Understanding Causality and Contagion in Economic Analysis

1. Elaborating on causality and causality in econometrics

Causality is being termed as a genetic connection of phenomena in which one thing (the cause) within certain conditions can influence some other things (the effect). The core of causality is identified as the creation and determination of specific phenomenon by another factor. Therefore, causality is also considered a distinct approach that is differed from various other kinds of connection. For example, the simple chronological series of phenomena that are influenced by regularities of accompanying processes. For example, a pinprick influences pain in the body. Brain damage could be activated as a mental illness (Brooks, 2019). Furthermore, it is evaluated that causality is also called an active relationship in which a relationship offers something new in the life that transforms possibility into actuality. In addition to that, a cause is also considered as an actor as well as the primary thing about the effect. It would be a parody of justice in which if there is certain punishment then a crime has been performed. Therefore, causality can be termed as terminology that defines cause and effect relationship.

As per Drakopoulos and Torrance(1994), causality in econometrics is being termed as a relationship between the approach of causality and modern economics. It seems that econometrics has become the new rising subfield in the context of economics. It results in a statistical concept of causality. It can be stated that the importance of the statistical aspect of causality is significantly enhanced due to the increased importance of predictions within economics. It is found very useful in the assessment of high probability in different economic conditions (Stock and Watson, 2015). In this context of economics, this approach helps to determine the change in properties of subject matter due to change in a specific model as a result of new observations. In some conditions, causality in econometrics is defined as an idea of non-necessity of a chronological time ordering associated with cause and effect.

In the context of econometrics, there are several points addressed for determining the relationship between different variables. The first point is termed as understandable insofar, and it is also distinguished with causal connections concerning statistical correlations. Apart from that, the second point is addressed as concerning time sequence (Magnus and Neudecker, 2019). This approach is adopted by asserting a static functional relationship between two or more variables points. Further investigation of Amini, Cont and Minca (2016) has found that if there is some alteration identified in one variable, then there are some other variations addressed in another variable. This approach has been found very useful for conducting a scientific investigation. In the context of econometrics, this approach offers significant assistance for analysing recent economic trends and changes in the business environment due to alternation in business economic factors. This is because every business entity has to manage different current market trends for influencing the effectiveness of management decisions. In the context of the current business environment, it has addressed that statistical analysis is being identified very useful for evaluating different business trends along with cause and effect relationship. For example, an organisation uses sales trends in different business conditions in which business entity examines changes in sales volume due to alteration in different business strategies so as statistical analysis is being identified as an excellent tool for analysing several facts and figures about current economic trends (Brown, Trautmann and Vlahu, 2016). It has addressed that causality assists managers in determining different economic factors while determining different business policies and procedures as per the current market trends.

2. Elaborating on contagion

As per Forbes and Rigobon (2002), contagion has been addressed as the most effective terminology within economic market trends. The contagion effect can be defined as the transmission of the shock of one country’s economic market to another country’s economic market. This approach has found it very useful for analysing the cross-market relationship within the global business environment. This kind of situation is addressed when two markets identify a high degree of movement during stable market conditions (Anand, Craig and Von Peter, 2015). Therefore, it has addressed that this cross-relationship can be termed as contagion when there is significant increment addressed within in cross-market movement after certain market shock. There are several empirical pieces of evidence related to contagion. Therefore, the first methodology is focused on applying the cross-market correlation coefficient that is termed as a very useful straight forward approach for testing contagion. These tests have found it very useful for measuring the correlation in returns between two markets within a stable period and then examine the significant increase in the correlation coefficient after the shock. Further investigation has found that the second is focused on analysing market movement is performed by using ARCH or GARCH framework that has found very useful in order to estimate the variance-covariance transmission mechanism within two countries (Magnus and Neudecker, 2019). This approach has found it very useful for determining the stock market crashes and its transmission from that country to another. Furthermore, the third method is focusing on cross-market linkage tests that are used to evaluate changes in co-integrating vector among different market over a long period. It determines several factors that are playing a vital role in increasing cross-market relationships such as greater trade integration or higher capital mobility. In addition to that, it is deemed that the last section is focused on evaluating the final series of papers that are examining international transmission mechanism for measuring different factors that are used to identify different factors associated with the financial crisis.

3. Discussing the main features of the ways to test for possible contagion effects

For testing possible contagion effects, a feature of new tests is determined below through evaluation of different financial crisis and cross-market relationship can be performed by conducting tests of contagion based on alternative higher-order movement (Frey, Martin and Tang, 2010). In addition to that, it seems that the descriptive statistics have found very useful for highlighting the importance of modelling risk within the financial crises using higher order moments. For formalising the cross-market relationship between risks along with the variations of the distribution of returns, a portfolio model is used for conducting different tests (Magnus and Neudecker, 2019). This model is going to determine the extension of the mean-variance framework in which an expected excess return on assets is going to be expressed in terms of risk prices. These prices are being termed as essential functions of the risk preferences of investors and risk quantities which are a function of higher order conditional moments including skewness and skewness:

1. Generalised normality: In this section, new tests of contagion are carried out through higher-order movement. This is because it is essential to specify a non-normal multivariate returns distribution. Therefore, these new tests are considered to extend the previous univariate class of normal exponential distribution.

2. Application of contagion tests: Tests of contagion is developed by considering two types of studies. The first approach is associated with the Forbes and Rigobon (2002) contagion test which is playing critical for testing changes in correlations. Apart from that, the second is a contagion test based on changes in skewness. In addition to that contagion, a test is performed concerning changes in correlation in which adjustment within a coefficient of variance is performed. Furthermore, the assessment of changes in Coskewness is also performed. This test is mainly found very useful for identifying the significant variations within skewness between the period of financial crisis and pre-crisis period (Amini, Cont and Minca, 2016). It is identified that this test is worked on finite sample properties in which pre-crisis sample periods are relatively large as compared to crisis sample periods within the tests. Therefore, the approach of finite sample distribution properties of contagion test statistics is considered concerning the null hypothesis. For enhancing the effectiveness, a chi-squared asymptotic distribution is also performed with one-degree freedom as the continuous line basis. Therefore, findings of asymptotic distribution are offered an appropriate approximation within the finite sample distribution.

REFERENCE

• Amini, H., Cont, R., and Minca, A. (2016). Resilience to contagion in financial networks. Mathematical finance, 26(2), 329-365.
• Anand, K., Craig, B., and Von Peter, G. (2015). Filling in the blanks: Network structure and interbank contagion. Quantitative Finance, 15(4), 625-636.
• Brooks, C. (2019). Introductory econometrics for finance. Cambridge university press.
• Brown, M., Trautmann, S. T., and Vlahu, R. (2016). Understanding bank-run contagion. Management Science, 63(7), 2272-2282.
• Frey, R., Martin, L. V. and Tang, C., 2010. A New Class of Tests of Contagion With Applicants. Journal of Business & Economic Statistics. 28(3).pp. 423-437.
• Magnus, J. R., and Neudecker, H. (2019). Matrix differential calculus with applications in statistics and econometrics. Wiley.
• Stock, J. H., and Watson, M. W. (2015). Introduction to econometrics.