Evaluating Claims About Overnight and Intraday Stock Returns
Summary
The document examines a claim that stock gains since 1993 occurred entirely overnight and that high-volatility stocks earn positive overnight returns followed by intraday reversals. The accepted response disputes the strength and reliability of these conclusions. It says an open-to-close and close-to-open decomposition for S&P 500 stocks would contradict the cited claim about all gains being overnight, and reports that a check across a small, varied set of stocks did not reproduce the proposed clean volatility-return pattern.
The response does not present its own full dataset, calculations, or statistical results, and it encourages readers to run independent studies. A second answer notes that an earlier working paper documented the effect, while raising uncertainty about why it was not published. The exchange therefore provides a contested research lead rather than a settled account of a robust anomaly. It does not establish whether the pattern generalizes across markets in Europe or Asia, which was part of the original question.
Key ideas
- Separate open-to-close and close-to-open returns to evaluate claims about when stock gains occur.
- The response challenges the claim that all gains were earned overnight.
- A small cross-sector check did not reproduce a clear volatility-linked overnight return pattern.
- The exchange leaves the anomaly’s robustness, publication status, and cross-market reach unresolved.
Tags
Full text
# When gains are made: Overnight or during trading hours? What is the connection to volatility? # When gains are made: Overnight or during trading hours? What is the connection to volatility? Falkenblog reports an interesting finding: All of the stock returns since 1993 are from overnight returns and cross-sectionally, volatility receives a positive overnight risk premium, a negative intraday one: Another Overnight Return Puzzle My questions Is this a known anomaly (At least I have never heard of it)? Is there a name for it? Is this documented in the literature? Is this effect exclusive to the US or also true for Europe and Asia? ## Answer by Matt Wolf (score 5, accepted) https://quant.stackexchange.com/a/4573 The study you cited seems to be exaggerating slightly. 1) "An interesting fact of returns is that all of the stock returns since 1993 are from overnight returns" -> This is simply factually incorrect. Why don't you pick the S&P 500 names, you calculate the log returns taking into account price changes from the open to the close, then you do the same for the close-open, you will notice that the chart on that website MUST be incorrect. Returns during the US trading sessions contributed much more returns than indicated in this study. 2) "If you take all the tickers, the top 1000 non-etfs over the past 2 years, and rank them by prior daily volatility, and then look at their overnight returns, you see that volatility is strongly positively correlated with subsequent overnight returns, which then reverse over the next day session." -> Also that does not seem to be accurate (such results with such low p-value). I ran the same study over a small subset of names of different sectors and groups and nowhere find such clean delineation. I cannot prove my point other than encourage those who want to make sure to simply run their own studies. Its extremely simple to run in R, you even get the price data off several websites free of charge. ## Answer by itzy (score 1) https://quant.stackexchange.com/a/4582 This was documented in this working paper about 6 years ago. I wonder why it was never published... may be some problem with the results.
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.