Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
5 Cards in this Set
- Front
- Back
|
Stationarity |
A time series whose properties do not depend on the time at which the series is observed --trends or seasonality will break this BUT cyclical behavior will NOT if the cycles are not of a fixed period/length |
|
|
differencing |
computing the differences between consecutive observations --stabilizes the variance of a time series, and can eliminate trend and seasonality |
|
|
ACF |
Sample auto correlation function, gives correlations between the series and the lagged values of the series --often very useful when looking at the residuals of a model |
|
|
Python ACF plot |
pandas.tools.plotting.autocorrelation_plot(total_data["organic.all"]) |
|
|
ADF |
augmented Dickey Fuller test. A regression test to determine if a series needs to be differenced, uses a regression series where the first order difference is regressed against the previous value and other differenced values. If the co-efficient on the previous value is zero then it does not need to be differenced and if if it less than zero it is already stationary |
