Now that we know how to characterize a probability distribution, we can use that information to calculate other familiar measurements, like averages and more.
While Probability Density Functions for continuous random variables are useful in describing many statistical processes in nature, they’re not much use when analyzing polling data. In this post, we’ll introduce the discrete version of PDF’s and use it to describe some previous examples.
Now that we have some experience with calculating probabilities, we can start developing more sophisticated tools for describing and analyzing statistical properties. While some of what we’ll discuss today doesn’t necessarily lend itself well to polling, we’ll cover all types of probability distributions, just to be complete.
In the last post, we introduced the basic concepts of probability, as well as the events for which we calculate those probabilities. In many statistical calculations involving polling data, we’re interested in the probabilities of combinations of multiple events. We’ll talk about correlations and other advanced concepts soon, but today we’ll start off with some simple relationships.
This is the first in a series of posts about the fundamental rules behind probability and statistics. If the relationship between statistics and polling isn’t completely clear yet, don’t worry, that will come soon.