Survey of Multivariate Time Series Analysis Algorithms
The data was collected from metal oxide sensors on a significantly polluted patch in an Italian City. Find the Dataset here: https://archive.ics.uci.edu/ml/datasets/Air+quality
There are 15 attributes and the Time Series Analysis. Since the individual attributes are associated with a time stamp and the concentration of the gases at any given instance depends on the previous values of the same, we go on to perform a multivariate time series analysis.
We applied Coint Johansen Cointegration Test for checking stationarity of attributes in a Multivariate Dataset (similar to Dickey Fuller for Univariate Data).