DEVELOPMENT OF ACTUAL RISK COSTS BASED ON ESTIMATED RISK COSTS AS WELL AS PROBABILISTIC RESTRICTION OF THE ACTUAL RISK COSTS

Abstract

An evaluation is performed for a device, an application and/or a method, in particular a method for establishing a technical system such as a power plant for instance, the assessment being carried out on the basis of costs for risks. In accordance with the method, the costs for specific risks are to be assessed. A risk costs interval is to be determined, which contains the actual risk costs with high probability. This is achieved by a regression of intuitive assignments to a straight line by an indirect linear regression by a non-linear regression in an intermediate diagram.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

These and other objects and advantages will become more apparent and more readily appreciated from the following description of the preferred embodiments, taken in conjunction with the accompanying drawings of which:

FIG. 1 is a graph of an assignment in a risk costs coordinate system, risk costs assessment number coordinate system,

FIGS. 2A and 2B are graphs of a first exemplary embodiment of a non-linear regression;

FIGS. 3A and 3B are graphs of a second exemplary embodiment of a non linear regression;

Claims

1. A method for evaluating at least one of a device, an application and a method for establishing a technical system such as a power plant, with an assessment carried out based on costs for risks, comprising: determining risk costs causes;assessing possible risk costs depending on risk costs causes,assigning risk costs values to intuitive risk costs assessment numbers for possible risk costs, respectively,representing said assigning in a risk costs to risk costs assessment number coordinate system having a risk costs axis with a decadic logarithmic scale and a risk costs assessment number axis with a linear scale;assuming that values of the possible risk costs have errors randomly and stochastically distributed, in particular normally distributed;determining a variance and an expected value for the possible risk costs based on a probability to determine actual risk cost values to which are assigned intuitive risk cost assessment numbers, respectively;implementing regression of the intuitive risk cost assessment numbers on a straight line by an indirect linear regression using a non-linear regression on a straight line in an intermediate diagram;determining actual overall risk costs from a sum of the actual risk costs by a regression line of the actual risk cost values; andassigning a probability such that the sum of the actual risk costs remains below an upper limit, with an assumption that the risk costs sum exhibits a probability distribution, in particular a normal distribution, such that quantiles are calculated on this basis.

2. The method as claimed in claim 1, wherein in the intermediate diagram, the risk costs values are plotted along a y-axis forming a linear scale, and the intuitive risk costs assessment numbers are plotted along an x-axis forming a linear scale.

3. The method as claimed in claim 2, wherein the non-linear regression uses an exponential function with a base and a linear y-axis ax+b.

4. The method as claimed in claim 3, wherein the base of the exponential function is base 10.

5. The method as claimed in claim 3, further comprising determining values a and b occurring by minimizing quadrats of intervals between determined actual risk costs values and the exponential function.

6. The method as claimed in claim 5, further comprising: forming an inverse function of the exponential function; andback transforming the inverse function in a risk costs coordinate system, the risk costs assessment number coordinate system having a risk costs axis with a decade logarithmic scale and a risk costs assessment number axis with a linear scale, with a straight line ax+b determined by the values a and b being determined.

7. The method as claimed in claim 6, wherein said determining determines risk costs causes from the system to be established, deadline difficulties, currency fluctuations, overtime hours and/or price increases.