Risk and Decision Making Flashcards
Sensitivity analysis
ADVANTAGES
Presented to management in a form which facilitates subjective judgement
Identifies those areas which are critical to the success of the project and which need to be carefully monitored
No complicated theory to understand, it is relatively straightforward
DISADVANTAGES
Only one factor at a time can be analysed
It assumes that changes to variables can be made independently
It only identifies how far a variable needs to change, it does not look at the probability of such a change
It provides information on the basis of which decisions can be made, it does not point directly to the correct decision
Linear regression
ADVANTAGES
Linear regression models are simple to use and easy to explain
Can be used to predict the impact of expanding variables beyond current estimates
DISADVANTAGES
There will not always be a linear relationship between variables and outcomes
Complex models are needed to consider multiple variables
Surplus relationships between variables and outcomes may be identified
The data collection may be inaccurate or there may be a large error variable
Decision trees
ADVANTAGES
Simple decision trees are easy to explain and logical to use
Can be used to analyse different outcomes based on a number of variables
DISADVANTAGES
Variables have to be simplified and restricted to avoid overcomplicating the decision tree
Large decision trees can be difficult to interpret
Simulation
ADVANTAGES
It gives more information about the possible outcomes and their relative probability
It is useful for problems which cannot be solved analytically
DISADVANTAGES
It is not a technique for making a decision, only for obtaining more information about the possible outcomes
It can prove expensive in designing and running the simulation on a computer for complex projects
Monte Carlo techniques require assumptions to be made about probability distributions and the relationships between variables that may turn out to be inaccurate
Prescriptive analytics
ADVANTAGES
Prescriptive models can identify optimum decisions whilst incorporating multiple variables
DISADVANTAGES
Creating models is complex and requires specialist data science skills
Reliability of the models depends on the reliability of the data and relationships between the past and the future
Expected values
ADVANTAGES
The information is reduced to a single number for each choice
The idea of an average is readily understood
DISADVANTAGES
The probabilities of the different possible outcomes may be difficult to estimate
The average may not correspond to any of the possible outcomes
The average gives no indication of the spread of possible results, i.e it ignores risk
Unless the same decision has to be made many times, the average will not be achieved
Weaknesses in CAPM
The company’s shareholders may not be diversified. Particularly in smaller companies they may have invested most of their assets in this one company.
Even in the case of larger companies the shareholders are not the only participants in the firm. Directors and employees are exposed to both the systematic and specific risks of the business so may try to diversify.
CAPM depends on a perfect capital market
The need to determine the excess return. Expected, rather than historical returns should be used although historical returns are often used in practice
The need to determine the risk-free rate. A risk-free investment might be a government security. However, interest rates vary with the term of lending.
Errors in the statistical analysis used to calculate beta values. Betas may also change over time
The CAPM is also unable to forecast accurately returns for companies with low price/earnings ratios and to take account of seasonal ‘month of the year’ effects that appear to influence returns on shares
