Interpreting Long-Lag ACFs as Evidence of Price Momentum

Summary

The document raises a time-series interpretation problem: a price chart over 19 years appears to show little momentum, while its autocorrelation function has positive continuation over roughly 700–800 business-day lags. The author reports testing for trend stationarity with the Zivot–Andrews procedure before examining the ACF, and asks why the apparent multi-year persistence conflicts with the visual impression and the efficient market hypothesis.

No answer or resolution is included, so the document does not establish that the asset has a tradable momentum effect. Its value is as a research question about what an ACF of price levels can and cannot say. In particular, the reported test and plot are not enough here to determine whether the result reflects persistence in levels, return predictability, or a specification issue. The series, plot, asset identity, and test details are absent, limiting any conclusion.

Key ideas

• The author compares a visually weak trend with strong long-lag autocorrelation in prices.
• The reported ACF suggests continuation over roughly 700–800 business days.
• A Zivot–Andrews test was used to assess trend stationarity before the ACF was reviewed.
• The document poses the interpretation question but provides no answer or evidence of profitable momentum.

Tags

# Interpreting the ACF graph


# Interpreting the ACF graph












I am currently struggling with the interpretation of a price chart and the corresponding ACF graph. The question is, if there is momentum in the price of this asset. This is the corresponding price chart for a period of 19 years (5000 business days):

It doesn't´t seem to have much of momentum when looking at the price development. After verifying that the time series is (trend)-stationary by means of the Zivot / Andrews Test (ur.za in R), i generated the ACF plot to get a further idea of potential Momentum. And there´s the problem. The ACF graph indicates a price continuation pattern of around 700-800 lags (business days as the data has business days as frequency) or 2.5 - 3 years of momentum. But this is in strong contrast to the price chart above and to the efficient market hypothesis. Is there any rationale mistake from my side?

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.