STA457 Flashcards
Horizontal pattern
Data fluctuates around a constant mean
Stationary time series
Statistical properties are independent of time.
The process generating the data has a constant mean.
The variability of the time series is constant over time.
Stationary time series implies horizontal pattern, but not the other way around.
Trend pattern
Time series show gradual shifts or movements to relatively higher or lower values over a long period of time.
Seasonal pattern
Time series displaying a repeating pattern over a period of time.
Trend + seasonal pattern
Time series displaying a repeating pattern over a period of time, while gradually increasing or decreasing over a long period of time.
Signal + noise
Signal is deterministic, noise is random
Types of white noise
- Collection of uncorrelated random variables (white noise) with mean 0 and variance \sigma_w^2
- Collection of noise are independent and identically distributed with mean 0 and variance \sigma_w^2.
- Gaussian white noise. Collection of noise are iid Normal random variables with mean 0 and variance \sigma_w^2
Moving average and filter
Replacing white noise series with moving average (averaging the neighbouring noise).
Autoregression
Regression of the current value of the time series as a function of the last value of the series.
Random walk with drift
Current value of of time series is a function of the previous value of the time series plus white noise and constant delta, which represents drift
Autocovariance function
Covariance of 2 elements of a time series