Let's say I was collecting data on something for about 200 years. The first 100 or so aren't very reliable, but let's give me the benefit of the doubt and say I have good, hard data for a 200-year period. I now turn around and use that 200 years of data to predict both forwards and backwards--sometimes as much as a million years in either direction. Is that good science or is it craziness?
Before you answer, consider that the Global Warming camp is doing just that. When pressed they openly admit no data or hard evidence to support any claim that goes beyond the late 19th century, but that doesn't stop them from scare tactics such as declaring that we're nearing the warmest point in the last million years.
Don't get me wrong. I'm not denying any scientific evidence that the so-called greenhouse gases might be contributing to the planet getting hotter. I'm merely asking that we stick with science and not jump to wild speculations designed to grab headlines and secure more funding.
Check out JunkScience.com for more information on the lack of scientific method in many of the popular claims you've seen on TV from people purporting to be scientists.