Modeling loss given default (LGD) by finite mixture model The 'highly skewed' and 'highly irregular' loss data from the insurance and banking world is routinely fitted by a simple beta/ lognormal/gamma/Pareto distribution. While looking at the distribution plot, I bet that many people don’t want to buy this story and are willing to explore better ways. Finite mixture model that incorporates multiple distributions can be a good option in the radar map. For example, Matt Flynn will present how to use PROC NLMIXED to realize finite mixture model for insurance loss data in the incoming SAS ANALYTICS 2011 conference. Finally the revolutionary FMM procedure shipped with SAS 9.3 makes ...
A test to count missing values for large data This morning Rick introduced how to count the missing frequencies for all variables in a dataset, including character and numeric variables. He provided two solutions by either PROC FREQ or PROC IML. I have a petty macro based on PROC SQL’s nmiss() function to do the same job. In this big data era, I am interested in those SAS codes’ efficiencies to check large data. Then I simulated a 1e8 size dataset (5 numerical and 5 character variables) and tested the 3 methods. According to the results, PROC FREQ is slightly better than PROC SQL in both memory usage and ...
Add 10 buttons to enhance SAS 9.3 environment One striking change in SAS 9.3 is that everything is HTMLized. Adding user-defined buttons to the toolbar of SAS’s windowing environment would make coding more efficient. 1. Clear log and resultThe most used SAS command is now prompted by a button.output;clear;log;clear;wpgm;2. Clear files left by results viewerLots of trash (mostly HTML files and PNG-formatted images by SAS 9.3's results viewer) would permanently remain in the current folder after each SAS session (the current folde is indicated on the Window Bar at the bottom). To avoid the possibility that someday the hard disk is jammed, clearing them out at times may ...
My 10 wishes for SAS No wonder that SAS 9.3 is one of SAS’s greatest products. Beyond it, I have 10 secret wishes and hope the far-away SAS 9.3.2 or SAS 9.4 might realize them someday. 1. Trigger for SAS datasetA wonderful thing about SAS is that it can be used as a RDBMS with full functionality. Just one piece from the SQL language is missing in SAS - trigger. Adding triggers would bring more security for SAS datasets or data views, and automate some routine operations.  2. PROC PIVOT for pivot tablePivot table is a huge business success, since I found that every boss ...
10 interesting discoveries from SAS 9.3 1. SAS 9.2 and SAS 9.3 coexistI thought that a new installation of SAS 9.3 would automatically uninstall the old SAS 9.22 on my laptop. Amazingly, the two editions live together peacefully. The directory for SAS 9.3 is SASHOME while SAS 9.22’s is SAS. I can even run them simultaneously, and they don't bother to interfere each other. Anyway, Enterprise Guide 4.3 replaced the old 4.2 edition after this upgrade. 2. Zero-configuration for Enterprise Miner 7.1In SAS 9.2 era, installation of Enterprise Miner was a nightmare for me. I can’t imagine somebody other than a trained technician can install it ...