A View of Survey Results: the 2016 Philippine Elections



Assuming the survey responses were gathered appropriately (methodologically compliant), then the estimates of prevalence can be interpreted meaningfully in terms of an electoral race, provided the percent standard error is considered.

Bobbi tiglao also posits that another crucial parameter needs to be estimated and included in the calculation of voting preference: that of machinery generated votes, which should be added to the survey responses.

Now since the two quantities are additive, we can analyze the survey preferences before or after the machinery generated votes are included, and the results will be the same. It is more intuitive, though, to consider it at the end when the quantities are compounded into a single measure.

Let us now go to the final estimates (survey responses plus machinery generated).


Source: Tiglao, see FB posts

If we use the SWS declared standard error */- 6 percent, then the following conclusions are warranted:

1. there is seemingly a bimodal distribution, top position or rank, and bottom position or rank.

2. with standard errors, a range of values, called confidence intervals [let's call it for now flux intervals], can be calculated to show how either the survey measures of voting preference, or the compounded preference with machinery delivered votes will fluctuate up and down.

3. within the flux intervals, the candidates with highest “top” votes are “statistically” tied; the same goes for the candidates with lowest “bottom” votes, to wit:

The upper tail of Poe's 32 percent plus the 6 percent of standard error equals 38 percent, which well includes Binay's 34 percent. The lower tail of Poe (32 percent minus 6 percent of standard error) will include the two “bottom” candidates Duterte and Roxas

So, what's the bottom line? The actual results are still a toss up. Until later updated with attending changes, we now have Poe and Binay leading; both Duterte and Roxas are at their very heels.

Comments

Post a Comment

Popular posts from this blog

Population Growth and SocioEconomic Development

Labor has ever been central to issues of production. Indeed, Marxists assert that it is the primary factor of production. Labor comes from the demographic stock, population. Recently, social scientists have again resurrected the specter of continued, if not worsening, prospects of poverty in the Philippines, in spite of projected growth of the economy. Their contention is that demographic growth will serve as stumbling block to Philippine development. Students of Economic Planning, let me hear your views on the matter. Students of Sociology of Socio-Political Change, likewise. Please consider this as a sort of written examination. Your posts should reflect your theoretical position, as well as your empirical observations. Citations are most welcome. Due date for your posting is 5 p.m. on September 20, 2008.
Read more

The Religion of IT

The assigned module for discussion is “The Religion of Computers” by David S. Bricklin, found at http://www.atariarchives.org/deli/the_religion_of_computers.php Your task(s) are (1) to reduce to some 3 sentences paragraph the essence of Bricklin’s argument, and then (2) to write a critique, where you state whether you agree or disagree with his basic arguments. Although Bricklin writes about computer technology, you may extend his argument to mobile communications technology, such as the proliferation of cell phone models, and so on. In Youtube, see the clip "Colossus (the prequel to the Terminator?) It can add visual dimension to this learning module
Read more

The Uses of Conflict

Students of Sociology of Development should write a scholarly critique of "The Functions of Conflict in the Context of Schooling" found at http://www.newfoundations.com/EGR/FunConflict.html Your comments are due on July 22, 2009
Read more