Research project - Possible, probable and preferable futures of BHP Billiton

I have received approval from my study leader for my research subject. The research project will be 80 pages.

The main objective of this research project is to create and consider probable, preferable and possible futures for BHP. 

The research project will take cognisance of the interrelated trends and possible discontinuities that could impact on its future.

RESEARCH DESIGN & METHODOLOGY 

A framework proposed by Sohail Inayatullah will be used to formulate the probable, preferable and possible futures (Inayatullah, 2008). 

· Mapping the past, present & future 

The history of BHP will be considered by documenting the main historical events and trends that have led to its present position. Particular attention will be paid to determine whether historical trends suggest any discontinuities in key trends. (Singer & Piluso, 2010) The history of BHP will be placed in a broader pattern of history (Kurian & Molitor, 1996) 

The present will be mapped by identifying current quantitative drivers and trends that are impacting the future of BHP and its industry. A system based approach will be used to identify such drivers and trends (Kunc, 2008). An environmental scan will be performed to identify any new emerging issues impacting on the natural resources industry and BHP specifically. 

An assessment of the strategic positioning of BHP will be performed. Porters’ competitive forces model will be used. The forces to be assessed are potential new entrants into the market, current competition, suppliers, buyers and substitute products and services (Porter, 2010)

· Deepening the understanding of selected trends 

Based on the futures studies work performed in the previous section significant trends will be identified. The understanding of these selected future trends will be deepened by making use of a structural mapping matrix. The matrix integrates a depth dimension with a breath dimension (Slaughter, 2002) 

· Creating alternatives 

A scenario based approach will be used to create alternatives futures for BHP(Schoemaker, 1995). Four scenario archetypes are to be used, being: 

1) Continued growth that enhances current conditions. 

2) Collapse, as continued growth fails. 

3) Steady state. 

4) Transformation as a result of dramatic change. (Dator, 1979) 

· Transforming 

A preferred scenario is selected by comparing the different scenarios with that of the stated aims of the company. 

CHAPTER OUTLINE 

The chapter outline is as follows: 

- Chapter one will be an introduction.

· Chapter two will consider the history of BHP and the natural resources industry by documenting the main historical events and trends that have led to the present. The history of BHP will be placed in a broader pattern of history. 

· Chapter three will identify quantitative drivers and trends that are impacting the future of BHP and its industry. A system based approach will be used to identify such drivers and trends. An environmental scan will be performed to identify any new emerging issues impacting on the natural resources industry and BHP specifically. 

· Chapter four will include an assessment of the strategic positioning of BHP. Porters’ competitive forces model will be used to perform this assessment. The competitive forces to be assessed are potential new entrants into the market, current competition, suppliers, buyers and substitute products and services 

· Chapter five will use a structural mapping matrix to deepen the understanding of selected significant trends. 

· Chapter six will create four scenarios based on the work performed in the previous chapters. 

· Chapter seven will select a preferred future based on the scenarios proposed and the stated aims of the organisation. 

· Chapter eight gives a summary of the futures of BHP as well as the limitations of the process.

Some initial ideas on possible strategic responses to the threat of nationalisation of mining assets in South Africa.

Strategic Management of Mining Nationalisation

Reading 12.l Qualitative Models & Reading 12.m Economic Meaning

LOS 12.l reads:
“Discuss models with qualitative dependent variables”

It is important to note that to date we have dealt with models that produce QUANTITATIVE dependent variables (e.g. Y). 

An ordinary regression model (e.g everything up to now) is not able to deal with QUALITATIVE dependent variables. 

There are 2 types of models that can deal with qualitative dependent variables

1. Probit & Logits:
 - Probit – Based on the normal distribution
 -  Logit – Based on logistic distribution

These models estimate the likelihood that an event will occur

2. Discriminant models
Similar to Probit & Logit models, but make different assumptions regarding the independent variables.
The model produces a score that produces a Yes or No answer.


LOS 12.m reads:
“ Interpret the economic meaning of the results of the multiple regression analysis and critique the regression model & its results”

This is easy, but important in practice. 

Just because an item is statistically significant does not mean it is economically significant. For example, you might calculate that the share prices rise by 2% in January. If your trading costs are however 3%, it would not make economic sense to buy the shares.

Reading 12,k Model misspecification

The LOS reads:
"Discuss the effects of model misspecification on the results of a regression analysis, and explain how to avoid the common forms of misspecification."

Introduction – What is misspecification?
A model that provides an incorrect description of the data. To some extent all models are misspecified, as no model can consider all potential outcomes. (1) 

The effect of Misspecification
You end up with either biased or inconsistent regression coefficients.
Taking you back to CFA 1, a reminder of biased & inconsistent coefficients.

Bias of an estimator is the difference between this estimator's expected value and the true value of the parameter being estimated. An estimator or decision rule with zero bias is called unbiased. Otherwise the estimator is said to be biased. (2)

A consistent estimator means that the distributions of the estimators become more and more concentrated near the true value of the parameter being estimated, as the sample increases. (2)

The result of biased and inconsistent estimators is unreliable hypothesis testing and inaccurate predictions.


Types of Misspecification

1. The functional form is misspecified
This means in essence that the regression formula is incorrect
There are three types of functional form misspecification, being:

1.1 Important variables are omitted
If road accidents (Y) are caused by speed (X1) and driver skill(X2), omitting speed out of the function will result in misspecification.

1.2 Variables should be transformed
Regression assumes that the Y variable is linearly related to each of the independent variables. (Being Assumption 1) 

The issue is that not variables are often not transformed. Watch out if you are dealing with any variable related to size!

1.3 Incorrect data pooled
Relationships are calculated for a period (e.g 10 years), when the relationship was only applicable for 5 years (but you still include 10 years worth of data).


2. Explanatory variables are correlated with the error term in time series models.

2.1 Using a lagged dependent variables as an Independent variable 

2.2 Forecasting the Future
When you are using information from a period to predict something else from that period 

2.3 Measuring independent variables with error
An example would be when we want to use real interest rates, but we use nominal interest rates.

3. Other time-series misspecifications that result in nonstationary
This is covered in Reading 13.

Source
(1)Read more: http://www.answers.com/topic/misspecified-model#ixzz1C8jRkHh0
(2) www.wikipedia.com

Reading 12, Types of Errors and Linear Regression

In the previous blogs, heteroskedasticity, serial correlation & multicollinearity were discussed.
These events result in errors as it relates to hypothesis testing. I thought it worthwhile to summarize the types of errors.

Type of violations        Type of Error           Meaning of Error
Heteroskedasticity          Type 1 Error              Rejection of the null hypothesis, when it is true
Serial Correlation            Type 1 Error              Rejection of the null hypothesis, when it is true
Multicollinearity              Type 2 Error              Failure to reject the null hypothesis when it is actually false