Distribution goodness-of-fit test device, consumable goods supply timing judgment device, image forming device, distribution goodness-of-fit test method and distribution goodness-of-fit test program

• US 20050283505A1
• Filed: 12/03/2004
• Published: 12/22/2005
• Est. Priority Date: 06/21/2004
• Status: Active Grant

• Current Assignee: Fujifilm Business Innovation Corp. (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Fujimoto, Masakazu
• Granted Patent: US 7,231,315 B2
• Time in Patent Office: Days
• US Class Current: 708/200
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04

Abstract

A distribution goodness-of-fit test device for testing whether measured data matches an estimated probability distribution has a counting section determination unit, a counting unit and a goodness-of-fit test unit. The counting section determination unit determines according to the number of the measured data, widths of counting sections for counting the measured data. The counting unit counts the numbers of data in the respective determined counting sections. Also, the goodness-of-fit test unit performs a goodness-of-fit test based on the numbers of data in the respective counting sections.

Claims

1. A distribution goodness-of-fit test device for testing whether measured data matches an estimated probability distribution, comprising:

a counting section determination unit that determines according to the number of the measured data, widths of counting sections for counting the measured data;

a counting unit that counts the numbers of data in the respective determined counting sections; and

a goodness-of-fit test unit that performs a goodness-of-fit test based on the numbers of data in the respective counting sections.

4. A distribution goodness-of-fit test device according to claim 1, wherein the counting section determination unit determines the counting sections, and the widths of the respective counting sections have equal probabilities on the estimated probability distribution.

5. A distribution goodness-of-fit test device according to claim 1, wherein the counting section determination unit determines a specified division number m corresponding to the number of the measured data, divides the estimated probability distribution into equal probability sections each having a probability of 1/m, and determines the widths of the respective counting sections.

6. A distribution goodness-of-fit test device according to claim 5, wherein when a discrete value of the measurement data is k, the counting unit judges the equal probability sections in which a cumulative probability of from 0 to k is included, and classifies the measurement data into the counting sections.

7. A distribution goodness-of-fit test device according to claim 1, wherein it is assumed that the measured data follows a plurality of probability distributions, and the counting section determination unit determines the widths of the counting sections for each of the assumed probability distributions.

8. A distribution goodness-of-fit test device according to claim 1, wherein when a discrete value of the measurement data extends over a plurality of counting sections, the counting unit divides the data into a plurality of counting sections and counts.

9. A distribution goodness-of-fit test device according to claim 6, wherein when a discrete value of the measurement data extends over a plurality of counting sections, the counting unit obtains a rate at which a probability of taking the discrete value of the measurement data is included in the equal probability sections, divides the measurement data into the a plurality of counting sections, and counts.

10. A distribution goodness-of-fit test device according to claim 1, wherein the goodness-of-fit test unit tests the counted data by a chi-square goodness-of-fit test.

11. A distribution goodness-of-fit test device according to claim 1, wherein the estimated probability distribution is a probability distribution varying temporally.

12. A distribution goodness-of-fit test device according to claim 1, wherein the estimated probability distribution follows a inhomogeneous Poisson process.

2. A distribution goodness-of-fit test device for testing whether measured data matches an estimated probability distribution, comprising:

a counting section determination unit that determines, according to the estimated probability distribution, widths of counting sections for counting the measured data;

a counting unit that counts the numbers of data in the respective determined counting sections; and

a goodness-of-fit test unit that performs a goodness-of-fit test based on the numbers of data in the respective counting sections.

3. A distribution goodness-of-fit test device for testing whether measured data matches an estimated probability distribution, comprising:

a counting section determination unit that determines, according to the estimated probability distribution and the number of the measured data, widths of counting sections for counting the measured data;

a counting unit that counts the numbers of data in the respective determined counting sections; and

a goodness-of-fit test unit that performs a goodness-of-fit test based on the numbers of data in the respective counting sections.

13. A consumable goods supply timing judgment device comprising:

a distribution goodness-of-fit test device for testing whether measured data matches an estimated probability distribution, further comprising;

a counting section determination unit that determines according to the number of the measured data, widths of counting sections for counting the measured data;

a counting unit that counts the numbers of data in the respective determined counting sections; and

a goodness-of-fit test unit that performs a goodness-of-fit test based on the numbers of data in the respective counting sections;

wherein the goodness-of-fit test from a measured consumption rate of consumable goods per unit time and an average value of a past consumption rate of the consumable goods per unit time, and

the consumable goods supply timing judgment device further comprising;

a control unit that calculates an estimated supply time from a ratio of a present consumption rate of the consumable goods to a past consumption rate of the consumable goods and notifying the estimated supply time when a difference between the present consumption rate and the past consumption rate is judged by the goodness-of-fit test.

14. An image forming device comprising:

a consumable goods supply timing judgment device comprising;

a distribution goodness-of-fit test device for testing whether measured data matches an estimated probability distribution, further comprising;

a counting section determination unit that determines according to the number of the measured data, widths of counting sections for counting the measured data;

a counting unit that counts the numbers of data in the respective determined counting sections; and

a goodness-of-fit test unit that performs a goodness-of-fit test based on the numbers of data in the respective counting sections;

wherein the goodness-of-fit test from a measured consumption rate of consumable goods per unit time and an average value of a past consumption rate of the consumable goods per unit time, and

the consumable goods supply timing judgment device further comprising;

a control unit that calculates an estimated supply time from a ratio of a present consumption rate of the consumable goods to a past consumption rate of the consumable goods and notifying the estimated supply time when a difference between the present consumption rate and the past consumption rate is judged by the goodness-of-fit test.

15. A distribution goodness-of-fit test method for testing whether measured data matches an estimated probability distribution, comprising:

determining, according to the estimated probability distribution and the number of the measured data, widths of counting sections for counting the measured data;

counting the numbers of data in the respective determined counting sections; and

performing a goodness-of-fit test based on the numbers of data in the respective counting sections.

16. A distribution goodness-of-fit test method according to claim 15, wherein the widths of the respective counting sections have equal probabilities on the estimated probability distribution by determining the counting sections.

17. A distribution goodness-of-fit test method according to claim 15, wherein it is assumed that the measured data follows a plurality of probability distributions, and the widths of the counting sections are determined based on each of the assumed probability distributions.

18. A distribution goodness-of-fit test method according to claim 15, wherein when a discrete value of the measurement data extends over a plurality of counting sections, the data is divided by a plurality of counting sections and being counted.

19. A storage medium readable by a computer and storing a distribution goodness-of-fit test program of instructions executable by the computer to perform a function for testing whether measured data matches an estimated probability distribution, the function comprising:

determining, according to the estimated probability distribution and the number of the measured data, widths of counting sections for counting the measured data;

counting the numbers of data in the respective determined counting sections; and

performing a goodness-of-fit test using the numbers of data in the respective counting sections.

20. A storage medium readable by a computer and storing a distribution goodness-of-fit test program according to claim 19, wherein the widths of the respective counting sections have equal probabilities on the estimated probability distribution by determining the counting sections.

21. A storage medium readable by a computer and storing a distribution goodness-of-fit test program according to claim 19, wherein it is assumed that the measured data follows a plurality of probability distributions, and the widths of the counting sections are determined based on each of the assumed probability distributions.

22. A storage medium readable by a computer and storing a distribution goodness-of-fit test program according to claim 19, wherein when a discrete value of the measurement data extends over a plurality of counting sections, the data is divided by a plurality of counting sections and being counted.