Data is essential in any analysis, and keeping it tidy and well-structured is even more important. Every next step will take you down the wrong path, if your initial data structure and format was not well-designed. Hence, it is worth taking an notice of some best practices.
Time series analysis provides an insight into the nature of the phenomenon represented by the series of observations and suggests how to forecast or to prediction future values.
Before diving into the detailed analysis of business problems or data investigation, we will define a number of important concepts through a series of briefs.
These briefs will aim to explain the basics and clear the pathway for further discussions.
Variance surrounds us. Despite our desire to have the same thing every day, we will face a slight variation of something we want to encounter again.
A mathematical definition of the variance is quite straight forward:
it is a measure of how far are the data values are located from the mean.
Biases are something to be aware of in any analysis.
Early in our life we start to shape our comprehension of the world through our own perception. We tend to see the colours that suit and soothe us. We look for things that make sense quickly and tend to avoid those that take time. We are interested in something that “feels right” and ignore anything that causes some level of discomfort.
All of these are just a result of our views, opinions or putting it simply, are our biases.