Real-world data really matter

How Scientists Really Reason: Scientific Reasoning in Real-world Laboratories

Modeling Real-World Data Sets

Traditionally, the performance of algorithms is evaluated using worst-case analysis. For a number of problems, this type of analysis gives overly pessimistic results: Worst-case inputs are rather artificial and do not occur in practical applications. In this lecture we review some alternative analysis approaches leading to more realistic and robust performance evaluations. Specifically, we focu...

Measuring Real-World Data Availability

This paper examines how server marketing claims of high reliability (e.g., 99.999%) stack up against real world data measurements. Our goals were to: measure discretionary NFS data availability, compare data availability between standalone and clustered systems, and draw some conclusions about best practices for customers. We explain our methodology for measuring, filtering, and categorizing av...

Does Size Really Matter?

ver since its discovery by Banz (1981), the size effect has remained an enigma. Although the empirical fact that firms with low market values earn higher returns than firms with high market values is beyond dispute, a theoretical explanation of this regularity has eluded the profession for almost 15 years. Because this empirical regularity is almost universally interpreted as evidence that smal...

Does evidence really matter?

When I was in my mid-40s, I took up golf and quickly realized that it is a challenging game. More than 10 years later, after many games of golf and several visits to golf schools, I still consider it a good day if I break 100 over the course of 18 holes. My only consolation is that I am not alone: according to a few golf books that I have read, fewer than 10% of those who golf will ever legitim...