John Wasige wrote:> > Hi Jim, > > I still get the same error. This is to kindly request for your help. Attached herewith is the > test dataset. Thanks for your help.... Hi John, The file you sent is in some proprietary format that I cannot read. Fortunately there is a text header and this includes a description of a variable named "time" coded as the number of days since 1/1/1900. This is probably the variable you want to use instead of "dates". I don't know how "dates" was constructed, but it is probably the cause of the error. Jim