The Washington Post and its laughable polling conclusions regarding the Palin video.

With the following headlined story regarding the Washington Post's recent PPP of Sarah Palin and the presentation of her video, we show why such liberal polls are more often than not ludicrous and wholly without merit. In fact, the results of the recent Public Policy Poll is laughable and we prove our point in the following:

Tom Jensen / Public Policy Polling: Palin shoots herself in the foot — Sarah Palin might have really squandered an opportunity to improve her image last week. — Despite endless discussion in the wake of the Arizona shootings about whether Palin might suh any responsibility for fostering an atmosphere conducive to such an attack. . . . . . . .

Editor's notes: here is the heart of the article which reviews Palin's failure to advance her presidential status:

Despite endless discussion in the wake of the Arizona shootings about whether Palin might bear any responsibility for fostering an atmosphere conducive to such an attack, 64% of Americans firmly say Palirn has no culpability to just 26% who think she is partly to blame. Even among Americans with an unfavorable opinion of Palin- the vast majority of them- most don't think she should be getting the shooting pinned on her in any way, shape, or form. . . . Beyond that there are a significant number of voters, even beyond Palin's small group of partisans, who think she gets treated unfairly by the media. 45% of voters in the country think Palin gets a bad shake from the press to 47% who think that she is treated fairly. . . . . [in the end, the survey purports to show that Palin's video was a serious mistake. ] see the article.

From the PDF recording the details of the PPP poll (PPP is a part of the very left leaning Washignton Post - so lets be real about who is doing the survey), we make these observations:

The poll claims to give us a national opinion of the Palin video with a margin of error of 3.9%. The actual number interviewed was just 632. There are 308 million of Americans. In this case, the "margin of error" pertains only to the internal workings of the poll and has nothing to do with the measured opinion of the American people. How could it?

We make our case that it could not:

Understand the polling was done by computerized auto call. Consequently, it made no effort at verifying the demographic influences of the survey. Understand that in the end, the "margin of error" is a statistical assumption as the result of an effort to quantify variables effecting the survey. The authors of the survey admit to serious difficulties in the effort to account for all influences effecting the poll, resulting in the possibility of "error [in the survey results] that is more difficult to quantify." In other words, the margin of error could be greater than specified, even much greater. In fact, we would argue that the admission, itself, is an indicator that the margin of error is more than claimed and, thus, an impossible equation for the purposes of validating this survey.

Unnamed variables in this survey: one, 308 million minus 632 were not interviewed. Understand that if you rounded down the percentage represented by dividing 308 million into 632 individuals, that number would be "zero." Secondly, none of those surveyed were necessarily "likely voters." Non-voting Americans should have no place in an opinion poll about anything relating to politics. Third, only 23% of those polled claimed to be "Independents" although "Independents" consistently represent 40% or more of the voting population.

Conclusion: this particular poll is useless in depicting the measured opinions of the American voter. In fact, there is no reason to believe that the American voter was even interviewed.

J Smithson

1 comment:

  1. Yet Smithson swears by the Rasmussen poll because it tells him what he wants to hear. Sorry, Rasmussen has been proven a fraud and statistically inaccurate.

    "Every election cycle has its winners and losers: not just the among the candidates, but also the pollsters.

    On Tuesday, polls conducted by the firm Rasmussen Reports — which released more than 100 surveys in the final three weeks of the campaign, including some commissioned under a subsidiary on behalf of Fox News — badly missed the margin in many states, and also exhibited a considerable bias toward Republican candidates.

    Other polling firms, like SurveyUSA and Quinnipiac University, produced more reliable results in Senate and gubernatorial races.

    The 105 polls released in Senate and gubernatorial races by Rasmussen Reports and its subsidiary, Pulse Opinion Research, missed the final margin between the candidates by 5.8 points, a considerably higher figure than that achieved by most other pollsters. Some 13 of its polls missed by 10 or more points, including one in the Hawaii Senate race that missed the final margin between the candidates by 40 points, the largest error ever recorded in a general election in FiveThirtyEight’s database, which includes all polls conducted since 1998.

    Moreover, Rasmussen’s polls were quite biased, overestimating the standing of the Republican candidate by almost 4 points on average. "

    ReplyDelete