Statistics in Business Decision Making - Term Paper Example

Topic: How Statistics is used in Business Decision Making This paper looked at how statistics can be used in various business decision making processes. Techniques such as standard deviation, correlation and regression analysis are discussed to provide description of various methods that can be used in business context. Introduction Statistics is one of the most fascinating fields of knowledge with very diverse use in many fields of knowledge. It provides a clear advantage in conducting the research and deal with day to day business problems in more objective as well as rational manner. Business use of statistics therefore is in many departments including the operations, finance as well as marketing and human resource of the firm. Most importantly, statistics has greater use in the field of finance as organizations such as investment firms; banks, brokerage houses, hedge funds etc use statistical methods more extensively to measure and compare the various performance parameters. Some of the methods or tools of statistics that are used in finance include standard deviation to measure the volatility or risk of returns, variance analysis as well as the use of more sophisticated techniques such as multiple regression etc. similarly, in other areas such as human resource management, statistics is used to perform critical analysis such as measuring employee turnover, performance appraisals etc. This paper will therefore attempt to discuss statistics from the perspective of its applications in business and how managers are using statistics as the valid tool for making more informed and rational decision. The first of this paper will discuss some important statistical concepts such as mean, variance, standard deviation, correlation, regression analysis etc which are mostly used by the businesses in their day to day operations. This paper will therefore also discuss the overall importance of these statistical tools to the business and how managers can use them in best possible manner. Descriptive Statistics As discussed in the introduction that this paper will attempts to describe statistical tools such as mean, standard deviation, variance etc. These statistical tools are often come under the heading of descriptive statistics as they are the main tools used to collect data quantitatively and present in more meaningful manner to draw some logical conclusions from the data collected. Some of the tools that are used in descriptive statistics are: (Black,35) Mean or Average Once data is collected, it is nothing more than a raw set of data which may provide no clue about the potential information that they may provide. Thus one meaningful way of manipulating the data will be calculate the mean or average of the data. Mean value is calculated in following manner: Mean = Sum of all Observations / Total No. of Observations It is also important to note that mean values may provide distorted information because of the outliers effect. One large observation value can distort the results and mean values may become more inflated due to the impact of outliers or larger values in the population. (Downing and Clark,56) Mean value is considered as one of the most significant and important measure especially in finance. There are various uses of this measure in finance i.e. from measuring the average rate of return on an investment to calculating the weighted average rate of return of a portfolio, mean values provide critical insight into the performance of an investment. Similarly, average values are also calculated for studying the costs also as concepts such as average cost, average variable costs, average fixed costs are important concepts to understand in order to make important business decisions because controlling costs is one of the fundamental responsibilities of the managers. Measures of Dispersion Measures of dispersion measures the degree of variability in data or probability distribution and provides important information regarding the behavior of the data and how meaningful it can be in making informed and rational decisions. Some of the important tools used for measure of dispersions are: Variance Variance is one of the important measures of dispersion as it provides information regarding the dispersion of the data from its mean. Variance is calculated by taking an squared deviation of the individual sample from its mean value and the sum is than divided by the total number of observations in a sample. (Weiss,85) Variance and standard deviation (discussed below) are two of the important measures of dispersion and provide important information to the managers to make decisions. Variance analysis can be used in assessing the variances in the budgeted as well as actual costs/average costs along with calculating the machine break times etc. Standard Deviation In pure statistical terms, standard deviation is the square root of the variance showing the variance or dispersion from the mean or average values. Standard deviation is widely used measure of understanding the deviation or variability in the data from its mean value and can provide critical insight into the overall predictability as well as the behavior of the data. Standard deviation is calculated in following manner: Standard Deviation = Sqrt (Variance) In statistics, standard deviation is denoted with α or sigma. Some of the important applications of standard deviation in finance include assessing the variability of the returns on investment, variability of returns of a portfolio. One