[meric]

Prediction and forecasting are two different things in regression.

Regression is for predicting a dependent variable based one or more independent variables. It may or may not involve a time component.

"Regression analysis is widely used for prediction and forecasting, where its use has substantial overlap with the field of machine learning."

Exactly. Prediction and forecasting are not the same thing. That's why they had to state both.

I know your bio is impressive, but I've studied statistics for two years, specifically time-series forecasting and regression modelling. Predictions are a lot of the times not made in a temporal context. E.g. if you predict aspects of the population based on your observations in a sample.

>> Only if you don't understand science. Correlation is not causation.

I might not understand science as well as you do, but I have some modicum of ability in statistics, so there's no need to wave "Correlation is not causation." at me in every reply you make.

Prediction are not always made as a result of a causation.

[lutusp]

> Prediction and forecasting are two different things in regression.

"Prediction" and "forecasting" are synonymous, in both common usage and in statistics.

> Prediction and forecasting are not the same thing. That's why they had to state both.

No they said both so people who refuse to accept the fact that they're synonymous, won't feel left out in the cold.

http://en.wikipedia.org/wiki/Prediction : "A prediction (Latin præ-, "before," and dicere, "to say") or forecast is ..."

http://en.wikipedia.org/wiki/Forecasting : "Forecasting is the process of making statements about events whose actual outcomes (typically) have not yet been observed. A commonplace example might be estimation of some variable of interest at some specified future date. Prediction is a similar, but more general term."

http://dictionary.reference.com/browse/prediction: "Synonyms: forecast, augury, prognostication, divination, projection."

http://dictionary.reference.com/browse/forecast: "Synonyms: 1. foretell, anticipate. See predict. 3. project. 4, 7. guess, estimate. 9. forethought, prescience."

How can you go on like this about a word that literally means "to say before"?

> Predictions are a lot of the times not made in a temporal context ...

Yes, but those also represent the use of a set of observations (A) to assert a cause-effect relationship with some B. You objected that "prediction" wasn't about time, but it is. You also objected that prediction wasn't about arguing a cause-effect relationship, but it is.

> Prediction are not always made as a result of a causation.

Yes, and "literally" doesn't always mean literally -- sometimes it means "figuratively.":

http://dictionary.reference.com/browse/literally:

"1. in the literal or strict sense: What does the word mean literally?

4. in effect; in substance; very nearly; virtually."

The above is my favorite example of the perversity of arguing about word meanings, as though a word that usually means something, can be said to always mean that.

> I know your bio is impressive ...

Oh, please, let's not go there, all right? Nothing is more certain to undermine an argument than an appeal to authority -- either positive of negative (an in "I'm not an authority, but ..."). Science rejects authority -- the largest amount of eminence is trumped by the smallest amount of evidence.

[meric]

"In statistics, prediction is a part of statistical inference. One particular approach to such inference is known as predictive inference, but the prediction can be undertaken within any of the several approaches to statistical inference. Indeed, one description of statistics is that it provides a means of transferring knowledge about a sample of a population to the whole population, and to other related populations, which is not the same as prediction over time. When information is transferred across time, often to specific points in time, the process is known as forecasting."

http://en.wikipedia.org/wiki/Prediction#Statistics

It's not forecasting if it doesn't involve time, but it is if it does. That's why you can find evidence saying "Prediction == Forecasting" because that is true if there is a time component.