What does the nth order partial autocorrelation coefficient measure?

• A. The overall correlation between two time series
• B. The marginal contribution of lagged returns
• C. The volatility in asset prices
• D. The average return over several periods

Answer: (B)

The nth order partial autocorrelation coefficient specifically measures the marginal contribution of the nth lag of a time series to its current value, while controlling for the effects of all intermediate lags. This is a crucial aspect of time series analysis, as it helps to isolate how much of the current value of a series is explained by its past value that is n lags behind, without the influence of values that are between the two.

In practical terms, when analyzing time series data, such as financial returns, understanding the influence of various lags allows analysts to build more accurate models. The partial autocorrelation function (PACF) is often used in autoregressive models to determine how many lagged values to include, thereby delineating the direct relationships among observations in the series over time.

The other options do not accurately represent the focus of the nth order partial autocorrelation coefficient: overall correlation pertains to broader relationships between two different series, volatility refers to the degree of variation in asset prices generally, and average return denotes a simple computation of returns over periods rather than a dynamic relationship across different lagged observations.