# Progress

* **20/04/2010** Tests for trend in repairable systems when there are several systems. Some theory for renewal processes.Slides

* **09/04/2010** Parametric analysis of NHPP: Likelihood construction and MLE. slides

* **26/03/2010** More on recurrent event slides

* **23/03/2010** Recurrent events and repairable systems. Nonhomogeneous Poisson processes (NHPP). Ch. 7 in book. Non parametric estimate of W(t)

* **16/03/2010** Case study in Cox regression: CNS lymphoma data. Here is the data set, a description of the data set and the R code to perform the analysis

ALT models (Ch. 12 of H&R book). One worked out example data and R-code

* **12/03/2010** Lecture 16: Continue Cox regression. Estimate of the cumulative baseline hazard. Model checking: Cox-Snell residuals, Schoenfeld residuals, “log minus log” plot, dfbetas. Here is the R code to reproduce the example on sodium sulphur battery data in Ansell&Phillips

* **09/03/2010** Lecture 15: Cox regression. The partial likelihood. Simple example for hand-calculations Testing for significant coefficients. Comparison of Cox and Weibull regression a simulated case

* **05/03/2010** Lecture 14: Case studies in Weibull regression. Motorette.R, alloy.R, AlloyData

* **02/03/2010** Lecture 13: Survival regression (expecially for weibull and exponential models) Book from Ansel & Phillips

* **23/02/2010** Lecture 12: Likelihood estimation for log-location scale models. Exact confidence intervals for exponential data with type II censoring. Started regression models.
Slides of the lecture

* **19/02/2010** Lecture 11: Maximum likelihood for Weibull model. Here are the slides. You can find the R function to compute the log-minus-log and the PP plot in the Helpfull R functions section.

* **16/02/2010** Lecture 10: Continue parametric inference. Confidence intervals and tests.

Slides

* **12/02/2010** Lecture 9: More on Log rank test.

Parametric models. Likelihood contribution for observed failures, right, left and interval censored data. Maximum likelihood estimation: the exponential case. Here are some slides about likelihood construction and about parametric inference on lifetime data.

Slides from the lecture.

* **09/02/2010** Lecture 8: TTT plot for censored data set (NB what done in the lecture is different from the book!!!!). The logrank test for comparison of survival functions. (Not in the book…)

Slides from the lecture

* **05/02/2010** Lecture 7: Finished Nelson-Aalen estimator. TTT plot and Barlow-Proschan's test for complete data set.

Slides about TTT plot in R.

* **02/02/2010** Lecture 6: The Nelson-Aalen estimator (11.3.6, to be continued next week).

The exponential distribution and the Poisson process (2.10 in the book).

Additional notes About the Exponential Distribution, Poisson Process, Total Time on Test and Barlow-Proschan's Test.

Slides about Nelson Aalen estimator in R.

* **29/01/2010** Lecture 5: Non-parametric estimate of the reliability function, the Kaplan Meier estimator.

Slides on how to compute the KM estimator with R.

* **26/01/2010** Lecture 4: CANCELLED!

* **22/01/2010** Lecture 3: Extreme value distribution, Gumbel distribution (Ch 2.17). Log-location scale family (download extra notes). Censoring mechanisms (Ch 11.2).

(*For a detailed definition and discussion of independent censoring you may read Chapter 1.3 in Kalbfleisch and Prentice "The Statistical Analysis of Failure Time Data", Wiley 2002*)

* **19/01/2010** Lecture 2: MTTF (2.6). Distributions (2.9-2.14): Exponential, Weibull, lognormal. QQ-plot.

Slides about fitting distribution in R.

* **15/01/2010** Lecture 1: Introduction to the course and par 2.3-2.5 in book (general concepts for lifetime distributions, failure/hazard rate).