Economics: Financial Economictrics

Financial Econometrics
Student’s Name
Institutional Affiliation
Financial Econometrics
Financial Econometrics is a branch of economics that involves the study of quantitative problems that arise from finance. It consists of the integration of finance, probability, applied mathematics and statists. Some of the activities include risk management, building financial models, testing financial economics theory, capital asset pricing, portfolio allocation, hedging strategies, among others. Econometrics provides a tool that enables financial analysts to provide useful information about the issues arising from economic policies. Additionally, financial activities provide valuable theoretical foundation such as probability which as essential tools in solving quantitative problems in finance (Fan & Yao, 2017). Econometrics uses a linear time series that use stationarity, modelling, forecasting, auto-correction function, and dynamic dependence theories. Furthermore, the Auto-Regressive Integrated Moving Average (ARIMA) models provide s the description of a static stochastic process in terms of auto-regression (AR) and moving average (MA). ARIMA is one of the most used models when handling time series in econometrics (Fan & Yao, 2017). Furthermore, ARIMA is appropriate when a system is a function of a series of unforeseen or unobserved shocks.
The ARMA, AR and MA are all univariate descriptive models that are different from the multiple explanatory repressors models. The AR process model mainly describes a time series in terms of its lags. Where a sequence is modelled as its weighted lag and random shock term is referred to as innovation. The usability of this specification can be predicted based on its persistence and past in the series because AR is always correlated (Somarajan et al., 2019). The MA process model is applied where a time series is modelled as the weighted sum of the white noise values. White noise involves a sequence of identical and independent variables that are distributed randomly with finite variance and mean. Therefore, both AR and MA processes are stochastic, which means that their values come from a random distribution of probability. This distribution can be analyzed statistically, but they might n...