Regression analysis is a statistical tool with the help of which we are in a position to estimate (or predict) the unknown values of one variable from unknown values of another variable. With the help of regression analysis we can find out the average probable change in one variable given a certain amount of change in another. In fact it provides estimates of values of the dependent variables from the values of independent variables. (S.P.Gupta , M.P.Gupta, 2003)
Time series analysis is the most popular method of business forecasting because it helps in understanding of past behavior, it helps in planning future operations, it helps in evaluating current accomplishments above all it facilitates comparison. ( S.P.Gupta, M.P.Gupta, 2003)
The basic objective of the study of trend is to predict the future behavior of the data. If a trend can be determined, then the rate of change or progress can be ascertained and tentative estimates concerning the future be made accordingly.
Mathematical methods of fitting trend are not foolproof – in fact, they can be a source of some of the most serious errors that are made in statistical work. They should never be used unless rigidly controlled by a separate logical analysis. Trend fitting depends upon the judgment of the statistician, and a skillfully made freehand sketch may often be more practical than a refined mathematical formula. (Riggleman, Frisbee, ).
The straight line trends indicate the increase or decrease of a time series at constant amount but in many cases, straight line can not fit the data adequately. In such a case better description of the time series can be attained by non-linear curve rather than straight line. The methods of measuring non-linear trends are: graphic method, moving average method, second degree polynomial equation method and so on. . ( S.P.Gupta, M.P.Gupta: 2003).
Moreover, the trends discussed so far were plotted on arithmetic scales. Trends may also be plotted on semi-log chart in the form of straight line or a non-linear. The types of trend usually computed by logarithms are: exponential trends, and growth curves. However based on the trend/regression type (exponential, linear, logarithmic, polynomial, power, moving average) polynomial fits better because it is a measure of how well the data fits the trend line: the closer to one the better the fit. A trend line is most reliable when its R2 value, known as the correlation coefficient, is at or near 1. The reason for adoption of this polynomial regression is that this trend analysis is done with single dependent variable and single independent variable whereas the year is taken as the independent variable which actually does not have or have insignificant influence on dependent variable.
Basically, trend line polynomial regression has been applied for processing of data and developing the trend equation on the last five years key financial data with the help of Microsoft Excel application.
2.0 Objectives of the Study
The objectives of the study are to:
• Make a bridge between past and future performance of Trust Bank Ltd. • Forecast future performance based on the past performance of Trust Bank Ltd. • Analyze the past growth to predict the future growth of Trust Bank Ltd. • Identifying present strengths and weaknesses and future opportunities and threats. • Provide better insight of the Trust Bank Ltd.
3.0 Research Methodology
This is a quantitative analysis based on some key financial data of Trust Bank Limited. For trend analysis and forecasting, secondary data have been collected from published annual report of Trust Bank Limited for the year 2009. Last five years data have taken into consideration for forecasting financial performance of the year 2010 and 2011. For ease, the year 2005, 2006, 2007, 2008, 2009, 2010 and 2011 has taken as year 1, 2, 3, 4,...