-sample edge is nil), and adding the 'climbing' filter actively hurts (-0.27). A volume-weighted cousin of the advance/decline line, same verdict: breadth confirms the move, it doesn't time it.

What the test did and did not do

tested out of sample
point-in-time data
checked for look-ahead
net of real costs

Almost nobody publishing a backtest says which of these they did. We list the ones we failed as well as the ones we passed.

Tested 2026-06-23. The same treatment, applied to every other system, is on the test bench.

← Up/Down (Advancing) Volume All findings VIX9D<VIX →

Written with AI assistance from our own test database. The numbers are computed, not composed.
General market commentary for education, not personalised investment advice. Backtested results are hypothetical. Trading carries a real risk of loss.