Sensitivity Analysis is important in Risk management and analysis. Good question.

The Sensitivity analysis is carried out to determine how changes in cost and revenue items can alter the cash flow estimate in project.

It involves studying how the overall expected outcome is likely to alter response to change in input variables i.e Analysis of NPV expected eith respect to sales volume, selling prices or initial outlay

It also involves identification of key variables in the base case appraisal. - which input variables have considerable significant impact by a small change on the project IRR or NPV

This is a good method but the draw back or limitation is this does not qualify and does not provide any clear decision system to the management. In sensitivity analysis it treats variables as if they are independent and does not consider interrelationship

You can solve few numerical on sensitivity analysis and the concept will be clear.

I follow to know

A very interesting question I follow

I follow question.

Following

Thank you very much Sheth Sir for your quick satisfactory answer.

Sensitivity analysis is the simplest risk analysis method. The concept is to use an expected numerical value of one of the elements or objectives of the project and to examine its effect on the project as a whole. This value is changed by another component and the effect is studied. This is repeated in several ascending and descending values, The effect of changing the value of this element on the project is known within the range of change. This process can be replicated on other elements separately to examine their impact, for example, on the project price or implementation time.

As per Dr Sheth

Dear Sir,

Try this link.

econwpa.repec.org/eps/fin/papers/0409/0409020.pdf

Following

Data Preface: Energy Investments: An adaptive approach to profiti...

A drawback of sensitivity analysis, within the context of NPVs or similar analytical methods, is the limitation on our ability to set a range that captures possible extent certain variables could vary.

In my new book - Energy Investments: An adaptive approach to profiting from uncertainties - I suggest using binomial tree analysis to partly remedy the limitations of NPVs and sensitivity analysis. I also use scenarios and option games to analysis the interacting effects of a set of variables on the outcomes of your analysis under conditions of uncertainties.

Trust this provides a viable approach to what you are trying to resolve in your research.

I agree with Dr K N Sheth

I agree with much of what Dr Sheth said but as to 'it treats variables as if they are independent and does not consider interrelationship', there is opportunity to combine various iterated interplay of variables at the same time under sensitivity analysis. For instance, effect of say 10% rise in interest rate combining with 1 week reduction in project delivery time, of 15% rise in cost with 2 weeks delay in completion time, or say a particular percentage rise/fall in cost with another % fall/rise in revenue together with specified change in delivery time etc.

Sensitivity analysis is actually meant to appreciate the likely behaviour of investment performance under an array of dynamic forces with ultimate view of establishing boundaries for each input variable or interplay of different variables.

Sensitivity analysis studies the change in the result when you modify an input variable. In capital budgeting you can modify the discount rate, the forecasting of revenues or costs, etc. and see if the decision changes: for example this investment is not interesting with a rate of discount higher than 4%.

You can do sensitivity analysis as complex and sophisticated as you wish. It depends on the model you have constructed. A spreadsheet offers some simple tools for that. Montecarlo Simulation, MCS, programs provide many options to examine the behavior of results subject to changes in input variables. Some simple MCS tools are found in the standard spreadsheets but you can use specialized Add-ins for that such as Crystal Ball or @Risk. However, no matter which tool you use, results depend on how complete and/or complex your model is.

The question by Hetesh Garati is the introversion of the expectation aspects. We may go wrong, will-it be wrong? Answers and corrections are eventual by priori specifics and scanstio entailed, which dearly crutinises the linear expectations. Owing to the component observational entries and their dynamical boyouncy, leaving us to the non-Gaussian like component. Eventually, Gaussian component of the complex my or generic non-linear reduced form of the sample in mind of the sensitivity analysis. Do wrvgave a proper scale to distinguish the severity form for all the considerable states effect?

