The days of statistics are numbered.
Statistics as a mathematical field was invented to turn imperfect information into usable generalizations. In an age of door-to-door censuses, phone surveys, and weather stations, it let humans make strong predictions about their world.
The impending rise of ubiquitous sensors detecting everything from weather to traffic to human relationships will supplant the need for statistics. Why sample data when you can have it all?
That said, statistics won’t entirely disappear. It will still be useful in making sense of experimental data since lab experiments simulate only a single case, and others may not even exist to be monitored. It will also still be useful in situations in which the extra cost of obtaining ubiquitous data is not worth the extra accuracy achieved over traditional statistical and sampling methods. Yet, even in this case, as the infrastructure for ubiquitous data is laid out, it will become more and more practical and economical to start using it.
I think you make quite a bold claim, yet I disagree with the core argument of your claim. If anything, a greater compilation of data will in fact make statistics more necessary. According to Wikipedia, statistics is:
In support of my claim, statistics is the science of making sense of data: data collected, data compiled, and data compared. I do not doubt we are entering an era of “ubiquitous data”, but do believe statistics are at the core of understanding information, and necessary for the describing trends on which we will base our “intelligent” algorithms.
How’s that for my best Oxford voice?
Outstanding, chap. I thought Simon Schama himself was leaning over my shoulder.
I spoke too generally. Statistics is a much broader, deeper field than I presumed. In retrospect, it is certain methods within the field of statistics that will become obsolete, methods that make up only a small part of the entire field. This specifically applies to methods of error correction.
Though even with ubiquitous data, where there is no need to extrapolate sample data to represent a population, extrapolation methods will still be useful for applying data inferences forward or backward in time.