Selecting MAX values within records with the same name

Question

I'm working in ArcMap 9.3 and I've never dealt with that kind of queries...

I need to Select the MAX value from column [A] for each set of records in the table which have the same value in column [B]

For example

[A] [B]
100 aaa 
101 aaa
102 aaa
999 aaa
100 bbb
101 bbb
102 bbb
999 bbb

so the selection would be record#4 (where [A]=9999 which is the biggest value of all 'aaa') and record#8 (where [A] = 999 which is the biggest of all 'bbb')

Is it possible to do that using queries and subqueries when working with databases?

Any help appreciated! Dan

Answer 1

Do you just need to know the max value for each unique entry in column B, or do you actually need to select the features with the maximum values on your map?

If you just need an output table with headings [B], [Max_of_A], you can open the attribute table, then right-click column B and choose Summarize. In the list of summary statistics to be calculated, choose Maximum for column A and you should end up with the output you need.

If you need to actually select the features on your map, one way would be to join the table produced by Summarize back to your original features. Let me know if you'd like more details.

Someone else may have a better way, but I don't think you can do this directly using ArcMap's Select by Attributes option(?). Would be interested to be proved wrong, though.

Edit

As @GIS-Jonathan says, if your data is stored in a spatial database and you're just using ArcMap to view results etc. then your best bet is to use a GROUP BY query as per his method. If you're working with a shapefile or a feature class stored in a file or personal geodatabase, the method below should work, but it's a bit of a faff! 300,000 records shouldn't be a problem, though.

Start by using Summarize on your original table. You should get an output something like this:

[B] [Max_of_A]
aaa 999
bbb 999

Now join this table back to your original dataset using column B as the join field (right-click your original dataset, then Joins and Relates > Join. Choose to keep all records). This should make your attribute table look something like this:

[Orig_A] [Orig_B] [Summary_B] [Max_of_A]
100 aaa aaa 999
101 aaa aaa 999
102 aaa aaa 999
999 aaa aaa 999
100 bbb bbb 999
101 bbb bbb 999
102 bbb bbb 999
999 bbb bbb 999

Then you can use Select by Attributes to select all the rows where [Orig_A] = [Max_of_A].

Quite a faff, but I can't think of an easier way to do it if your data isn't already in a spatial database supporting GROUP BY. Maybe someone else can suggest a better way?

Good luck!

• GIS-Jonathan: +1 Agree with this. It depends on the nature of the problem. If its only one or two, manually selected statistics per my answer is best. If its lots, then summarize per JamesS is best. The database option I listed would be simplest if you're comfortable in that environment and have lots of results you want tabulated.
• Dan Volkov: Yes, actually I need to select these features. And I have to deal with 300 000 records...
• JamesS: Please see edit. Might give you some more ideas if GIS-Jonathan's SQL-based approach isn't an option.

Answer 2

Its best to get this data straight from the database if you want it for every COLUMN_B grouping. This query in a database like Oracle would be (other databases will be similar):

select count(*), MAX(column_A), column_B from TABLE_NAME group by column_B

That will give:

4, 999, aaa
4, 999, bbb

To do it in ArcGIS is fairly easy. Use the Select by Attributes to select everything in group AAA or BBB. Then in the attribute table, right click on the column you want the MAX of and select Statistics. This will show the "maximum" which is of the selected rows.

• Dan Volkov: As said there are more than 300 000 records in the table so I can't do that one by one (set of records) so I still wonder if it's possible to make some query for that.
• GIS-Jonathan: Doing it in the database would probably be the best option then. The syntax will be similar to the SQL I provided, you'll need to "group by" your B column. If you just google for "group by" and your database of choice that should get you documentation with specific examples.

Answer 3

This can be achieved fairly simply by running the statistics tool. You can then select the field that you want the max/min or other statistical attribute. You then select the case field which in your case would be column B. Hope this helps someone.