of the most important concepts in finance i.e. capital asset pricing model is based on the concepts of standard deviation and variance analysis of the returns of the market as well as the individual security. Correlation Analysis In social sciences as well as in business, correlation is frequently used statistical tools to measure the strength of relationship between different variables. It therefore indicates the degree of relationship between two or more variables and how they can be related with each other. It is important to note that correlation analysis does not provide the indication regarding the cause and effect of one variable over other but rather it provides an insight into the degree of relationship between two or more variables. Another important sub-topic of correlation is the coefficient of correlation which can be calculated as : Coefficient of Correlation = Cov (a,b) / St. Dev (a) x St. Dev (b) A correlation coefficient of positive 1 indicate that there is a perfect correlation between the two variables i.e both the variables move in the same direction and a negative 1 correlation indicate no or opposite relationship between the variables. Correlation is used heavily in finance in assessing and calculating the correlation between the market returns and the individual stock returns. Beta value is a always calculated by using the correlation and covariance between the market returns and the individual returns and provide good insight into how the individual stock behave with respect to the market. Linear and Multiple Regression Regression Analysis is also one of the widely used statistical techniques for assessing the impact of dependent variables on any given independent variable. Typically, regression analysis will provide answer to the question of how the values of some dependent variables can converge towards the values of the independent variables. Regression therefore provides answers to how one variable in data is affected by another variable. Regression can be either linear where the relationship between two variables is calculated whereas it can also be multiple in nature wherein the relationship between more than two variable is calculated. It is important to note that both linear as well as multiple regression can provide misleading information and can lead to the wrong conclusions to be made. In order to avoid forming the wrong conclusions, it is therefore important that some other statistical techniques shall also be used to confirm the validity of the results provided by the regression analysis. There are various business related problems where regression analysis can be used successfully to understand the behavior and patterns of one or more variables. For example, in order to assess the machine breakdown times, managers may be looking for formulating the relationship between output and the breakdown times. In this case, output or production levels may be dependent upon how many hours the machine remains under operations. Similarly, managers can also explore the relationship between employee turnover with variables such as compensation etc to understand as to why the turnover may be higher or low Conclusion Business statistics is one of the most important fields of knowledge which are extensively used by businesses to make more informed and rational decisions. Different techniques such as correlation, regression, mean, mode and measures of dispersion provide an important insight into the way different variables behave and what actions can be take to overcome the problematic situations. Though statistical techniques have their own inherent weaknesses however, still they offer scientific method of assessing the facts from a rational perspective and offer insight into how the problematic situations can be corrected with proper application of other fields of knowledge. Statistics can only provide a meaningful presentation of data into good information however, to take decisions on such information, it is important that the managers must use other tools and techniques such as strategic management practices in order to take decisions which make commercial and business sense. Taking decisions solely on the basis of the statistical data and information therefore may be misleading and can result into wrong decisions to be made if managers fail to offer unique business insights to these problems. Appendix The following table provides the Average, Standard Deviation as well as the Variance of Google Stock Prices from 2004 till date.1 Average St. Deviation Variance 418.60 132.41 17532.6 This table indicates the average, standard deviation and variance of the stock returns of Google. Average values are calculated over the period of last five years and may indicate the impact of outliers i.e. google’s prices may have fluctuated over different ranges. Standard Deviation and Variance provides the measures of the stock’s risk and its behavior during the period. These values are higher indicating that Google’s prices may have swung against the movements in the stock prices. This graph shows the historical trend of Google’s Stock Prices from 2004 till date. Historical progression of stock prices indicate that the prices fluctuated however, during last five years are showing upward trends. Bibliography 1. Black, Ken. Business Statistics:Contemporary Decision Making. New York: John Wiley and Sons, 2009. 2. Downing, Douglas and Jeff Clark. Business Statistics. New York: Barrons Educational Series, 2003. 3. Weiss, N A. Introductory Statistics. New York: Addison Wesley, 2007. Read More