Chapter 18 Flashcards
A collection of historical observations recorded over time that are presented in chronological order.
Time series analysis
What are the 3 patterns in a time series
- trend
- seasonality
- cycles
The change of a variable over time
Trend Pattern
Patterns of highs and lows in a time series within a calendar year that tend to repeat annually
Seasonality
A pattern of highs and lows occurring over periods of many years. Minimum of 1 year
Cyclical pattern
The random variable in a time series referred to as the residual variation
Irregular component
A time series pattern with no trend or seasonality is described as
Stationary
The error or lack of precision in a forecast
forecast error or residual
The mean of the absolute error is called
The mean absolute deviation or MAD
The sum of the absolute relative (percent) errors
The mean absolute percent error or MAPE
Forecasting technique when a series is stationary and observations are equally weighted
Simple moving average
Forecasting technique when series is stationary and observations are not equally weighted
exponential smoothing equation
A value applied in exponential smoothing to determine the weights assigned to past observations. Vale is between 0 and 1
Smoothing constant
When successive residuals are correlated
Autocorrelation
What is the null and alt hypothesis in a Durbin-Watson Statistic
ho=no correlation
H1 = positive correlation
