System and method for testing prediction models and/or entities
First Claim
1. A computer including a data storage device including a computer usable medium having computer usable code means for evaluating the effectiveness of a best of a plurality of comparable entities vis-a-vis a benchmark, the computer usable code means having:
- computer readable code means for receiving, from a computer input device, past market data from a database;
computer readable code means for generating the entities to be evaluated, at least one entity outputting at least one indicator of predicted performance;
computer readable code means for generating an effectiveness measurement of the benchmark using at least one predetermined measurement criterion, the predetermined measurement criterion being based on the past market data;
computer readable code means for generating an effectiveness measurement of each entity evaluated using the at least one measurement criterion;
computer readable code means for determining the best one of a plurality of entities;
computer readable code means for generating a statistic representative of the statistical significance of the effectiveness of a best one of the comparable entities vis-a-vis the benchmark using the effectiveness measurements such that the statistic is determined based on the evaluation of all the entities; and
based on the statistic, using the best one of the entities to predict future performance.
1 Assignment
0 Petitions
Accused Products
Abstract
A computer-implemented performance evaluation method includes specifying a group of comparable entities and a benchmark against which the comparable entities are evaluated. The entities evaluated may be a process, technology, strategy, treatment, organization, individual, or other identifiable unit. A primary data matrix is arranged by data indices, and the primary matrix is sampled with replacement N times to bootstrap N observation matrices. Alternatively, a Monte Carlo approach can be used. Then, all the matrices are filled with measurement criteria, with each criterion being representative of a respective data index and a respective entity. A p-value estimate is returned that measures the statistical significance of the best of the comparable entities relative to the benchmark, where the p-value represents the probability of wrongly rejecting the null hypothesis that a best of the comparable entities has expected performance no better than that of a benchmark. The p-value accounts for the examination of all of the comparable entities, i.e., the p-value depends on the examination of all of the entities as a group, and not simply on a single entity.
-
Citations
18 Claims
-
1. A computer including a data storage device including a computer usable medium having computer usable code means for evaluating the effectiveness of a best of a plurality of comparable entities vis-a-vis a benchmark, the computer usable code means having:
-
computer readable code means for receiving, from a computer input device, past market data from a database; computer readable code means for generating the entities to be evaluated, at least one entity outputting at least one indicator of predicted performance; computer readable code means for generating an effectiveness measurement of the benchmark using at least one predetermined measurement criterion, the predetermined measurement criterion being based on the past market data; computer readable code means for generating an effectiveness measurement of each entity evaluated using the at least one measurement criterion; computer readable code means for determining the best one of a plurality of entities; computer readable code means for generating a statistic representative of the statistical significance of the effectiveness of a best one of the comparable entities vis-a-vis the benchmark using the effectiveness measurements such that the statistic is determined based on the evaluation of all the entities; and based on the statistic, using the best one of the entities to predict future performance. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer-implemented method for evaluating the effectiveness of the best among plural comparable entities against a benchmark, comprising the acts of:
-
collecting past performance data in a database; specifying the comparable entities; defining a primary matrix arranged using data indices, the primary data matrix including the past performance data; sampling the primary matrix with replacement N times to define N observation matrices; filling the matrices with effectiveness measurement criteria, each criterion being representative of a respective data index and a respective entity; returning a statistic representative of the statistical significance of a most effective entity vis-a-vis a benchmark, based on the matrices; using the most effective entity to predict future performance. - View Dependent Claims (9, 10, 11, 12)
-
-
13. A computer program product comprising:
-
a computer program storage device readable by a digital processing apparatus; and a program means on the program storage device and including instructions executable by the digital processing apparatus for performing method acts for evaluating plural comparable entities, the method acts comprising; receiving past performance data from a database, the past performance data being input by means of a computer input device; generating the entities to be evaluated, the entities outputting one or more indicators of predicted future performance based on the past performance data; generating an effectiveness measurement of a benchmark using at least one predetermined measurement criterion; generating an effectiveness measurement of each comparable entity using the measurement criterion; generating a statistic representative of the statistical significance of the effectiveness of a best one of the comparable entities vis-a-vis the benchmark using the effectiveness measurements such that the statistic is determined based on the evaluation of all the comparable entities; based on the statistic, determining the best one of a plurality of entities; and using the best one of the entities to predict future performance. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification