Using Early-Session Returns to Study Intraday Momentum

Summary

The document asks whether the sign of an index’s first-hour price move predicts whether the full trading day will close up or down. It frames the question as a possible intraday momentum strategy and asks whether the effect might be strong enough to investigate. No index data, statistical test, or performance result is provided, so the proposed relationship remains a hypothesis.

The answer points to research by Gao, Han, Li, and Zhou (2015), which studies whether the first half-hour return predicts the last half-hour return. That paper offers a related methodology for testing an intraday momentum idea, but it does not directly replicate the question’s proposed first-hour-versus-full-day comparison. The document gives no details of the paper’s sample, findings, transaction costs, or robustness. Any application to large indices or a full-day direction forecast would therefore require separate empirical testing.

Key ideas

• The proposed signal is the sign of the first hour’s return, compared with the sign of the full day’s open-to-close return.
• The question presents a hypothesis and provides no empirical evidence for its predictive power.
• Research on first-half-hour returns predicting last-half-hour returns offers a related testing approach.
• The cited study does not directly test the exact first-hour-to-full-day relationship.

Tags

# Momentum Analysis on Indices


# Momentum Analysis on Indices












I'm interested in analysis of day-on-day momentum of certain large indices. In particular, I'm interested in the predictive power of the sign of the price change of the first hour of trading with respect to the sign of the difference between the open and close price. For example, I'd be interested in the probability of a positive day-on-day price change conditional on losses/gains in the first part of the trading period.

Does anyone know of attempts of analyzing this idea? If not, would you expect a sufficiently great predictive power to make investigating this worthwhile?

## Answer by Quant.Pi (score 2, accepted)

https://quant.stackexchange.com/a/38426

I think there is not the exact replication of the momentum strategy you proposed in your question above.

Anyway, in Gao, Han, Li & Zhou (2015) the authours suggested a methodology that can be used to develop a momentum strategy model on the basis of your hypothesis.

Shown below the reference suggested:

> GAO, Lei, et al. Intraday momentum: The first half-hour return predicts the last half-hour return. 2015.

You can find the .pdf file of the paper on the SSRN website.

Hope this helps.

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.