The question leadsto some of the principal fundamental acjivef goals in sampling. To generally by badics link any incorrectoln of the model as a sampling problems. Indeed, this generally takes into effect or plays into effect, as per the knowldge of the variable or the component knowlrdge reliasable as non-Gaussian. To reach all agreements, the severity of the component is indeed put fundamental clarity to reduce linear to conformity be in a Gaussian component. Therefore, all variables acting andbtge operators needs to defaukts and act for the buoyancy. Mostly, we protect any sample, validate the operator, and lay dtrigent to yhe observed entry and it's component suite. Principal by methods, bi-linear or generic

by goemetric method expectation fracas to gaussnity clearing the exposure embedded.

The sensitivity analysis is the support knowledge in managing the TAKE-OVER or LEAVE-OVER of the project. Involving the risk which is the variance of the returns, the scenario state of the appraisal in terms of the profit sample, called the Minimum Sample Profit, which can be negative or positive, appraises in the vica-versa and not changing in state by scenarios limits scales in the preferable Gaussian boyouncy. All the incurred bi-states by loss or profit are the Sensitivity Analysis Limitations Adjustment. Which can be a positive orientated exposure. Contrary, to the leading exposure, which can clearly subordinate between the loss or profit and foresee the specifics and generics of the model. Hence, the minimal sample containing the minimum sample and of positive profit is the exposure or the linear reduced expected exposure. If not, there outlay a non-linear exposure, which is linealy observed, per the Maximal Exposure proper scaling the non-Gaussian /Gaussian component. Which, the ME is required to refrain from the instances of limitations dure to the complexities of specifics & generics of the components. The solution is of the Maximal Sensitivity Analysis, by the Minimal Sample Correction method which fits the calibration technique accross complexities in the buoyancy estimation and sample scaling of estimators. Thus, a drawback/follow-up procedure to linearity is essential in addressing the limitations. Perfectly, for risk management calibration of estimators inform quantitatively and the sensitivity analysis is a quantity matter of the estimation and set-up to the problem, where a linear exposure, linear by procedure is needed.

following

The problem of doing sensitivity analysis and more specifically MCS is that when you introduce probability into the decision making, you lose the comfort of a simple rule approach, such as the NPV rule: if NPV>0 accept the project, if NPV

Sensitivity Analysis examines the effects on profitability, of changes in the values of the key economic variables. A particular case of sensitivity analysis is to take high, low and medium values of the key economic parameters and compute the profitability for various combinations of these pessimistic, average and optimistic estimates, thus providing a range of possible results (the Best–Worst–Average Approach).

This seeks to answer the question; the performance of any investment is the product of many variable factors, if any factor changes, what effect will that have on the overall performance? Are there any factors that will have a greater effect than others? The investor is then able to pin point those variable that require additional care.

I go with Dr K N Sheth

Due to inflation various experience get affected. When expenses varies profitability varies. Thus, due to probable change s in price level changes projected profitability get affected, Analysis of this variability i.e. Risk, called Sensitivity Analysis in Investment Decision or Project Appraisal.

Thanks for all the answers that are on record of RG . The matter is clear.

A range of techniques has been used to develop stress test scenarios. Sensitivity tests, which are at the most basic level, generally shock individual parameters or inputs without relating those shocks to an underlying event or real-world outcomes. Given that these scenarios ignoremultiple risk factors or feedback effects, their main benefit is that they can provide a fast initial assessment of portfolio sensitivity to a given risk factor and identify certain risk concentrations.

More sophisticated approaches apply shocks to many parameters simultaneously. Approaches are typically either historically based or hypothetical.

Wonderful interaction Thanks Dear Colleagues

A quick additional comment regarding the implementation: try 'data table' in Excel, possible also for two variables (e.g. price, volume).

Thanks all RG Colleagues for the answers

Dear you can read my article

https://www.researchgate.net/publication/340769576_Financial_Performance_Evaluation_of_the_commercial_banks_in_Jordan_Based_on_the_CAMELS_Framework

It's effect of changes in raw material price/decrease in selling price of finished goods on cash inflow and effect on IRR.

It can be considered from various angles. It helps in contingency.