Figures don’t lie, but liars figure – what to know about polls #polls #statistics

I’m bombarded by polling results that make cheap TV (that’s my opinion – I have no unique insight into TV. ) Roll out some results and ask a bunch of talking heads to comment. The more outrageous, the better the ratings, and the more likely that talking head will be invited back – maybe for money, maybe for a chance to push their latest book.

Statistics have bedeviled us since this guy started probability theory in 1713

Polls can be done scientifically. Even simple questions can be tricky to ask. For example, Do you prefer Candidate # or Candidate % ? There’s a human tendency to select the first option offered (in various sorts of questions, not just about politics.) If you are seeking information, you must ask half the people if they prefer Candidate # or Candidate %, and the other half if they prefer prefer Candidate % or Candidate #.

[You may] assume that the pollster is trying to collect accurate data. Are there any other purposes for polls and surveys, particularly in the way their results can be used? Of course there are. Learning something is not necessarily the reason many polls are conducted. Consider who hired the pollster, and why they were hired.

All of the complications that can skew the results of a survey or poll are problems that knowledge-seeking survey designers have to be aware of and account for; but to the spin doctor, or the political campaign, or the think tank, or anyone else in the propaganda business, they comprise a toolbox of nifty little tricks to get the data to say what they want it to say. Primacy bias is just the beginning. skeptoid

You don’t have to be cynical or paranoid to know the world is full of trickery. Check out more polling errors (or ways to spin results) by clicking on this Skeptoid article and podcast here. Primacy bias, acquiescence bias, context effect, sampling bias, mode effect, social desirability… all factors that affect a poll’s results. There’s a reason conducting sound, scientific polls requires professionals. Professionals seeking knowledge, that is.

Personally, I would add that I am suspicious of any presentation that tries to make me angry or fearful. Also, as an engineer, I learned to look twice at data that confirms my preference or my opinion, because no matter how satisfied I may feel in the short-term, reality will win in the end. Reality is important to me.

With the political season heating up in the USA, this is a good time to stop and ponder the news you consume, and not allow it to crawl into your head unexamined.