Choosing a Volatility Measure to Compare Nasdaq Years

Summary

The question compares Nasdaq volatility across years using average daily true range (TR). Since the index level changes over time, the author asks whether TR should be converted to a percentage or expressed through logarithms. The response says the right calculation depends on the quantity being compared: average TR describes absolute point movement, while a percentage or log-based measure describes movement relative to the index level.

The key lesson is to define the intended meaning of volatility before selecting a measure. Averaging TR is appropriate when absolute changes are the object of interest; it does not answer the same question as a scale-adjusted measure. The response does not prescribe a denominator or establish one universally correct method. It gives a conceptual distinction rather than worked calculations or empirical evidence, so the choice must reflect the comparison’s purpose.

Key ideas

• Average true range measures absolute price movement, so it can be sensitive to changes in the index level.
• A percentage or log-based measure represents movement relative to price scale.
• The appropriate volatility measure depends on what kind of movement the comparison is intended to capture.

Tags

# Comparing Volatility


# Comparing Volatility












Sorry for asking beginner level question. I want to compare Volatility of two different years of Nasdaq. I thought to compute true range (TR) on daily data and then average out TR values of this year vs 2019. My question is this seems to be incorrect way as scale of Nasdaq index is different in these two years.

```
TR = ​max [(high − low), abs(high − closePrev​), abs(low – closePrev​)]
```

I thought to convert it into % volatility. Still wondering what should be in denominator. OR Taking log.

## Answer by Richard Hardy (score 3, accepted)

https://quant.stackexchange.com/a/73559

What is correct or incorrect depends on how you define the object that you want to compare across years. If you define volatility as you did, then you are doing the correct comparison. If you define volatility as % volatility or log volatility, then what you did is not correct. In essence, you have to choose a measure that makes intuitive sense for your purpose and then go with it.

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.