Pick any two topics covered in the course and apply real world examples and appl
ID: 452904 • Letter: P
Question
Pick any two topics covered in the course and apply real world examples and applications of these topics. You do not need to show the calculations as much as discuss how that models are used in the real world similar to the discussion forum assignments. List one pro and one con of each of the two topics you choose. Some sample topics that you can discuss but feel free to discuss others such as Linear Programming, Sensitivity Analysis, Simulation, Inventory, Decision Analysis, Multi-criteria Decisions, Forecasting & Time Series.
The paper as a guide should be about 5 pages give or take a page, typed, single or double spaced in 12 pt. font. IN YOUR OWN WORDS.
The importance to this paper analysis is the use of the decision analysis topics and how they are used in the real world beyond calculations and definitions so use your OWN words! Please note that this is NOT intended to be a term paper just more along the lines of a long essay.
Explanation / Answer
The two topics I will select from the above list would be Sensitivity Analysis & Forecasting & Time series.
Sensitivity Analysis
This related to study of uncertainty in the output mathematical model or a system as such with related to the changing input. It helps in testing the robustness of the system and identifies the pitfalls or error in assumptions and interpretations. It helps to find a systematic review based on sensitiveness of many parameters. Sensitivity analysis can be a repeat of meta-analysis or primary analysis. Many testing parameters for sensitivity analysis are identified during the review stage ,Sensitivity analysis are somewhat close to subgroup analysis. But it is much more advanced than sub group analysis as it estimates only the desired output rather than finding estimates on each sub class.
Analysis methods:
Which effect fixed or random must be used for analysis ?
For getting dichotomous outcomes, whether different rations such as odd ration, risk ratio will be different or can be assumed as same.?
And while dealing with continuous outcomes, results needs to be analysed as a standardized mean difference across all scales or it is just as mean differences for individuals.
Practical example: Let’s take an example from economics, In every budgeting process there are always variables that are uncertain. Future tax rates, inflation and deflation rates, interest rates, count of resources, operating & overhead expenses and other variables may not be known with accurate precision. Sensitivity analysis answers many things like if something got changed or deviated from the normal variance what could be the impact that could make on the whole system.
Forecasting & Time series.
Time is equivalent to money in business aspect. So time series and forecasting helps in predictability of many factors that support in taking a quality decision. It can be considered as a quality as well as quantity tool In making strategic decisions under uncertainty, we use many forecasting models using probability and other statistical methodologies. When information is traverse along with time, time series have significant role in deciding many factors. By looking at the observed value time series gives the flexibility to predict the future results. Curve fitting, functional approximation, exploratory analysis all comes under the predictability models. Some are used for mathematical interpretation and its majorly focusing on finding a solution with minimum variance and risk. Functional approximation technique use set of function among a well-defined class for a task specific thing. It will test using the time series by changing the value like numerical analysis and find the way how certain functions can be normalised by the available set of numbers.
Practical example: Bank or insurance companies use the time series model for analysing or estimating the future return given to their clients for a particular year. Their rate of interest and dividend calculations is based on time value of money.