Application of Statistics in the Analysis of Financial Accounts - Coursework Example

Application of Statistics in the Analysis of Financial Accounts Introduction: The application of statistics in the management and analysis of financial accounting is the field of financial econometrics. J. Fan (2004, 1) defines the combination of statistics and finance in a very elaborate manner: ‘It uses statistical techniques and economic theory to address a variety of problems from finance. These include building financial models, estimation and inferences of financial models, volatility estimation, risk management, testing financial economics theory, capital asset pricing, derivative pricing, portfolio allocation, risk-adjusted returns, simulating financial systems, hedging strategies, among others.’ The evolving financial system means that the needs of the financial markets become more and more sophisticated. Therefore, more detailed financial modeling techniques are required in order to deal with the problems in the new globalization era. A. W. Lo (2006, 1) explains that ‘the first is the fact that the financial system has become more complex over time, not less. This is an obvious consequence of general economic growth and development in which the number of market participants, the variety of financial transactions, and the sums involved have also grown. As the financial system becomes more complex, the benefits of more highly developed financial technology become greater and greater and, ultimately, indispensable.’ In addition, new financial products are created every day to meet customer’s demands, making it even more necessary to use sophisticated techniques to solve problems. Techniques in Statistical Analysis: The process of financial analysis starts with the collection of relevant financial data. Financial data can be of three types: i. Times Series: Data collected over a period of time for a variable. ii. Cross-sectional: Data collected for one of more variables at one point in time. iii. Panel Data: Data collected for multiple variables over a period of time. Other characteristics of financial data include the fact that the data is always discrete and always cardinal – i.e. it represents actual numbers and can be compared with one another to determine which value is better or worse. The collection of data is followed by the formulation of mathematical models, which are defined as ‘relationships between different variables and/or variables in different moments and different places’ (Rachev, S. T., et al. 2006, 3). To arrive at such models, financial analysts need to use a variety of mathematical techniques that would help them make conclusions that are backed by statistical proof. The first tool used in financial analysis is of probability. Probability is defined as the chance that something will happen. Financial analysts not only need to forecast what will happen, but also how likely it is to happen. One of the most common techniques in this regard is the Bayesian statistics. This is characterized by the fact that statistical models are uncertain and subject to modification with respect to new information. It also distinguishes between prior probability and posterior probability – that is, probability is determined at any point in time with all the information available at that time. Bayes provides the relationship between the prior and posterior probabilities and explains how probability changes (Rachev, S. T., et al. 2006). One of the most popular techniques in statistical analysis in finance is regression analysis. Regression is defined as the definition of the relationship between two variables, one a dependent variable and the other an independent variable. Linear regression techniques linearize the relationships between the two variables (often symbolized by x and y). It discovers the best fit relationship and reduces the variation from the estimate value. Such a relationship, once established, can be used to forecast future values and to normalize the variations in future values to obtain a long-term perspective. In the area of statistical analysis in equity markets, some analysts use static asset pricing models while others use dynamic asset pricing models. A very famous technique used in equity analysis is called the Capital Asset Pricing Model (CAPM). CAPM provides a theoretical justification for passive investing. It provides the ‘estimates of expected return on individual investment and can establish fair rates of return on invested capital in regulated firms’ (Ruppet, D. 2004, 225). It is a pre-defined model that helps the analysts define a relationship between the more variable expected return on equity and the relatively stable returns on market. Pros and Cons of Using Statistics in Finance: The nature of financial data itself provides the justification for the application of statistical techniques to its analysis. There are very few measurement error and revisions problems when statistics is applied to finance. This is because the data observed is generally observed from actual prices and values and not estimated to approximate levels. This makes financial statistics a reliable source of analysis in accounting and decision-making. Furthermore, the high frequency of data available makes it a good candidate for application of very powerful statistics techniques. This makes financial decision-making more reliable and accurate. However, there are certain characteristics of financial data that can make it difficult for analysts to apply statistical analysis to this set of values. As Brooks, C. (2008, 3) elaborates, ‘financial data are often considered very noisy, which means that it is more difficult to separate underlying trends or patterns from random and uninteresting features. Financial data are also almost always not normally distributed in spite of the fact that most techniques in (statistics) assume that they are. High frequency data often contain additional patterns which are the result of the way that the market works, or the way that prices are recorded.’ Furthermore, it is very easy to distort financial data for the purpose of window dressing. The best example of this in the history of financial frauds is the Enron case. Enron used consolidation of SPEs, different accounting treatment of arm length transactions, deceptive income recognition practices, fair value accounting and inadequate disclosure of related party transactions and conflicts of interest to shareholders in order to create a rosy picture of the company’s financial position. When analysts failed to account for such embellishment of financial accounts, they forecasted patterns of future growth that were unreliable. This means that the patterns identified in financial data through the application of statistical techniques can be dependent on a set of values that is erratic and susceptible to fraud in nature. The analysis and the decisions derived from that analysis are, therefore, not as reliable and accurate as we would expect them to be. The characteristics of financial data often make the financial conclusions unreliable. Therefore, careful analysis must be made of any data and of the conclusions derived from it. How do you identify whether a Financial Analysis is Reliable? Brooks, C. (2008, 11) has identified five points to consider when reading a financial analysis: 1. Does it involve the development of a theoretical model or is it merely a technique looking for an application so that the motivation for the whole exercise is poor? 2. Are the data of ‘good quality’? Are they from a reliable source? Is the size of the sample sufficiently large for the model estimation task at hand? 3. Have the techniques been validly applied? Have tests been conducted for possible violations of any assumptions made in the estimation of the model? 4. Have the results been interpreted sensibly? Is the strength of the results exaggerated? Do the results actually obtained relate to the questions posed by the author(s)? Can the results be replicated by other researchers? 5. Are the conclusions drawn appropriate given the results, or has the importance of the results of the paper been overstated? Conclusion: The application of statistics to financial analysis is a technical aspect that is normally performed by those who have an avid command over the field of financial econometrics. Though statistical techniques often provide very valuable information, they are prone to errors caused by mechanical and human mistakes. Therefore, any decision based on statistical analysis should be supplemented with the application of common sense and instinct. This will help overcome the weaknesses of the statistical techniques and help improve the analysis. Bibliography Brooks, C. 2008. Introductory Econometrics for Finance. Second. New York: Cambridge University Press. Fan, J. 2004. "An introduction to financial econometrics." Operations Research and Financial Engineering: Princeton University. http://orfe.princeton.edu/~jqfan/papers/03/overview.pdf (accessed April 7, 2010). Lo, A. W. 2006. "Financial Econometrics." Massachusetts Institute of Technology. http://web.mit.edu/alo/www/Books/fmetrics.pdf (accessed April 7, 2010). Rachev, S. T., S. Mittnik, F. J. Fabozzi, S. M. Focardi, and T. Jai. 2006. Financial Econometrics: From Basics to Advanced Modeling Techniques . New Jersey: John Wiley & Sons. Ruppert, D. 2004. Statistics and finance: an introduction. New York: Springer-Verlag. Statistics and Probability Answers. March 16, 2010. http://www.cramster.com/answers-mar-10/statistics-and-probability/financial-accounting-30200326-enron-is-one-the-enduring-legacies-of-corporate-fraud-in_799272.aspx (accessed April 7, 2010). Read More