May 28, 2014
The Lost Sales case study and data sets.
Download the case studyDownload the data set - 1Download the data set - 2
Determine whether certain conditions make it more likely that a customer order will be won or lost.
JMP features demonstrated:
Analyze > Distribution, Analyze > Fit Y by X (Contingency), Analyze > Fit Y by X (Logistic), Analyze > Fit Model (Nominal Logistic), and Prediction Profiler (from Fit Model)
Statistical/graphical tools used:
Bar charts and frequency distributions, mosaic plots, contingency tables (cross tabs), chi-squared tests, logistic regression, predicted values and confusion matrix.
This collection of business case studies was provided by Marlene Smith at the UC Denver Business School. Lost sales data provided by North Haven Group, LLC.
Note: Updated to JMP 12 May 13, 2015.