SAS Time Series Exploration

SAS Time Series Exploration:
We use Time series exploration to get a statistical insight about the data which helps estimating the best time series model to fit and forecast.
The exploration task helps detecting stationarity through plotting, ACF, PACF and Unit Root Test results.

Data setting:
Data – The data set to analyze.
Roles – The dependent and indepedent variables.
Time ID and season length- if there is a seasonality, setting these variables helps detecting it.
image49


Analyses settings:
– Time Series
– Series Histogram
– Seasonal Cycles
– Auto-correlation Analysis.
– Decomposition Analysis.

image47

– Statistical analysis:

Input Data Set
Name BIZ4CAST.CPI_CHANGE
Label
Length of Seasonal Cycle 1
Variable Information
Name CPI_Change
Label CPI Change
Number of Observations Read 17
Time Series Descriptive Statistics
Variable CPI_Change
Number of Observations 17
Number of Missing Observations 0
Minimum 1.6
Maximum 4.1
Mean 2.694118
Standard Deviation 0.711047

Plotting helps detecting trends, seasonality, outliers, and stationarity.
image46

– Auto-Correlation analysis results:
ACF and PACF help detecting:
– trends: If there is a trend, the ACF will always be falling slowly, meaning Y’s of all lags will be correlated to the Yt.
– seasonality: When there is a seasonality of m, the ACF of lag m will have a spike.
– stationarity: For non-stationary, the ACF is falling slowing and PACF only has Lag1 spike of near 1 value.

image48

Leave a Reply

Your email address will not be published. Required fields are marked *