Decision Modeling & Analysis: Probability, Distribution, Uncertainty

Decision Modeling & Analysis
Name
Course name
Instructors’ name
Date
Decision Modeling & Analysis
Making decisions can be challenging, whether we make fast or slow decisions, the process of analyzing information is important because making an informed decision means analyzing all the alternatives before arriving at an amicable solution. Decision-making is a key task of organization top management, managers are expected to choose between two extreme cases, and it depends on the degree of knowledge possessed by those in charge (Shepherd, Williams & Patzelt, 2015).
The first extreme case in decision-making is the one that is deterministic, and the other one that is uncertain. Between the two extreme sides of decisions making process, there are risks, but the main idea is to analyze the degree of certainty depending on the levels of understanding of the business problem. This research paper present decision analysis process using different decision criteria, and different types of scenarios. The research describes certain elements that are important in the analysis before making decisions (Shepherd, Williams & Patzelt, 2015).
In every business decision is related to some aspect of probability, probability is a theoretical idea that helps identify the levels of risks involved in certain business decisions. To determine probability is to identify the degree of risk of the potential outcomes and compare the difference from the benchmark expectation (Albright, Winston & Zappe, 2010). For example, consumers demand forecasts can be determined by random sampling of the target market population to understand their purchasing decision in relation to the cost. The cost of each item is determined by the nearest outcomes that match the cost expectations (Albright, Winston & Zappe, 2010).
Probability means conducting a risk assessment to analyze the expected outcome. Decision-making requires compressive information; probability assessment is done to quantify the information gaps between what is known, and what needs to be known for an optimal decision (Albright, Winston & Zappe, 2010). Probabilistic models are important because of its protection against adverse uncertainty and exploitation from uncertainty. Decision-making can be complex in situations where information is scarce or vague, however, using probabilities, managers can make informed decisions (Albright, Winston & Zappe, 2010).
Suppose that a firm wants to launch a new product in the market, they can administer a pre-launch questionnaire, and if 88 out of the 100 questionnaire respondents said that, they would buy the product this could be translated into a probability statement as follows
p- Product successful = 88 divide by 100 = 0.88. In business, the decision-making process is full of uncertainty, but the more information available, the better the decision. This means trading off values of the specific outcome against the suitable probability (Shirangi & Durlofsky, 2016).
Uncertainty is the state of working with limited knowledge; managers deal with uncertainty and try to reduce risks when making decisions to avoid undesired outcomes (Shirangi & Durlofsky, 2016). Managers need to develop skills of good judgment to reduce uncertainty and avoiding situations that can impact negatively on the business. Managing uncertainty when making decisions means identifying, quantifying and analyzing certain factors that are likely to affect the intended outcomes. The manager needs to analyze both the risks and their impact (Shirangi & Durlofsky, 2016).
Some of the risk includes macroeconomic risk like the alignment of buyers and seller to be consistent with the principles of demand and supply, transaction risks and operational risks related to mergers and acquisition or partnerships (Shirangi & Durlofsky, 2016). Risks can only be determined through prediction, therefore when making business decisions, statistical inference is among the tools that can be used to generate crucial information about what to expect based on the past activities after all the alternatives to arrive at an amicable solution (Provost & Fawcett, 2013).
Statistics and statistical inferences provide comprehensive data that enable us to make better decisions (Provost & Fawcett, 2013). For example, assume that there is a tree near your neighbor's house; the tree is old and almost dead. The weather is bad, a big storm is expected that night; the question is what is the danger involved if the tree falls on the house. Should your neighbor spend $ 2,000 for the tree to be cut down before the storm comes? Basing on last year’s information where many trees fell on houses within the neighborhood.
Using statistical inference, you can gather data about the proportion of old tree within the neighborhood that fell, in this case, the ratio is 5 in 100. The question is, if the tree will fall on the house or not, using statistical inference we can study the variation in the outcomes of such trees (Provost & Fawcett, 2013). The average of such group of trees that fell last year is 5 percent, the assumption is that the neighbor's tree is like the other trees within the neighborhood that fell or can be different from most of them. What would be the outcome if one in 10 trees had fallen instead of 5 in 100; this is a statistical inference (Provost & Fawcett, 2013). Data gathered from the neighborhood helps in making important decisions.
When gathering important data before making critical decisions, it is not practicable to count all the trees in the neighborhood; sampling is a data collection technique that helps in conducting statistical research. The assumption is that the sample size represents the whole population. Business use sampling to determine market niches and to determine customer levels of satisfaction (Shepherd, Williams & Patzelt, 2015).
Sampling of a population enables manager be informed whether a product is visible in the market. Small businesses can ask its customers how they feel about the product, but this is not applicable to businesses that serve hundreds of customers on a daily basis like in restaurants. That is why sampling of the customers is a good idea to understand the customer trend (Shepherd, Williams & Patzelt, 2015). Some firms hire an outsider to conduct surveys to understand the market trends. Sampling can only be effective and should be conducted within a short period because the sample might change or certain events may occur that will affect the data (Shepherd, Williams & Patzelt, 2015). Data generated through sampling provides decision makers with information that can be used to determine the future market trends.
Business needs to predict the future market trends, managers use several tools to forecast on the future market conditions. Forecasting providing insights that help in decision making towards a more profitable future (Albright, Winston & Zappe, 2010). Regression analysis helps in predicting events that are expected to occur in the near future. For example, demand analysis can predict the quantity customers are likely to purchase. Predicting the number of customers who will see a specific billboard or number of viewers watching an advertisement can be done using regression analysis (Albright, Winston & Zappe, 2010).
Insurance companies rely on regression analysis to estimate the number of policyholders that can be involved in accidents. Regression analysis is an important forecasting tool that analyzes situations to help decision makers allocate resources appropriately (Albright, Winston & Zappe, 2010). For instance, a factory manager can use regression analysis to...