Archive for the ‘Research’ Category
In Parts 1, 2 and 3, we looked at statistical measures of datasets that were purely one-dimensional in nature, i.e., all the observations constituting the dataset were of the same type. Examples of such datasets are the time elapsed between eruptions of the Old Faithful Geyser
This short blog is in response to a recent support ticket querying whether particular domains display significant differences in terms of the ratio of referring subnets to referring IP addresses. We were asked what a “normal” value of this ratio could be.
In Parts 1 and 2, we have looked at the definitions of correlation, population and sample size. In this part, we will go through the essentials of the mathematics involved. Before we can proceed any further, however, we have to define certain fundamental statistical concepts.
Statistical Measures of a Data Set
In this section, it will be assumed that… Continue reading
(This is a guest post by Barrie Smith. His observations and insights are his own.)
I have recently been keeping a tab on Google page 1 results for “Payday Loans” – a search term historically showing results of websites ranking having used spammy, dodgy and/or underhand link building techniques.
Even in the year 2013 – more than 12 months after the Google Penguin algorithm update was… Continue reading
In Part 1, we looked at how correlation can be used to examine relations or associations between variables in a data set. We described the different types of correlations, and presented the advantages and disadvantages of the correlation technique to analyse data. This part will attempt to ease the reader into methods of quantifying correlation.
Up till now, correlation has been defined as a measure of… Continue reading