TITLE: Analysis of Recurrent Events Data in Medicine, Engineering, Marketing, and Other Fields
SPEAKERS: Wayne B. Nelson, Wayne Nelson Statistical Consulting and Training
MODERATOR: Din Chen
Abstract:
Recurrent events data observed over time on sample units include the number and costs of recurrent disease episodes in patients, repairs of products, sales to customers on Amazon.com, and births of babies to statisticians. Analysis of such data requires special statistical models and methods not covered in basic courses. This tutorial presents a general simple and informative nonparametric model and plot for analyzing such recurrence data on numbers or costs of recurrences. The plots and analyses are applied to data on numbers and costs of bladder tumor and herpes recurrences, car transmission repairs, childbirths to statisticians, sales resulting from promotions on amazon.com, and other applications. Computer programs that calculate and make the plots with confidence limits are surveyed.
The plots provide:
- An estimate of the average number or cost of recurrences per sample unit during a period of interest.Examples include the number and treatment cost of disease recurrences, product repairs during warranty or design life, and profit on Amazon.com sales promotions.
- The behavior of the population recurrence rate – does it increase or decrease with population age?This information is useful for decisions on product burn-in, overhaul, and retirement and on planning patient treatments.
- Predictions of the future number or cost of recurrences for a unit or the population.This is useful for predicting warranty costs of products and the demand for their replacement parts and for predicting patient treatment costs for recurrent diseases.
- A comparison of data sets from different populations; this is used to decide which disease treatments and product designs, materials, treatments, environments, etc., produce lower recurrence rates, and which amazon.com promotions yields more sales.
- Unsought, useful information.
Speaker Bio:
Dr. Nelson is a leading expert on analysis of reliability and accelerated test data. He consults on applications, gives training courses, and works as an expert witness. For 24 years he consulted across the General Electric Co. and received the Dushman Award of GE Corp. R&D for developments and applications of product reliability data analysis. He was elected a Fellow of the Amer. Statistical Assoc. (1973), the Amer. Soc. for Quality (1983), and the Inst. of Electrical and Electronics Engineers (1988) for his innovative statistical developments for reliability data modeling and analysis. He was awarded the 2005 Lifetime Achievement Award of the IEEE Reliability Society and the 2003 Shewhart and 2010 Shainin Medals of ASQ for his developments of reliability methodology and contributions to reliability education, and the 2018 Hahn Award of ASA for outstanding service to clients. He has received nine Outstanding Presentation Awards from ASA. He authored three highly regarded books Applied Life Data Analysis (Wiley 2004),Accelerated Testing (Wiley 2004), Recurrent Events Data Analysis (SIAM 2003), two ASQ booklets, and 140 literature publications.