Time series
A Time series is a set of values {Xt},
that can be used to represent measurements taken at various sequential time
periods ‘t’ = 1,2,3,4,……..n.
Interestingly, time though is itself a
continuous variable, however us human beings make observations at specific
points in time and so it appears as discrete. Usually a single value or a
variable is analysed at a single point in time, which we know as uni-variate
analysis, even when multiple variables are recorded for that point in time, for
instance, hourly stock prices, daily weather conditions.
Usually, data are measured or defined for
equal time intervals such as 5 minutes, every hour, daily, monthly or yearly.
However, a time series is of no use if we can not study the relationships between the elements of time series. In order to understand and apply the relationships between time series elements to practical problems, we need to be aware of certain conceptual relationships.
The time series are applied based on certain concepts which need to be discussed if we have to move ahead and understand it better. Most of us must be aware of the term correlation in lay terms.
Interestingly, correlation as a term has statistical
connotations and usually understood to mean association between variables. In
specific terms it relates to a measure of similarity between two or more paired
sets of data. Correlation does not necessarily imply causation, though it might
suggest a possibility of a causal relationship.
Correlation concept is the basis of studying the time series applications. However, in terms of time series we are more interested in studying the concept of how correlation translates to auto-correlation, which will be covered in the next post.
Till then Happy STAT-ing 😊
