Good Critical Thinking On Decision Making

Management

Decision Tables
Decision tables are tools for making decisions in conditions where there is complete uncertainty as to which state of nature in a decision environment may occur. The decision tables rely of one of three decision methods: ‘maximax’, ‘maximin’ or ‘equally likely’. Under ‘maximax’, the alternative that maximizes the maximum outcome for every alternative is chosen. ‘Maximax’ locates the alternative with the highest possible gain, and is therefore an ‘optimistic’ decision criterion. Under ‘maximin’, the alternative that maximized the minimum alternative for every alternative is chosen. The decision criterion is to minimize loss and locates the alternative with the least possible loss, thereby earning the sobriquet of being a ‘pessimistic’ decision criterion. The ‘equally likely’ method finds the alternative with the highest average outcome under the assumption that each state of nature is equally likely to occur (Pearson, n.d.).
Example. Suppose a manufacturer has to decide whether to put up a small plant or a large plant amidst uncertainty over whether the market would be favorable or unfavorable. If the manufacturer is able to calculate the payoffs he would get for a big plant and a small plant had each operated in a favorable or an unfavorable market, he could then use a decision table to decide as to which plant he would set up. His decision would be based upon maximax (optimistic), maximin (pessimistic) or equally favorable decision criterion.

Decision Trees

Decision trees are used for making decisions where the decisions required and states of nature are sequential in conditions of risk. A decision tree is a graphic display of the decision process that indicates decision alternatives, states of nature and respective probabilities, and payoffs for each combination of decision alternative and state of nature.
At each node in a decision tree, the criterion utilized is that of ‘expected monetary value (EMV)’. The EMV for an alternative is the sum of all possible payoffs from the alternative, each weighted by the probability of that payoff occurring (Pearson, n.d.).
Example. In the previous example, if the probabilities of having a favorable and an unfavorable market, together with payoffs, were known, the manufacturer could employ a decision tree to determine whether he should set up a large plant or a small plant, or even do nothing.

Monte Carlo Simulation

Monte Carlo simulation is a computerized mathematical technique that allows people to account for risk. It performs risk analysis by building models of possible results by substituting a probability distribution for any factor that has inherent uncertainty. The simulation calculates values iteratively, each time using a different set of random values from the probability functions. Probability distributions could be the normal ‘bell’ curve, the ‘lognormal’ curve which have unlimited positive potential, the uniform line where all possibilities could occur equally, the triangular function where a minimum and maximum value are known, or the PERT where the likelihoods of most likely and least likely values are known (Palisade, n.d.).
Example. Monte Carlo simulations are useful to generate probabilistic results and to carry out an analysis of likely scenarios. Contractors developing new business segments in the international markets where the probability of risk and the impact of the risk follow probability distribution functions could use Monte Carlo simulations.

Use of Cognitive Mapping Tool to Enhance Decision Process

Cognitive mapping tools could be used to draw decision trees. An example is shown in Figure 1 below.
Figure 1: Decision Tree using Cognitive Mapping Tool

Reference

Palisade. (n.d.). Monte Carlo simulation. Retrieved 07 Feb 2015, from http://www.palisade.com/risk/monte_carlo_Simulation.asp
Pearson. (n.d.). Decision making tools. Retrieved 07 Feb 2015, from http://wps.prenhall.com/wps/media/objects/2234/2288589/ModA.pdf