Fundamentals of Interpreting Test Results
podcast episode with speaker Fred Schenkelberg
What role does ‘wishful thinking’ play in interpreting reliability test results? Hopefully, none. A well-designed test will likely provide meaningful results. You and your team may not like the results, yet the results will be clear.
From success testing to design of experiments based on accelerated life testing, from shipping and storage testing to ongoing reliability testing, we do a lot of testing. To create tests and results that are meaningful, we need to both design and execute the test well, then, most importantly, interpret the results accurately.
The often-overlooked process of making assumptions is our focus for the discussion. What assumptions are we making, and how differences from those assumptions will impact how we may interpret the results? Let’s discuss a few cases and highlight what to consider, assume, and check as you prepare to interpret your test results.
This Accendo Reliability webinar was originally broadcast on 12 October 2021.
- Social:
- Link:
- Embed:
To view the recorded video and PDF of slides, visit the webinar page.
Related Content
Wishful Accelerated Testing episode
Issues with Single Stress Testing episode
Next Steps after Surprising Test Results episode
Ways to Partner with Test Engineers episode
Use FMEA to Design for In-Process Testing episode
Collecting and Analyzing Your Field Data
Let’s explore where the data comes from and how to prepare for analysis. Plus, let’s discuss some ways to look at your data initially.
Time to Failure Data Analysis for Your Factory Equipment
For repairable items, the mean cumulative function and associated plots provide you with an estimate of the effectiveness of your repairs.
Reliability Data
We will discuss the pros and cons of various sources. Plus, let’s examine a few ways to use simulations or models.
Fundamentals of Weibull Analysis
The Weibull distribution is a versatile tool to analyze time to failure data. Like any tool, it could be wielded well or not so well.
Fundamentals of Field Data Analysis
The design is done, the assembly process is working, now we can focus on answering the question: is the product hitting reliability targets?
Weibull Probability Plotting
Data is only as useful as the information you derive. So would you like to take your Weibull probability plotting skills to the next level?
Overview of Life Testing in Minitab
Minitab itself has many reliability functions available; this presentation covers the basics, including distributions, censoring, and fitting.
The Survivorship Bias Principal
This webinar examines an important perspective. Its’ so simple and has made many heroes in the data analysis world since Abraham Ward.
So what is up with this ‘Bayesian’ analysis stuff
Some of you may have heard of ‘Bayesian analysis.’ You may think this is something fancy that only universities do.
Reliability Analysis … now what? Part 2
Let's take a closer look at the concept of likelihood and it's role in an MCMC analysis. A powerful tool for data analysis.
Reliability Analysis … now what? Part 3
This webinar is about how we use this thing called Markov Chain Monte Carlo Simulation (MCMC) to create this ‘posse.’
Reliability Analysis … now what? Part 4
We show you how to get your computer to help you give useful reliability information to your boss, manager, director, or whoever.
Fundamentals of Interpreting Test Results
To create test results that are meaningful, we need to both design and execute the test well, then, interpret the results accurately.
How to Take the Guess Work out of Expert Judgment
there are ways you can suck out information from a group of experts in a quantifiable and remarkably accurate way.
What do you see in a ‘Probability’ Plot?
A Weibull plot is a really useful way of quickly ‘looking’ at data and being able to ‘see’ really useful things.
What is WeiBayes Analysis?
WeiBayes is useful, and there are quite a few catches. Interested in learning about Weibayes analysis? Join us for this webinar.
Using Monte Carlo Simulation
Sometimes the equations we need to model reliability are just so complicated that we simply avoid them. Let's use Monte Carlo instead.
Leave a Reply