Methods and apparatus to estimate population reach from different marginal rating unions

1. An apparatus comprising:

at least one memory;

instructions; and

processor circuitry to execute the instruction to at least:

determine a population reach estimate of a union of time intervals for which media ratings data is available, the population reach estimate based on a pseudo universe estimate of a population audience corresponding to the union of the time intervals;

determine a pseudo universe estimate of a recorded audience corresponding to the union of the time intervals;

determine the pseudo universe estimate of the population audience based on the pseudo universe estimate of the recorded audience; and

in response to a decision to update the pseudo universe estimate of the population audience to reduce an error of the population reach estimate:

adjust the population reach estimate of the union;

apply a correction to the population reach estimate of the union to maintain a condition associated with the population reach estimate; and

output the population reach estimate of the union when the error of the population reach estimate satisfies a threshold.

2. The apparatus of claim 1 , wherein the processor circuitry is to adjust the population reach estimate of the union to fit within a range defined by a lower bound and an upper bound.

3. The apparatus of claim 2 , wherein the processor circuitry is to apply the correction to the population reach estimate of the union by:

determining a correction for the union reach estimate when the union reach estimate is not within the range;

iteratively adjusting the range based on the correction until all unions are satisfy a condition; and

adjusting the union reach estimate based on the correction.

4. The apparatus of claim 2 , wherein the lower bound is a second population reach estimate corresponding to a subset of the union of the time intervals.

5. The apparatus of claim 2 , wherein the upper bound is at least one of (A) a sum of reach estimates for a plurality of subsets of the union or (B) a universe estimate of users that potentially could be exposed to media corresponding to the media ratings data.

6. The apparatus of claim 5 , wherein the union is a first union, the lower bound is a first lower bound, the upper bound is a first upper bound, the range is a first range, the population reach estimate is a first population reach estimate, and when the processor circuitry adjusts the population reach estimate of the first union, the processor circuitry is to adjust at least one of a second lower bound or a second upper bound of a second population reach estimate of a second union of the time intervals is adjusted, the processor circuitry to adjust the first population reach estimate of the first union to ensure that the second population reach estimate of the second union of the time intervals is within a second range defined by the second lower bound and the second upper bound.

7. The apparatus of claim 1 , wherein the pseudo universe estimate of the recorded audience corresponds to a recorded reach for subsets of the union of the time intervals, and the pseudo universe estimate of the population audience corresponds to a population reach for the subsets of the union of the time intervals.

8. The apparatus of claim 7 , wherein:

the pseudo universe estimate of the recorded audience corresponds to a first universe estimate that assures independency among recorded audience data for the subsets of the union of the time intervals; and

the pseudo universe estimate of the population audience corresponds to a second universe estimate that assures independency among population audience data for the subsets of the union of the time intervals.

9. The apparatus of claim 1 , wherein the error corresponds to a difference between (A) a first relationship based on the population reach estimate of the union of the time intervals and the pseudo universe estimate of the population audience of the union of the time intervals, and (B) a second relationship based on population reach estimates for subsets of the union of the time intervals and the pseudo universe estimate of the population audience of the union of the time intervals.

10. A non-transitory computer readable medium comprising instructions which, when executed cause one or more processors to at least:

determine a population reach estimate of a union of time intervals for which media ratings data is available, the population reach estimate based on a pseudo universe estimate of a population audience corresponding to the union of the time intervals;

determine a pseudo universe estimate of a recorded audience corresponding to the union of the time intervals;

determine the pseudo universe estimate of the population audience based on the pseudo universe estimate of the recorded audience; and

in response to a decision to update the pseudo universe estimate of the population audience to reduce an error of the population reach estimate:

adjust the population reach estimate of the union;

apply a correction to the population reach estimate of the union to maintain a condition associated with the population reach estimate; and

output the population reach estimate of the union when the error of the population reach estimate satisfies a threshold.

11. The computer readable medium of claim 10 , wherein the instructions cause the one or more processors to adjust the population reach estimate of the union to fit within a range defined by a lower bound and an upper bound.

12. The computer readable medium of claim 11 , wherein the instructions cause the one or more processors to apply the correction to the population reach estimate of the union by:

determining a correction for the union reach estimate when the union reach estimate is not within the range;

iteratively adjusting the range based on the correction until all unions are satisfy a condition; and

adjusting the union reach estimate based on the correction.

