Bless his heart… Mississippi Democrat Party chairman Bobby Moak is all a-Twitter this morning, promoting a Washington Post online survey that says his candidate of choice – Hillary Clinton – is within two points of Republican nominee Donald Trump here in the Magnolia State, painting Mississippi a toss-up.
Moak’s mass email/Tweet blast late Tuesday night also showed his glee, proclaiming, “Your message is working! Poll numbers out this week show that Mississippi is on the verge of turning into a swing state, one of 19 to close to call.”
Trouble is this “poll” Moak is referencing is limited in scope to such an extent that even the Washington Post gave a disclaimer of sorts on its own methodology.
As Scott Clement
, the Post's polling manager, writes, “The Post-SurveyMonkey poll used an online-based sampling methodology that differs from previous polls by The Washington Post… The new poll was conducted online as part of SurveyMonkey’s 2016 Election Tracking project, which recruits respondents from the large number people who take polls on the company’s do-it-yourself survey platform…”
He went on to write, “…the probability of any given voter being invited to a SurveyMonkey is unknown, and those who do not use the platform do not have a chance of being selected.”
Essentially what Clement is saying is that if you didn’t use SurveyMonkey already, you weren’t invited to take this presidential election poll, meaning the sample of actual voters and the probability of them voting are both unknown. I’d argue that the only toss-up here isn’t between Clinton and Trump, but in who actually took the survey and why.
Clement goes on to note, “The Post has generally avoided citing results from non-probability Internet-based surveys such as SurveyMonkey, as it is impossible to draw a random sample of Internet users, and random selection is a widely accepted standard in drawing representative samples of any population.”
So Democrat chairman Moak, who rushed to his computer to peck out a memo to the yellow dog faithful and send a tweet or two about how far Hillary Clinton has come in Mississippi, is hanging his hat on a limited online survey with questionable methodology. Saying this is a “poll” in the traditional sense of the term is even a stretch of the imagination.
Sheer common sense would tell you there is no possible way Clinton is within 2 points of Trump in the reddest state in the union. For the guys at the Washington Post to allow such skewed numbers to come out of their newsroom and pass them off as factual is a head scratcher. The Post’s Chris Cillizza normally has a better read on these things. Although it makes a nice headline, it simply isn’t based in fact, especially in Mississippi.
But, after all, as Clement points out in his article, this poll was more about tracking attitudes at a low cost than using more reliable, traditional methods of polling: “The Post-SurveyMonkey survey gave The Post an opportunity to gauge political attitudes on a far greater scale than would have been financially and practically feasible using traditional, probability-based polling.”
If voters of Mississippi really want to see how the race in this state is shaping up, I’d suggest studying both the recent Reuters/Ipsos
poll which shows Trump up by 29% and our YP/Magellan
poll showing Trump leading by 14%.
Posted September 7, 2016 - 1:11 pm