Reference no: EM132218709 , Length: word count:1500
STATISTICAL DATA ANALYSIS AND DECISION MODELLING ASSIGNMENT -
ASSESSMENT TASK - STATISTICS AND DATA ANALYSIS PROJECT
The objective of this assignment is to apply statistical theory covered in the subject to business situations. Students are given data related to a simulated real-world business case. Students must read and analyse the case using appropriate statistical method and tests by using Microsoft Excel/PHStat.
Students are required to:
(a) Comprehensively explain and critically analyse the relationship between the business issues;
(b) Apply appropriate and accurate statistical model to solve the business issues;
(c) Evaluate, analyse, and discuss the model outcomes; and
(d) Communicate findings and draw critical justified conclusions and present recommendations with supporting evidences and implications.
Note: (a) to (c) is the ACTION PLAN and (d) is the MANAGEMENT REPORT.
For the first assignment, we want to predict the future price of a company's shares on the stock exchange. There are several companies to choose from:
CMP = Compumedics Limited (a pharmaceutical company)
ESL = ESL Australia (makes video games)
MCD = McDonalds (a fast food chain)
PKG = Packaging Corporation of America (makes packaging materials)
VLO = Valero Energy Corporation (refines petroleum)
WERN = Werner Enterprises (transportation and logistics)
In these files:
The last column is the future change in a company's share price, i.e., the change from the close of trading today to the open of trading tomorrow morning. This is the dependent variable (Y).
All the other columns are the price (or the changes in price) of various financial instruments, including the price of the same company's shares, interest rates, currency exchange rates, and the price of oil and certain metals (gold, silver, copper, aluminium). These are the independent variables (Xs).
The original price changes have been ranked and sorted, so that all numbers go from 0 to 1:
0 means the smallest value.
1 means the biggest value.
0.5 means the median value.
Some columns are also interaction variables, i.e., a new column created by multiplying 2 other columns. These have "_X_" in their title. For example, "30year_x_Aluminium" means the number is these two numbers multiplied together.
Students need to create a regression model to see if a relationship exists between an output variable and the input variables and improve the model stepwise. Students are also expected to critically evaluate and discuss the model (or models) and draw conclusions about how well we can (or can't) use the model to make predictions.
Students are required to submit a REPORT including the following:
(1) Action Plan - students should explain their approach to build the regression model(s) and discuss its regression outputs, the stepwise approach or best subset approach and the decision for the final model. Students should attach the Excel output as evidence of their work. In the action plan, students will meet the criteria (a) to (c). The action plan serves as the supporting evidence or reference for the management reporting. No word limits. Student's (1) knowledge and application and (2) analysis and evaluation will be assessed in this section.
(2) Management reporting - In this report, students will compare their models, summarise their findings, justify their conclusions and present their recommendations as requires in part (d). The management report will evaluate students' ability to communicate with management with correct writing style and syntax.
The word limit is 1500.
Attachment:- Assignment Files.rar