The pre-holiday effect on US indices: does it still work?
A well-known effect from academic research: indices rise on the day before a market holiday. We tested it on broker data and on the S&P 500 in 1990–2010. Still visible.
Written by: WICKVIPERStudy ID: K149 (KSIEGA-01)Published: Updated:
Drafted with AI tools. Editorial review: WickViper Team, 7 Oct 2026. Sources are listed at the end of the article.
Works
Short answer
Do US indices still tend to rise on the day before a market holiday?
In our data, yes: on US500, US100 and US30 with a broker, +40 to +66 bp on average for the session before a holiday after costs (t 3.4–4.0), and +44 bp on the S&P 500 in 1990–2010 (t 3.27).
Data
US500, US100, US30 (CFD); S&P 500
Period
broker data to 2026; S&P 500 1990–2010
Sample
dozens of holidays across three indices
Costs
broker cost in the stress case (higher than typical)
Key numbers
US500 — before a holiday
+46.6 bp
US100
+65.6 bp
US30
+40.5 bp
S&P 500, 1990–2010
+44 bp
Where the idea comes from
The pre-holiday effect was described back in 1990 by R. Ariel in the Journal of Finance: US stocks rose much more on the day before a market holiday than on ordinary days. Many "anomalies" disappear after they are published — so we checked whether this one survived.
Result
On broker data, after costs in the stress case: US500 +46.6 bp, US100 +65.6 bp, US30 +40.5 bp for the session before a holiday, t from 3.4 to 4.0 — the only legs that passed the strictest multiple-testing correction in this study. On independent S&P 500 data from 1990–2010: +44 bp, t 3.27.
What it means for a trader
The calendar can be information: effects tied to money flows (holidays, month end, Fed decisions) are more durable in our research than chart signals.
It is a few sessions a year — you cannot build daily trading on it, but you can take it into account in a plan.
Limits
There are about a dozen holidays a year, so the sample is long in years but small in trades. Past results do not guarantee future ones.
Questions
Why does the effect exist?
Common explanations: a shorter session and better mood before a break, and short covering before the market closes. Research is not conclusive.
Does it work in Europe too?
That is a separate question — European indices are covered in other studies.