Methods and apparatus to calibrate return path data for audience measurement

1. An apparatus comprising:

communications interface circuitry to receive, via a network, first and second return path data from a plurality of households that include set top boxes, the plurality of households associated with a geographic region having a population such that the households number in at least the thousands;

memory to store the first and second return path data;

instructions; and

processor circuitry to execute the instructions to:

classify first viewing periods, associated with respective ones of the households, into at least one of a live tuning classification or a playback tuning classification based on one or more segments of the first return path data, the first return path data corresponding to the first viewing periods; and

classify second viewing periods, associated with respective ones of the households, into a gap tuning classification based on one or more segments of the second return path data, the second return path data corresponding to the second viewing periods, the gap tuning classification to indicate the second return path data is associated with missing tuning data;

select at least one of a plurality of available methods to rectify the missing tuning data, the at least one of the plurality of available methods to be selected based on a hierarchy of different tuning classifications, the different tuning classifications including the live tuning classification and the playback tuning classification; and

rectify the second return path data associated with the missing tuning data, using the at least one of the plurality of available methods, based on valid tuning data included in the first return path data, rectification of the second return path data to improve operation of a computer determining media ratings based on the second return path data by correcting for bias in the second return path data.

2. The apparatus of claim 1 , wherein the processor circuitry is to replace the missing tuning data associated with the second viewing periods with the tuning data included in one or more segments of return path data associated with the first viewing periods to rectify the missing tuning data.

3. An apparatus comprising:

communications interface circuitry to receive, via a network, first and second return path data from a plurality of households that include set top boxes, the plurality of households associated with a geographic region having a population such that the households number in at least the thousands;

instructions; and

processor circuitry to execute the instructions to:

classify first viewing periods, associated with respective ones of the households, into at least one of a live tuning classification or a playback tuning classification based on one or more segments of the first return path data, the first return path data corresponding to the first viewing period;

classify second viewing periods, associated with respective ones of the households, into a gap tuning classification based on one or more segments of the second return path data, the second return path data corresponding to the second viewing periods, the gap tuning classification to indicate the second return path data is associated with missing tuning data;

determine whether a segment of tuning data covered by the first viewing periods has a start time and an end time that are consistent relative to a broadcast start time and a broadcast end time;

determine the first return path data includes valid tuning data based on the start time and the end time being consistent relative to the broadcast start time and the broadcast end time; and

rectify the second return path data associated with the missing tuning data based on the valid tuning data included in the first return path data, rectification of the second return path data to improve operation of a computer determining media ratings based on the second return path data by correcting for bias in the second return path data.

4. The apparatus of claim 3 , wherein the first return path data is obtained from a non-panelist household, and the processor circuitry is to:

generate activity validation data based on third return path data obtained from a panelist household; and

when the start time and the end time of the segment of tuning data for the first return path data are not consistent, adjust the first return path data to include the valid tuning data based on the activity validation data.

5. The apparatus of claim 1 , wherein a first one of the first viewing periods, associated with a first one of the households, covers multiple segments of tuning data, and the processor circuitry is to:

determine whether ones of the multiple segments of tuning data are associated with at least one tuning source;

when more than one of the multiple segments of tuning data is not associated with at least one tuning source, compare a total tuning duration of the first one of the first viewing periods to mapped tuning duration of the first one of the first viewing periods, the mapped tuning duration corresponding to a duration of the ones of the multiple segments of tuning data associated with at least one tuning source; and

determine the first return path data includes the valid tuning data based on the comparison of the total tuning duration to the mapped tuning duration.

6. A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to at least:

receive, via a network, first and second return path data from a plurality of households that include set top boxes, the plurality of households associated with a geographic region having a population such that the households number in at least the thousands;

classify first viewing periods, associated with respective ones of the households, into at least one of a live tuning classification or a playback tuning classification based on one or more segments of the first return path data, the first return path data corresponding to the first viewing periods;

classify second viewing periods, associated with respective ones of the households, into a gap tuning classification based on one or more segments of the second return path data, the second return path data corresponding to the second viewing periods, the gap tuning classification to indicate the second return path data is associated with missing tuning data;

select at least one of a plurality of available methods to rectify the missing tuning data, the at least one of the plurality of available methods to be selected based on a hierarchy of different tuning classifications, the different tuning classifications including the live tuning classification and the playback tuning classification; and

rectify the second return path data associated with the missing tuning data, using the at least one of the plurality of available methods, based on valid tuning data included in the first return path data, rectification of the second return path data to improve operation of a computer determining media ratings based on the second return path data by correcting for bias in the second return path data.

