The EXPAND Procedure
The EXPAND procedure provides time interval conversion and missing value interpolation for time series.
The features of the EXPAND procedure include
-
conversion of time series frequency; for example, constructing quarterly estimates from annual series or aggregating quarterly values to annual
-
conversion of irregular observations to periodic estimates
-
interpolation of missing values in time series
-
conversion of observation types; for example, estimate stocks from flows and vice versa. All possible conversions supported between
-
beginning-of-period
-
end-of-period
-
period midpoint
-
period total
-
period average
-
-
conversion of time series phase shift; for example, conversion between fiscal years and calendar years
-
choice of four interpolation methods: cubic splines, linear splines, step functions, and simple aggregation
PROC EXPAND enables you to control the end point constraints used to fit interpolating cubic spline curves. In addition, you can transform series before and after interpolation (or without interpolation) using any combination of the following:
shift by constant square root lags
scale by constant square leads
change sign logistic differences
absolute value inverse logistic cumulative sum
reciprocate upper bounds moving sum
logarithm lower bounds moving average
exponential reverse series
The EXPAND procedure offers support for a wide range of time series
frequencies:
YEAR SEMIMONTH DAY
SEMIYEAR TENDAY HOUR
QUARTER WEEK MINUTE
MONTH WEEKDAY SECOND
The basic interval types can be repeated or shifted to define a great variety of different frequencies, such as fiscal years, biennial periods, work shifts, and so forth.
Statistics and Operations Research Home Page | SAS/ETS Software