Data processing: generic control systems or specific application – Specific application – apparatus or process
Reexamination Certificate
2001-01-10
2002-10-01
Patel, Ramesh (Department: 2121)
Data processing: generic control systems or specific application
Specific application, apparatus or process
C700S029000, C700S030000, C700S031000, C700S089000, C700S091000, C700S110000, C707S793000, C707S793000, C707S793000
Reexamination Certificate
active
06459941
ABSTRACT:
TECHNICAL FIELD
This invention relates to a method for estimating performance parameters, such as dollar loss by condition, and units defective by condition, for different periods of business and/or production. For these estimations, population totals are known (or assumed known). An estimation algorithm allows detailed analysis as is required for problem-solving and similar uses of parametric data.
BACKGROUND ART
When a total population value is known (or can be assumed known), traditional estimation procedures apply a general percentage to all data points and all parameters. For example, if the known data represents 5 percent of the population, the parameter values of the sample data are multiplied by 20 (100%/0.5%) as an estimation. This estimation technique works if the data are randomly sampled and there is little or no bias to the sample.
There is frequently skewing and bias in the sampling procedure, however, and gross estimating procedures break down when one tries to analyze parameters at a detail level. By “detail level” is meant the estimation of a specific parameter or condition for a total population.
In the conception of the invention, the inventors theorized that a part-wise approach to sampling that is applied non-homogenetically could overcome the prior art deficiencies. Biases may result from bringing into the sampling, over time, data that cause more sampling representation of specific members of a population type or geographical area than other members bring. Whatever the source of the bias in the sampled data versus the total population, the bias needs to be minimized if any detail level analyses of the data are to be useful.
This invention looks to minimize biases by making estimations at varying levels of the analyses, where the assumption is reasonable that sampling is piece-wise homogenous at the various levels. At a minimum, the estimation is made using every data point provided in a given report, for that report.
Other objects of the invention will be apparent from the following description and claims.
SUMMARY OF THE INVENTION
A method for estimating conditions for a population of unknown conditions comprises the steps of (a) accumulating data for a specific population including population members having known parameters and population members having unknown parameters, wherein said specific population is defined for a specific time period, and a specific product, (b) retaining data for said specific population for a period of time, (c) breaking down the population members having known parameters into specific categories of conditions for all specific time periods reported, (d) applying the condition rate for said population members having known parameters to the specific population for a specific time period.
The method may comprise the further step of summing the estimation for said specific time periods to obtain an estimation for all conditions for all time periods.
REFERENCES:
patent: 5339818 (1994-08-01), Baker et al.
patent: 5448684 (1995-09-01), Holt
patent: 5461644 (1995-10-01), Bergmans et al.
patent: 6018311 (2000-01-01), David
patent: 6300778 (2001-10-01), Frederickson et al.
Lobb Jolan Fredda
Manka David Henry
Olsen Richard Joseph
Whittum Robert Carlton
Young Ray Allison
Patel Ramesh
Wheeler David E.
LandOfFree
Method for handling estimation/ratioing of adjustment does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for handling estimation/ratioing of adjustment, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for handling estimation/ratioing of adjustment will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2995266