Time Series Analysis Advantages And Disadvantages

996 Words4 Pages
The crucial need for studying, analysing and monitoring sequential information arising in several area of engineering and science, and from various type of problems has been one of the most challenging issue over the past two centuries. In order to handle these concerns, time series analysis has become a key tool to deal with data that are usually a time series, generated by a dynamical system, or a sequence generated by a univariate spatial process such as biological sequences. In this quest and by relying on statistical modelling techniques, some of the main goals of time series analysis are to understand and reveal the dynamic driving the observed time series and to forecast future events. Thus, the requirement of an appropriate time series…show more content…
These classical approaches however present some drawbacks. For example, in order to make prediction about the future, one would like a model where there is no restriction on how far we can go back in the past to gain inside information, which is not the case for the above mentioned models where the prediction of the future must be based on a finite time horizon into the past. Other challenges we face are the difficulty to incorporate prior knowledge into the model and handling multivariate…show more content…
In this framework and as it will be our case, what is often under consideration are partially observed dynamic systems driven by probability density functions, with one or more latent processes changing and interacting over time where only part of them or their linear transformations are observed. This methodology has been extensively applied on several real life examples arising from financial, engineering and biological sectors among others. For example, the mortality curve in insurance that describes how the mortality rate as a function of age changes over time and the implied volatility as a function of time to maturity and the option's strike price in financial sector. As for the example of observed process driven by another latent process, one can consider for instance the observed interest rate curve that can be driven by the unobserved curvature and level
Open Document