Currently there are various disciplines where statistics are necessary to achieve accurate conclusions and make correct decisions, such is the case of the probability that we usually use when we want to explain a relevant event. For example, such as increased sales, progress of an epidemic, evaluation of statistics by population growth. In turn, Statistics has deployed various graphic and quantitative methods that allow summarizing and extracting information from a set of observations taken from a variable under study, which in general helps to solve prediction problems.

It is clear that for years one of the concerns of organizations and of man is to predict the future to be aware of the performance of certain phenomena with the aim of planning or predicting. From there, planning anticipates the results that the organization wishes to achieve by determining the necessary measures to achieve the desired success. However, this cannot be determined by strictly mathematical manifestations, it must be the derivation of a composition of mathematical calculations or the specialist who makes the study or analysis.

As a consequence, in probabilistic models, the manager does not worry about the results, but about the amount of risks that each decision carries, anything influences and changes the future, since it has an element of uncertainty. For this reason, decision analysis provides quantitative support to decision makers because they are based on statistical applications for the estimation of uncontrollable events. In this way, it is the most important factor in determining a successful implementation decision model, since the development of probability has been accelerated, they have a variety of models, the use of which has generated considerably valuable mathematical developments.

In the construction of models, the problem is studied, then the mathematical model is developed, which in decision making, fundamentally, combines information on probabilities with information on desires and interests. Therefore, risk assessment means a study to determine the results of the decisions together with their probabilities. Despite the misinterpretation problems, they can be avoided if an understandable analysis of the extremely sophisticated models is provided, reducing the difficulties of the validation and verification process, that is, they are seen in a similar way to a game, the actions are based in the expected results, it moves from a deterministic to a probabilistic model.

The main reason that statistics requires study of the laws of probability is because good decisions are expanded with good information or wisdom. Certainly, decision makers compare, operate numbers to quantify subjective values and uncertainties, examine the sensitivity of expected utility, weighted for key probabilities, weighting parameters and risk preference that allows understanding the decision situation. A good decision requires looking for a set of alternatives, because you do not really know where the problem is that limits your success. In other words, when a decision maker is faced with a choice between courses of action, the results are governed by chance. Likewise, the application of statistics was created by the need to put knowledge in a systematic evidence base; it even becomes knowledge, when they are used in the successful addition of a decision process.

However, in decision theory, calculations are made of the value of a certain outcome and its probabilities. From there, the consequences of the choices, face the decisions as if they were bets, that is, the utility, the probability of options, must be calculated to establish strategies and apply good decision-making. A systematic study should facilitate the objectives, which quickly identify problems as in the evaluation of alternatives, since the objectives of the decision maker must be expressed as criteria that reflect the attributes of the alternatives relevant to the designation. For its part, the choice between possible actions, and the prediction of expected results result from the logical analysis that the manager makes of the decision situation.

In decisions made with pure uncertainty, the decision maker has no knowledge, the decision maker must analyze both scenarios, this is a subjective control, the decision maker is based purely on his attitude towards the unknown, not even on the probability of occurrence of any state of nature. Decision theory should focus on the factors of the decision maker's psychological attitude and on their most relevant environment. A rare or unexpected event with potentially significant consequences for the decision maker would get risks or opportunities.

Similarly, when making decisions, the risk within its expected return must be examined and critical aspects identified. This process encompasses both the quantitative and qualitative aspects of controlling the impact of risk, since decisions can also be affected by the subjective rationality of people and by the way in which the decision problem is perceived. However, the process for managing risk and uncertainty is part of any probabilistic model. There are different types of decision models that help to analyze different scenarios, depending on the amount and degree of knowledge that we have to formulate the decision problem, a well-defined benefits matrix is applied, and then utility on two domain sets such as A and B. Probability is the tool to communicate and manage uncertainty. That is, the probability always depends on how much the decision maker knows.

Bibliography

• Reference 1
  
  

• Reference 2

• Reference 3

• Image 1

• Image 2

Lcda. Exqueila del Valle Rodríguez Díaz

Specialist in Commercial Law Mention in Human Talent Management
Graduated from the Illustrious University of the Andes
Mérida State Venezuela