In science, this is called committing a Procrustean crime. Wikipedia explains a Procrustean solution as being:
"the undesirable practice of tailoring data to fit its container or some other preconceived stricture. A common example from the business world is embodied in the notion that no résumé should exceed one page in length.
In statistics, instead of finding the best fit line to a scatter plot of data, first choose the line you want, then select only the data that fits it, disregarding data that does not, so to "prove" some point you are making. Its a form of deception that rhetoricians make so to forward their own interests at the expense of others. The unique goal of the Procrustean solution is not win-win, but rather that Procrustes wins AND the other loses. In this case, the defeat of the opponent justifies the deceptive means."
Sound familiar? Seems to me that this was what the climate scientists were doing. They had a model of global that they knew had to be right. Just too bad that some of the data didn't quite fit in with the model. So they just did what Procrustes did.
Interestingly there is actually a Procrustes analysis of climate data. Even though the context is a little different. :)
There is a nice simple write up about theoretical thinking here.... something even I can understand; even though the climate scientists seem to have difficulty with these concepts.
"The second reason you can't prove a theory true is that there is never just one theory that fits the facts. A theory is really just a narrative. A tale that explains. But stories can be told very differently. In a sense, there are always an infinite number of theories that fit the facts."
But for climate science, we are told repeatedly that the science is settled. Theory proven.
Procrustes would have been proud.