Business Forecasting Topic 8 Flashcards
Box Jenkins
ST forecasting
- exploit correlation between observations at different points in time
- identify tentative model
- use series of diagnostic tests to assess model adequacy
stationarity (time series)
structure doenst change over time
each distribution = same mean and variance irrespective of time period
mean and variance = constant over whole time span of series
autocorrelation
correlation of a variable with itself at different times
-graphed above confidence limit = significant -> confidence limit requires std dev and mean
partial autocorrelation
how much of a correlation is there between sales k-periods apart, when the effects of the intervening weeks are removed
pattern of PACFs = help us identify forecasting model appropriate for given time series
above confidence limit = significant
influence of intermediary things are removed
significance tests
applied to ACF and PACF based on null hypothesis that data is completely random
approx standard error = 1/ root of n (n = number of data points)
calculating the ACF or PACF coefficients
significant values lie outside
these values are plotted as confidence limits on the diagrams
autoregressive models
first order autoregressive model
ACF AND PACF for autoregressive models
ACF - declines rapidly to zero (exponentially) or oscillates between positive and negative values and dying
PACF- cuts off after lag 1
moving average models
- show relationship between variable to be forecast shocks in earlier periods
ACF AND PACF for moving average models
exact reverse of first order autoregressive
mixed models
- involve both autoregressive and moving average terms
ACF AND PACF for mixed models
both decline rapidly to zero
ARIMA
- classify different models that are available
ARIMA (p, d, q)
ARIMA (1,0,0) = first order autoregressive
ARIMA (0,0,2) = second order moving average
ARIMA (1,0,1) = mixed model
degree of differencing
stationary series require no differencing
stages in box Jenkins approach to forecasting
- identify appropriate model
- estimate model parameters
- use diagnostic tests to make sure these parameters are appropriate
- use model to make forecasts