sparse time forecast

Hello to All

I have a dataset pertaining to 1980 and 2000. Because I have actual value in 1980 (CR80) and 2000(CR00); I want to make a model that is a forecast for the data point in 2000 using the value in 1980. I want to use covariates from 1980 to predict how good the forecast is. What could be the method for this? CR80 and CR00 are credit ratings like AAA AA A BBB BB B and etc.

Thanks to all!