Characterizing a time series involves
estimating not only a mean and standard deviation but also the correlations
between observations separated in time. In the identification phase
of the Box Jenkins procedure the empirical autocorrelation (ACF) as
well as the partial autocorrelation function (PACF) are important tools.
The autocorrelation function measures the strength of relationship
between and . For example if near to one, a “high” value of will
be followed by a “high” value tomorrow. The ACF is an important tool
in identifying the order of moving average time series models.
Partial autocorrelations measures the strength of the
relationship between observations in a time series controlling for
the effect of intervening time periods. Specifically, partial autocorrelations
are useful in identifying the order of autoregressive models.
The plots of ACF and PACF are called correlogram.
The Ljung-Box-statistic (Q-statistic) at lag k is a
test statistic for the null hypothesis that there is no autocorrelation
up to order k. The definition of it is:
is asymptotically distributed
as a with degrees of freedom equal
to the number of autocorrelations.
The autocorrelation of a series at
where is the sample mean of
the time series.
The partial autocorrelation of a series
The Add-In is written in VBA.
All links will be open in a new window
Time Series Analysis - ARIMA models - Basic Definitions and Theorems
about ARIMA models (HTML)
The correlogram Add-In was written by Kurt Annen.
This program is freeware. But I would highly appreciate if you could
give me credit for my work by providing me with information about possible
open positions as an economist. My focus as an economist is on econometrics
and dynamic macroeconomics. If you like the program, please send me