7. The non-transitory computer readable medium of claim 6 , wherein the instructions cause the machine to replace the missing tuning data associated with the second viewing periods with the tuning data included in one or more segments of return path data associated with the first viewing periods to rectify the missing tuning data.

8. A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to at least:

receive, via a network, first and second return path data from a plurality of households that include set top boxes, the plurality of households associated with a geographic region having a population such that the households number in at least the thousands;

classify first viewing periods, associated with respective ones of the households, into at least one of a live tuning classification or a playback tuning classification based on one or more segments of the first return path data, the first return path data corresponding to the first viewing period;

classify second viewing periods, associated with respective ones of the households, into a gap tuning classification based on one or more segments of the second return path data, the second return path data corresponding to the second viewing periods, the gap tuning classification to indicate the second return path data is associated with missing tuning data;

determine whether a segment of tuning data covered by the first viewing periods has a start time and an end time that are consistent relative to a broadcast start time and a broadcast end time;

determine the first return path data includes valid tuning data based on the start time and the end time being consistent relative to the broadcast start time and the broadcast end time; and

rectify the second return path data associated with the missing tuning data based on the valid tuning data included in the first return path data, rectification of the second return path data to improve operation of a computer determining media ratings based on the second return path data by correcting for bias in the second return path data.

9. The non-transitory computer readable medium of claim 8 , wherein the first return path data is obtained from a non-panelist household, and the instructions cause the machine to:

generate activity validation data based on third return path data obtained from a panelist household; and

when the start time and the end time of the segment of tuning data for the first return path data are not consistent, adjust the first return path data to include the valid tuning data based on the activity validation data.

10. The non-transitory computer readable medium of claim 6 , wherein a first one of the first viewing periods, associated with a first one of the households, covers multiple segments of tuning data, and the instructions further cause the machine to:

determine whether ones of the multiple segments of tuning data are associated with at least one tuning source;

when more than one of the multiple segments of tuning data is not associated with at least one tuning source, compare a total tuning duration of the first one of the first viewing periods to mapped tuning duration of the first one of the first viewing periods, the mapped tuning duration corresponding to a duration of the ones of the multiple segments of tuning data associated with at least one tuning source; and

determine the first return path data includes the valid tuning data based on the comparison of the total tuning duration to the mapped tuning duration.

11. An apparatus comprising:

communications interface circuitry to receive, via a network, return path data from a plurality of households that include set top boxes, the plurality of households associated with a geographic region having a population such that the households number in at least the thousands;

memory to store the return path data;

instructions; and

processor circuitry to execute the instructions to:

classify viewing periods, associated with respective ones of the households, the viewing periods associated with one or more segments of the return path data into two or more tuning classifications based on the one or more segments of the return path data;

calculate a total reported tuning duration for a first viewing period of the viewing periods based on individual tuning durations for the first viewing period associated with respective ones of the two or more tuning classifications;

compare the total reported tuning duration to a duration threshold; and

either retain or discard the return path data associated with the first view period based on the comparison to improve operation of a computer determining media ratings by correcting for bias in the return path data.

12. The apparatus of claim 11 , wherein the two or more tuning classifications includes at least one of live tuning or playback tuning.

13. The apparatus of claim 11 , wherein the processor circuitry is to:

determine whether the return path data is associated with an error based on the comparison;

retain the return path data when the return path data is not associated with the error; and

discard the return path data when the return path data is associated with the error.

14. The apparatus of claim 11 , wherein the duration threshold is greater than a duration of the first viewing period.

15. The apparatus of claim 11 , wherein the processor circuitry is to determine a number of tuning sources tuned by the set top boxes during the viewing periods based on the one or more segments of return path data associated with the viewing periods.

16. The apparatus of claim 15 , wherein the processor circuitry is to determine the number of tuning sources based on tuning sources tuned by the set top boxes for at least a threshold portion of ones of the viewing periods.

17. The apparatus of claim 15 , wherein the processor circuitry is to classify the viewing periods as a conflicted tuning period when the number of tuning sources satisfies a tuning source threshold.

18. The apparatus of claim 17 , wherein the processor circuitry is to:

classify multiple viewing periods associated with different segments of the return path data from a first one of the set top boxes into the tuning classifications, the multiple viewing periods including the first viewing period; and

determine whether the return path data is useable based on a comparison of a proportion of the multiple viewing periods classified as conflicted tuning periods to a conflicted tuning threshold.

19. The apparatus of claim 1 , wherein the hierarchy of different tuning classifications defines a preference of the live tuning classification over the playback tuning classification.

20. The apparatus of claim 1 , wherein the hierarchy of different tuning classifications defines a preference of the playback tuning classification over a stand-by classification.