All public courses using SAS are held at SAS, Marlow:

and cost for two-day courses 1000 GBP (plus VAT) per person which includes lunch and refreshments. Reduction to 900 GBP (plus VAT) per person for multiple bookings from the same organisation.

To book a place on a course either click here, or phone +44 (0)118 934 4265, or print and complete an application form (pdf format 115 Kb) .

Course dates for 2008/2009 :

• Propensity Scoring Models: 13th-14th Nov 2008, 12th-13th Feb 2009, 11th-12th June 2009, 5th-6th Nov 2009
  
• Segmentation of a Customer Database: 3rd-4th Nov 2008, 26th-27th March 2009, 24th-25th Sept 2009
  
• Planning & Interpreting of Marketing Campaigns: 18th-19th Sept 2008, 4th-5th June 2009
  

Response Times Analysis

Applications of Survival Analysis in Marketing and Credit Management Using the SAS^® System

The Course

Traditionally, much of the assessment of marketing initiatives is carried out by analysing response rates. To make this possible response has to be defined very strictly and usually with a time limit. This makes perfect sense for a specific campaign which is live for a fixed, usually short, period and is then closed so that no further responses are possible. It does not fit so well in more open-ended situations:

• What can be done to accelerate the time of next purchase of a regular customer?
• What tactics will cause more rapid conversation of prospects who have already registered interest?
• Can we create a model which predicts the time of next purchase of foreign currency on a credit card?
• How can a charity monitor the interval between donations?
• What characteristics of customers make them likely to respond more/less quickly?

These problems have three important features in common:

• They involve a period of time determined by two events, at least one of which will occur at a time determined by the customer.
• Whenever the modelling is carried out there will be some people who have not yet responded but will eventually.
• The response time distribution will usually be highly skewed and the modelling will need to accommodate that.

Even when there is a final endpoint, there will frequently be more data available to use response times as the basis for analysis. For example for final repayment of a fixed period loan the evaluation of default rates for a fixed term loan can use data only from completed cases (default or final repayment) while the methods discussed in this course can take advantage of the information contained in the length of time for which existing loans have been running successfully.

In short, situations where the outcome is not yet known for many individuals can often be tackled effectively by the tools and techniques of Survival Analysis. This course introduces the concepts, shows how to build the models and addresses the issue of presentation of the results in a commercially meaningful way.

The course uses SAS/STAT, in particular PROC LIFETEST, PROC LIFEREG and PROC PHREG.

NB: This training will be suitable for people who already have some knowledge of the statistical modelling process.