I am trying to determine if it is possible to run the DBMS_STATS_FUNCS.SUMMARY procedure against just one partition of a partitioned table. I have a large, range partitioned table in an Oracle 10g database. Each month I load ~ 1 billion new rows into a new partition in that table . I want to find a way to see what has changed with the data, in order to give feedback to my data provider on the quality of the data. I generate optimizer stats including column histograms, immediately after loading, which gives some insight into the distribution of the data in each column in the table. However, if I could run this procedure against the newly loaded data, I could get the mean, variance, std deviation, etc. that would be even better.