Multiple regression is a technique used to figure out linked variables as they relate to other variables. For example, an economists might use multiple regression to figure out if being more educated makes one more libertarian. To do that, they would want to look at a large group of equivalent people. Ideally, you want to compare a one person that has all the same traits as another except differing in views on liberty and one other variable. Then one can see if that variable has any effect. To do that you would have to try to control for all factors of relevance. This might include: income, race, number of parents, church attendance, etc. For the record, more education looks like it makes people more libertarian.

Bryan Caplan wants to know if Climate scientists have regressions showing Carbon and Warming are linked. This might not exist, as warming has paused for the last decade. Couple this with the fact that scientists are reluctant to release the data and some of it has been destroyed (a good general rule is not to trust anyone who is not transparent). But Caplan posts a valid question, where is the regression:

The baseline regression I suggested – temperature on CO2 and a linear time trend – is one that any competent first-year stats student should take seriously. It’s a standard way to see if your story that “X is making Y go up” is superior to “Y just seems to be going up.” Why add other trending variables? To see if the data are more consistent with your story than random made-up stories. Inquiring minds want to know.