Nate Silver Quotes

While data can only tell you what has happened in the past, it can in some ways give you a sense of what might be of interest to an audience in the future.

The best way to predict the future is to study the past, or prognosticate.

After all, the past is our only real guide to the future, and historical analogies are instruments for distilling and organizing the past and converting it to a map by which we can navigate.

The way that organizations and organisms anticipate the future is by taking signals from the past, most the time.

You want to evaluate future borrowers, but in order to train an algorithm that will help you identify future defaults, you have to train it and evaluate it on past data.

All too often when liberals cite statistics, they forget the statisticians' warning that correlation is not causation.

The best predictor of future events is probably past events.

You don't want to influence the same system you are trying to forecast.

If you have to forecast, forecast often.

The key to making a good forecast is not in limiting yourself to quantitative information.

Big data has been used by human beings for a long time - just in bricks-and-mortar applications. Insurance and standardized tests are both examples of big data from before the Internet.

I've become increasingly fascinated with social media to improve on traditional ways of preparing for and predicting the future.

I am incredibly bad at predicting the future; I am only smart enough to observe the present and listen to my intuition about tendencies.

I'm a lousy predictor of the future.

Probability is expectation founded upon partial knowledge. A perfect acquaintance with all the circumstances affecting the occurrence of an event would change expectation into certainty, and leave nether room nor demand for a theory of probabilities.

Prediction is very difficult, especially if it's about the future.

We have entered an era where the kinds of data and analyses that people run have gotten incredibly complicated. So you have researchers using sophisticated software programs that they probably don't understand but are generally accepted and everyone [in the field] uses.

The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data.

Coincidences, in general, are great stumbling-blocks in the way of that class of thinkers who have been educated to know nothing of the theory of probabilities.

By definition, big data cannot yield complicated descriptions of causality. Especially in healthcare. Almost all of our diseases occur in the intersections of systems in the body.

The bigger a data set that you have, the more polls, the more surveys that you have that people undertake, the more accurate your models are going to be. That's just a fact of data science.

The big mystery of Big Data is causation versus correlation.

How can you make sense of the future when you only have data about the past?

Correlations are not explanations and besides, they can be as spurious as the high correlation in Finland between foxes killed and divorces.

People who try to predict the future by extrapolating in a line of more of what exists - they are always wrong.