Why do we recommend weekly data? We are making judgments based on inter-market relationships that take time to evolve. A one-day rise in the corn price relative to the soybean price will neither change supply nor demand. Monthly data tends to be too slow to show trend changes, and has too few samples of data to get trustworthy results. Weekly data will also speed up the calculations from an estimated daily frequency.
Notice that the inclusive date range has been calculated for you. If you wish to include data outside of that range, you must remove or exchange the limiting data series to obtain common data for the date range preferred. In our example, the earliest common start date is displayed as "19720816 (KC)". This is because the KC series (coffee) begins on August 15, 1972. If we want to start earlier, we must discard the KC series contribution or exchange it with a series that goes back further. If you do not see a symbol listed, it is because all of our selected series begin or end, as appropriate, on the same date.
You may have to reduce the date range so that historical relationships in the data persist today. For example, the Green Revolution changed the level and character of the agricultural markets, so including earlier data is likely to worsen our results. We do recommend applying our detrending facility, but the investigator must still compromise between having a consistent economic period and having enough data to get a meaningful result. For more information on time series analysis and forecasting, see [Chatfield 1989] and [Abraham Ledolter 1983].
After selecting the options, press the "Next " button to continue by choosing lags.