AnalyticBridge

Social Network For Analytic Professionals

Paul Wilson
Share 

Paul Wilson's Groups

 

Paul Wilson's Page

Latest Activity

Hi Ralph, Yeah, I'm confused by the red line as well. The blue one does make sense to me as well for the same reasons you mentioned. I also thought the red one could be the lift score for each decile separately (i.e. non-cumulative lift), but I'm o…
December 6, 2009
The red line doesn't make any sense. The blue line is not the cumulative lift of the red line, Why are the lines going in different directions between 50 & 60%. However the blue line does make sense . The cumulative lift value should always be equal…
December 6, 2009
Hm ... If I understand this chart correctly, then the lift is calucaled for each decile. Could it be that your ranking of scores is so good, that indeed most positive class items have been ranked to the top, so that less positive class items are av…
December 5, 2009
Paul Wilson added a discussion to the group Data Mining
Have a look at the lift chart below: http://img705.imageshack.us/img705/2292/liftchart.png I'm used to looking at cumulative lift curve with respect to the baseline one (blue line) which looks quite like many I've encountered before (i.e. the top…
December 2, 2009
OK now you're talking propensity scores and again I 100% agree the algorithms you mention are useful for that purpose. However, I don't see why would one need to build a new predictive model in order to evaluate campaign results (i.e. response rate…
September 10, 2009
"Of course the strict assumptions behind the tests are often violated but this does not necessarily mean that the results are worthless" Sure, but that 95% percent confidence that one provides hoping to give the results little more backbone looses…
September 10, 2009
I certainly appreciate your perspective and agree with many things said. I'll also add that in my opinion there is a danger of relying on the statistical tests too much for a number of reasons. Here are a couple I could think of off the top of my h…
September 9, 2009
I don't know what you mean by flexibility, but you can utilize R through both SAS and SPSS. As well, you can also write SQL in SAS using PROC SQL procedure.
August 31, 2009
Well, their database technology is not their flagship product and I don't think many will dispute that DB2, SQL Server etc are dominant players in that arena.......however they have a formal partnership with Teradata that gives them leverage and is…
August 29, 2009
There is a SAS for Forecasting Time Series book written by David Dickey, one of world's leading experts on time series (co-creator of Dickey-Fuller test). I find it a bit too mathematical for my taste as I prefer to focus on practical aspects and in…
August 27, 2009
You can try using this SAS Enterprise Miner tutorial online: http://www.sas.com/technologies/analytics/datamining/miner/trial/index.html The data is already pre-loaded and runs on their server so you don't actually have the software installed on y…
August 22, 2009
Jim Goodnight, SAS CEO was asked if he would be willing to sell his company and he flat out publicly refused and mentioned it would be more likely for SAS to acquire some names mentioned then other way around. He's not interested in taking his compa…
August 18, 2009
I'm afraid not. By the way where did you get the student versions of Clementine and Statistica?
August 15, 2009
Partial Least Squares is available in SAS Enterprise Miner and so is Principal Component analysis you can use to reduce correlated predictor variables. As far as recommendations in SAS/STAT without using Enterprise Miner maybe you can try PROC ROBU…
August 13, 2009

Profile Information

Field of Expertise:
Data Mining, Marketing Databases, Operations Research, SAS, Web Analytics, Statistical Consulting

Comment Wall

You need to be a member of AnalyticBridge to add comments!

Join this Ning Network

  • No comments yet!
 
 

Featured


Advertisement

 

© 2010   Created by Vincent Granville

Badges  |  Report an Issue  |  Privacy  |  Terms of Service