Back to Patents

US10489233

Method, apparatus and computer software program for determining probability of error in identifying evidence

An apparatus for determining probability of error in identifying evidence includes a computer. The apparatus includes a non-transitory memory in communication with the computer in which is stored a software program, and prior and posterior probability distributions from a plurality of independent tests conducted on an item of evidence. For each test, the computer forms a factor distribution from the test’s probability distributions using the software program stored in the non-transitory memory of the computer. The computer convolves the independent factor distributions to form a joint factor distribution using the software program. The computer calculates a tail probability from the joint factor distribution using the software program to determine a probability of error in identifying the evidence. The computer stores the probability of error in the non-transitory memory. A method. A computer program.

Download Patent


Claims: The invention claimed is:
  1. A method for determining probability of error in identifying evidence in a criminal investigation comprised of the steps:
    1. obtaining prior and posterior probability distributions from a plurality of independent tests conducted on an item of evidence;
    2. entering the probability distributions into a non-transitory memory of a computer;
    3. for each test, forming a factor distribution from the test’s probability distributions with the computer using a software program stored in the non-transitory memory of the computer;
    4. convolving the independent factor distributions to form a joint factor distribution by the computer using the software program;
    5. calculating a tail probability from the joint factor distribution by the computer using the software program to determine a probability of error in identifying the evidence;
    6. storing the probability of error in the non-transitory memory of the computer; and
    7. reporting the probability of error from the computer to help implicate guilty defendants and exonerate innocent defendants in a court of law to a party interested in identifying the evidence.
  2. A computer program stored in a non-transitory memory for determining probability of error in identifying evidence in a criminal investigation comprising the steps of:
    1. obtaining prior and posterior probability distributions from a plurality of independent tests conducted on an item of evidence;
    2. entering the probability distributions into a non-transitory memory of a computer; and the computer implemented steps using the computer program of:
    3. for each test, forming a factor distribution from the test’s probability distributions with the computer;
    4. convolving the independent factor distributions to form a joint factor distribution by the computer;
    5. calculating a tail probability from the joint factor distribution by the computer to determine a probability of error in identifying the evidence;
    6. storing the probability of error in the non-transitory memory of the computer; and
    7. reporting the probability of error from the computer to help implicate guilty defendants and exonerate innocent defendants in a court of law to a party interested in identifying the evidence.
  3. An apparatus for determining probability of error in identifying evidence in a criminal investigation comprising:
    1. a computer;
    2. a non-transitory memory in communication with the computer in which is stored a software program, and prior and posterior probability distributions from a plurality of independent tests conducted on an item of evidence; for each test, the computer forms a factor distribution from the test’s probability distributions using the software program stored in the non-transitory memory of the computer; the computer convolves the independent factor distributions to form a joint factor distribution using the software program; the computer calculates a tail probability from the joint factor distribution using the software program to determine a probability of error to help implicate guilty defendants and exonerate innocent defendants in a court of law in identifying the evidence; the computer stores the probability of error in the non-transitory memory; and
    3. a printer or display in communication with the computer which prints out a report that reports the probability of error to a party interested in identifying the evidence, or a display in communication with the computer on which the computer displays the report.
  4. A method for determining probability of error in identifying evidence in a criminal investigation comprised of the steps:
    1. obtaining prior and posterior probability distributions conducted on an item of evidence;
    2. entering the probability distributions into a non-transitory memory of a computer;
    3. examining the probabilities of a plurality of possible outcomes in no more than one minute of computer time to help implicate guilty defendants and exonerate innocent defendants in a court of law; and
    4. forming a factor distribution from the probability distributions on the examined outcomes with the computer using a software program stored in the non- transitory memory of the computer.
  5. A method as described in claim 4 where after the forming step there are the additional steps of:
    1. calculating a rail probability from the factor distribution by the computer using the software program to determine a probability of error in identifying the evidence;
    2. storing the probability of error in the non-transitory memory of the computer; and
    3. reporting the probability of error from the computer to a party interested in identifying the evidence.
  6. A method as described in claim 1 where the factor is related to a likelihood ratio.
  7. A method as described in claim 1 where the factor is used for forensic identification.
  8. A method as described in claim 1 where the item is biological evidence.
  9. A method as described in claim 1 where the tests involve DNA analysis.
  10. A method as described in claim 1 where the item is fingerprint evidence.
  11. A method as described in claim 1 where the item is firearm evidence.
  12. A method as described in claim 4 where the factor distribution provides exclusionary information about the evidence.
  13. A method as described in claim 4 where the factor distribution provides inclusionary information about the evidence.
  14. A method as described in claim 1 where the probability of error helps identify an investigative lead.
  15. A method as described in claim 1 where the probability of error assists a trier of fact in understanding the evidence.
  16. A method as described in claim 1 where the test conducts a biometric measurement.
  17. A method as described in claim 1 where the test is for a genetic disease.
  18. A method as described in claim 1 where the test is for determining parentage.
  19. A method as described in claim 1 where the factor assists a physician in assessing an outcome of a diagnostic test.