Scenario Analysis

Scenario Analysis is conducted, to analyze the impacts of possible future events on the system performance by taking into account several alternative outcomes, i.e., scenarios, and to present different options for future development paths resulting in varying outcomes and corresponding implications. Scenario analysis is the process of forecasting the expected value of a performance indicator, given a time period, occurrence of different situations, and related changes in the values of system parameters under an uncertain environment.

Basic Scenarios
When performing the analysis, managers and executives at a company generate different future states of the business, the industry, and the economy. These future states will form discrete scenarios that include assumptions such as product prices, customer metrics, operating costs, inflation, interest rates, and other drivers of the business. Managers typically start with three basic scenarios:

• Base case scenario – It is the average scenario, based on management assumptions. An example – when calculating the net present value, the rates most likely to be used are the discount rate, cash flow growth rate, or tax rate.
• Worst case scenario – Considers the most serious or severe outcome that may happen in a given situation. An example – when calculating the net present value, one would take the highest possible discount rate and subtract the possible cash flow growth rate or the highest expected tax rate.
• Best case scenario – It is the ideal projected scenario and is almost always put into action by management to achieve their objectives. An example – when calculating the net present value, use the lowest possible discount rate, the highest possible growth rate, and the lowest possible tax rate.

The Process of Scenario Analysis

• Define the problem: First, you need to define the problem you want to tackle, including time frame, scope and decision variables. The scale of the organization's plans drives the first step and what scenarios they want to run. For example, a global manufacturer might want to know what the retail industry will be like in five years and determine answers to questions such as:
  • How will omni channel purchasing disrupt distribution channels?
  • Will manufacturers supply consumers directly or through distributors?
  • The impact of additional competition
• Create a list of variables: In this next step, the organization needs to create a list of known and unknown variables that could affect their organization. Known variables, such as unit pricing, sales volumes and margins, are collected from historical data sets. Unknown variables would include the impact of trade disputes, higher tariffs, a weaker dollar and possible recessions.
• Run a what-if analysis: Having identified as many variables as possible, the organization would then run a what-if scenario analysis to evaluate the worst-case and best-case scenarios and establish their impacts on the business. This is where the difference between scenario analysis and sensitivity analysis becomes apparent because it evaluates the impact of changing all variables at one time, rather than each individually.
• Evaluate options and determine probabilities.: Having determined the best- and worst-case scenarios, these are incorporated into the organization's planning. A further step could be to determine the sensitivity of various inputs to better understand the impact of individual variables on the overall scenario.

Criticism of the Scenario Analysis Process [1]</ref>
While there is utility in weighting hypotheses and branching potential outcomes from them, reliance on scenario analysis without reporting some parameters of measurement accuracy (standard errors, confidence intervals of estimates, metadata, standardization and coding, weighting for non-response, error in reportage, sample design, case counts, etc.) is a poor second to traditional prediction. Especially in “complex” problems, factors and assumptions do not correlate in lockstep fashion. Once a specific sensitivity is undefined, it may call the entire study into question.

It is faulty logic to think, when arbitrating results, that a better hypothesis will render empiricism unnecessary. In this respect, scenario analysis tries to defer statistical laws (e.g., Chebyshev's inequality Law), because the decision rules occur outside a constrained setting. Outcomes are not permitted to “just happen”; rather, they are forced to conform to arbitrary hypotheses ex post, and therefore there is no footing on which to place expected values. In truth, there are no ex ante expected values, only hypotheses, and one is left wondering about the roles of modeling and data decision. In short, comparisons of "scenarios" with outcomes are biased by not deferring to the data; this may be convenient, but it is indefensible.

“Scenario analysis” is no substitute for complete and factual exposure of survey error in economic studies. In traditional prediction, given the data used to model the problem, with a reasoned specification and technique, an analyst can state, within a certain percentage of statistical error, the likelihood of a coefficient being within a certain numerical bound. This exactitude need not come at the expense of very disaggregated statements of hypotheses. R Software, specifically the module “WhatIf,” (in the context, see also Matchit and Zelig) has been developed for causal inference, and to evaluate counterfactuals. These programs have fairly sophisticated treatments for determining model dependence, in order to state with precision how sensitive the results are to models not based on empirical evidence.

Another challenge of scenario-building is that "predictors are part of the social context about which they are trying to make a prediction and may influence that context in the process". As a consequence, societal predictions can become self-destructing. For example, a scenario in which a large percentage of a population will become HIV infected based on existing trends may cause more people to avoid risky behavior and thus reduce the HIV infection rate, invalidating the forecast (which might have remained correct if it had not been publicly known). Or, a prediction that cybersecurity will become a major issue may cause organizations to implement more security cybersecurity measures, thus limiting the issue.