"People can come up with statistics to prove anything... 40% of people know that!"
So which statistics should we trust?... Are there any statistics we can trust?
One of the problems comes from interpreting complex data and simplifying it for public consumption. Another comes from looking for evidence to support our ideas, which may be conscious or sub-conscious confirmation bias. And doesn't research funded by one interested party or another call into doubt the impartiality of that research?
It's not surprising that Homer (and most of the rest of us) distrust science and statistics.