Overview Sometimes, regardless of how carefully we conduct testing to gather data, we end up with results that just seem wrong. This could be a sign that we have stumbled upon an earth-shattering breakthrough that will change the world’s understanding of fundamental physics1 …. or, it’s possible that a mistake in the testing led to bad data. This column will discuss a few … [Read more...]
About the Author
Ross Wilcoxon
Ross Wilcoxon is a Principal Mechanical Engineer in the Rockwell Collins Advanced Technology Center. He conducts research and supports product development related to component reliability, electronics packaging and thermal management for communication, processing, displays and radars. Prior to joining Rockwell Collins in 1998, he was an assistant professor at South Dakota State University.
Probability
INTRODUCTION After a couple of decades in the industry, I have observed that a number of experienced engineers can be intimidated by the topic of statistics—these columns will attempt to reduce the level of intimidation. While I have been interested in statistics for a few decades now, I don’t claim to be an expert. I will do my best to get things as right as I can, as well as … [Read more...]
Is That Normal?
Introduction These columns on statistics began by describing the field of statistics as using the mathematical laws of probability to deal with data uncertainty [1]. Many statistical tools developed to apply probability do assume that data are drawn from a normally distributed population, in which the probability distribution function, f(x), of a population follows Equation … [Read more...]
Oscillating Heat Pipe Thermal Performance and Stability Limits
A heat pipe is a closed system that contains a saturated fluid. When heat is dissipated in one region of the heat pipe, liquid in that area boils or evaporates, which produces vapor that moves to another area in the heat pipe where it condenses. The condensed liquid then returns to its starting point to transport energy from the heat input region(s) to the heat output … [Read more...]
Statistics Corner: Modifying Sample Size
ABSTRACT Reliability verification often requires that a specific number of components be tested to a predetermined level of testing to demonstrate that none of the samples fail. This article describes a statistical approach for justifying the use of fewer samples by subjecting them to a more severe level of testing. BACKGROUND Reliability verification often includes … [Read more...]
