27.10.2014 Views

The Quick Count and Election Observation

The Quick Count and Election Observation

The Quick Count and Election Observation

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

CHAPTER FIVE: STATISTICAL PRINCIPLES AND QUICK COUNTS<br />

62 had a class of 10 or fewer students. More importantly, the grades of<br />

exceptionally good, or exceptionally poor, students will have quite a<br />

different impact on the average grade for the entire class. In a small<br />

class, those “outlier” grades will have a big impact on the overall distribution<br />

<strong>and</strong> on the class average; they will skew the results of the<br />

grade curve. But in a larger class, the impact of any individual exceptional<br />

grade will have a far smaller impact on the average mark for the<br />

whole class.<br />

<strong>The</strong> practical implication of the grade distribution example is simple: as the<br />

amount of data (number of observation points) increases, the impact of any<br />

one individual data point on the total result decreases.<br />

A second statistical principle that is vital to quick count methodology is known<br />

as the central limit theorem. This axiom holds that, the greater the number of<br />

observations (sample points), the more likely it is that the distribution of the<br />

data points will tend to conform to a known pattern. A class of 500 physics students<br />

in Brazil will produce the same grade distribution as a class of 300 literature<br />

students in France, even though the marks themselves may be different. In both<br />

cases, most of the data points will cluster around the average grade.<br />

<strong>The</strong>se two statistical axioms – the law of large numbers <strong>and</strong> the central limit<br />

theorem – work in conjunction with each other. Together they indicate that:<br />

<strong>The</strong> greater the number<br />

of observations we<br />

have, the more likely<br />

it is that we can make<br />

reliable statistical predictions<br />

about the<br />

characteristics of the<br />

population.<br />

1. the larger the number of observations (sample points), the less likely it<br />

is that any exceptional individual result will affect the average (law of<br />

large numbers); <strong>and</strong><br />

2. the greater the number of observations, the more likely it is that the<br />

dataset as a whole will produce a distribution of cases that corresponds<br />

to a normal curve (central limit theorem).<br />

A general principle follows from these statistical rules, one that has powerful<br />

implications for quick counts: the greater the number of observations we have,<br />

the more likely it is that we can make reliable statistical predictions about the<br />

characteristics of the population. However, it is absolutely crucial to underst<strong>and</strong><br />

that, for these two statistical principles to hold, the selection of the cases<br />

in the sample must be chosen r<strong>and</strong>omly.<br />

R<strong>and</strong>omness<br />

A sample can be thought of not just as a subset of a population, but as a miniature<br />

replica of the population from which it is drawn. <strong>The</strong> population of every<br />

country can be considered as unique in certain respects. No two countries are<br />

the same when it comes to how such characteristics as language, religion, gender,<br />

age, occupation <strong>and</strong> education are distributed in the population. Whether<br />

an individual possesses a car, or lives in a city rather than a town, or has a job,<br />

or owns a pet dog contributes to the uniqueness of personal experience. It is<br />

impossible to produce a definitive <strong>and</strong> exhaustive list of every single feature

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!