This is an individual coursework thats consists of the following tasks using the Excel spreadsheet inserted below. The data covers 5 years from 2007-2012, the task is to experiment with different forecasting models such as (Additive model T+S+C+R, Multiplicative model T x S x C x R. T=Trend, S=Seasonal variation, C=Cyclical movement and R=Residual.)What are the two basic models that could adopt to the data and the most appropriate time series model for the data.) Find out the moving averages and plot a trend line on a graph and explain why Forecasting is important, compare the forecasted figures with the actual figures for the year of 2012.
1. Introduction to the data – by explaining the data, the average measures o spread (mean, range, mode, standard deviations, interquartile range) [10 marks]
2. Time series Analysis – explain what time series analysis is, why it is used, how it is used in the data given, moving averages that show change of values over a period of time by creating a graph thats shows the value of R-squared and y-variable using the additive and multiplicative models. [30 marks]
3. Forecast – what it is, why is it used, how was it used in the data given with the formula given (Forecast= trend + seasonal variation + residual) this calculation is used to compare forecasted and actual figures in the data.
4. Critical explanation of using Clustering as part of the time series analysis – (used to identify homogenous groups of data or clusters) (text mining is the process of exploring and analysing large amount of soft unstructured text) [20 marks]
5. copies of the 2 models in appendix of report [10 marks]
