Working with Time Series Data

Interpolating between Stocks and Flows, Levels and Rates

A distinction is made between variables that are measured at points in time and variables that represent totals or averages over an interval. Point-in-time values are often called stocks or levels. Variables that represent totals or averages over an interval are often called flows or rates.

For example, the annual series Gross National Product represents the final goods production of over the year and also the yearly average rate of that production. However, the monthly variable Inventory represents the cost of a stock of goods at the end of the month.

The EXPAND procedure can convert between point-in-time values and period average or total values. To convert observation characteristics, specify the input and output characteristics with the OBSERVED= option in the CONVERT statement. For example, the following statements use the monthly average price index values in USPRICE to compute interpolated estimates of the price index levels at the midpoint of each month.

proc expand data=usprice out=midpoint
   id date;
   convert cpi ppi / observed=(average,middle);