114 The Basics of financial economeTrics
■ (^) Each observation comprising a time series is a pair of the components,
time and value.
■ (^) Time series analysis comprises methods for analyzing time series data.
■ (^) The most traditional decomposition in time series analysis is trend,
cyclical, seasonal, and disturbance (error).
■ (^) An autoregressive structure assumes that the next period’s value depends
on the value of prior periods.
■ (^) An autoregressive of order one structure assumes that the next period’s
value depends on the last prior value.
■ (^) The correlation of a time series with its own past and future values is
referred to as autocorrelation.
■ (^) The random walk and error correction models are candidates for mod-
eling security price movements.