13. The computer readable medium of claim 11 , wherein the lower bound is a second population reach estimate corresponding to a subset of the union of the time intervals.

14. The computer readable medium of claim 11 , wherein the upper bound is at least one of (A) a sum of reach estimates for a plurality of subsets of the union or (B) a universe estimate of users that potentially could be exposed to media corresponding to the media ratings data.

15. The computer readable medium of claim 11 , wherein the instructions cause the one or more processors to adjust the population reach estimate of the union to be between the lower bound and the upper bound.

16. The computer readable medium of claim 15 , wherein the union is a first union, the lower bound is a first lower bound, the upper bound is a first upper bound, the population reach estimate is a first population reach estimate, and when the instructions cause the one or more processors to adjust the population reach estimate of the first union, the instructions to cause the one or more processors to adjust at least one of a second lower bound or a second upper bound of a second population reach estimate of a second union of the time intervals is adjusted and adjust the first population reach estimate of the first union to ensure that the second population reach estimate of the second union of the time intervals is between the second lower bound and the second upper bound.

17. The computer readable medium of claim 10 , wherein the pseudo universe estimate of the recorded audience corresponds to a recorded reach for subsets of the union of the time intervals, and the pseudo universe estimate of the population audience corresponds to a population reach for the subsets of the union of the time intervals.

18. The computer readable medium of claim 17 , wherein:

the pseudo universe estimate of the recorded audience corresponds to a first universe estimate that assures independency among recorded audience data for the subsets of the union of the time intervals; and

the pseudo universe estimate of the population audience corresponds to a second universe estimate that assures independency among population audience data for the subsets of the union of the time intervals.

19. The computer readable medium of claim 10 , wherein the error corresponds to a difference between (A) a first relationship based on the population reach estimate of the union of the time intervals and the pseudo universe estimate of the population audience of the union of the time intervals, and (B) a second relationship based on population reach estimates for subsets of the union of the time intervals and the pseudo universe estimate of the population audience of the union of the time intervals.

20. A method comprising:

determining, by executing an instruction with one or more processors, a population reach estimate of a union of time intervals for which media ratings data is available, the population reach estimate based on a pseudo universe estimate of a population audience corresponding to the union of the time intervals;

determining, by executing an instruction with the one or more processors, a pseudo universe estimate of a recorded audience corresponding to the union of the time intervals;

determining, by executing an instruction with the one or more processors, the pseudo universe estimate of the population audience based on the pseudo universe estimate of the recorded audience; and

in response to a decision to update the pseudo universe estimate of the population audience to reduce an error of the population reach estimate:

adjusting, by executing an instruction with the one or more processors, the population reach estimate of the union;

applying, by executing an instruction with the one or more processors, a correction to the population reach estimate of the union to maintain a condition associated with the population reach estimate; and

outputting, by executing an instruction with the one or more processors, the population reach estimate of the union when the error of the population reach estimate satisfies a threshold.

21. The method of claim 20 , further including:

adjusting the population reach estimate of the union to fit within a range defined by a lower bound and an upper bound, wherein the applying of the correction to the population reach estimate of the union includes:

determining a correction for the union reach estimate when the union reach estimate is not within the range;

iteratively adjusting the range based on the correction until all unions are satisfy a condition; and

adjusting the union reach estimate based on the correction.

22. The method of claim 20 , wherein the pseudo universe estimate of the recorded audience corresponds to a recorded reach for subsets of the union of the time intervals and a first universe estimate that assures independency among recorded audience data for the subsets of the union of the time intervals, and the pseudo universe estimate of the population audience corresponds to a population reach for the subsets of the union of the time intervals and a second universe estimate that assures independency among population audience data for the subsets of the union of the time intervals.

23. The method of claim 20 , wherein the error corresponds to a difference between (A) a first relationship based on the population reach estimate of the union of the time intervals and the pseudo universe estimate of the population audience of the union of the time intervals, and (B) a second relationship based on population reach estimates for subsets of the union of the time intervals and the pseudo universe estimate of the population audience of the union of the time intervals.