Time Series Analysis in R
David S. Matteson
Associate Professor at Cornell University
Random Walk (RW) is a simple example of a non-stationary process.
A random walk has:
Time series plots of Random Walk:
The random walk recursion:
$$Today = Yesterday + Noise$$
More formally:
$$ Y_t = Y_{t-1} + \epsilon_t$$
where $\epsilon_t$ is mean zero white noise (WN).
Simulation requires an initial point $Y_0$.
Only one parameter, the WN variance $\sigma^{2}_{\epsilon}$.
The random walk process:
$$Y_t = Y_{t-1} + \epsilon_t$$
where $\epsilon_t$ is mean zero WN
As $Y_t - Y_{t-1} = \epsilon_t \rightarrow $ diff(Y)
is WN
The random walk with a drift:
$$Today = Constant + Yesterday + Noise$$
More formally: $$Y_t = c + Y_{t-1} + \epsilon_t$$
where $\epsilon_t$ is mean zero white noise (WN).
Time series plots of Random Walk with drift:
Time Series Analysis in R