After analysing the data, various factors have been evolved which is important to consider. First factor is that the product manufactured by PLE is mostly active in the first two quarters of the year. For the other two quarters the sales of the product goes down. PLE should notice this point and try to find out the main reasons behind this and should find the solutions for these problems.
The data is forecasted for the next three years 2013, 2014 and 2015 which will help the company to prepare the plans for the growth of the company in future.
As the result is according to the expectation, the three of the curves – cost of goods, Sales and operating cost – are of the same moving pattern with increasing zigzag but interest cost was slightly different from others which was nearly a straight line. Thus, the expected result was also an increasing zigzag (Bio rad, 2014).
The linear regression model is compatible for the simple data as our data is simply fluctuating in a well- defined manner. This also saves the time and cost for analysing the data. Linear regression technique is also easy to understand as the user needs to work only on a linear line rather than dealing with complicated curves.
The linear regression technique has certain disadvantages. The main disadvantage is the accuracy coefficient. Generally, the linear regression techniques provide less accurate data, thus, the accuracy coefficient of the linear regression techniques is generally less than the polynomial techniques.
Linear regression technique is also not appropriate for the purpose when we need to predict the data for a long time. As the time increases, the accuracy of the data will decrease. The curve fitting method will not be appropriate when a sudden change in the data occurs. For unexpected changes, the process may need to start from the beginning of each year.