Methods and apparatus to model on/off states of media presentation devices based on return path data

1 . An audience measurement computing system comprising:

a processor;

memory having stored thereon computer readable instructions that, when executed by the processor, cause the audience measurement computing system to perform operations including:

obtaining return path data indicative of a first tuning segment during which a set top box accessed first media;

determining a standby timer duration associated with the set top box;

accessing a modeled tuning segment duration distribution corresponding to the determined standby timer duration, wherein the modeled tuning segment duration distribution is based on modifications to at least some of a set of actual durations of second tuning segments representative of respective time durations during which monitored media presentation devices accessed respective media during the set of actual durations, wherein the modifications are based on the determined standby timer duration; and

estimating a presentation time duration corresponding to the first tuning segment during which the first media accessed by the set top box is presented on a media presentation device based on (i) the modeled tuning segment duration distribution, (ii) the set of actual durations, and (iii) the first tuning segment.

2 . The audience measurement computing system of claim 1 , wherein the operations further include crediting the first media with exposure during the presentation time duration.

3 . The audience measurement computing system of claim 1 , wherein the operations further include obtaining data indicative of the second tuning segments.

4 . The audience measurement computing system of claim 3 , wherein the data indicative of the second tuning segments is obtained from meters associated with a set of panelists, and wherein ones of the meters are associated with respective ones of a set of media presentation devices disposed in respective media presentation environments.

5 . The audience measurement computing system of claim 1 , wherein the operations further include:

identifying a device type of the set top box; and

determining the standby timer duration by associating the standby timer duration with the identified device type.

6 . The audience measurement computing system of claim 1 , wherein the operations further include:

obtaining additional return path data indicative of a set of multiple tuning segments aggregated from a plurality of set top boxes including the set top box, each tuning segment in the set of multiple tuning segments having a corresponding reported duration; and

identifying a prominent reported duration over-represented among a distribution of the reported durations of the set of multiple tuning segments, wherein determining the standby timer duration associated with the set top box is based on the identified prominent reported duration.

7 . The audience measurement computing system of claim 1 , wherein the operations further include:

generating the modeled tuning segment duration distribution by:

modifying ones of the set of actual durations of second tuning segments by extending the ones of the set of actual durations based on the standby timer duration; and

not modifying other ones of the set of actual durations of second tuning segments, wherein an amount of the other ones is based on a probability that the set top box has a standby timer feature enabled.

8 . A computer-implemented method comprising:

obtaining return path data indicative of a first tuning segment during which a set top box accessed first media;

determining a standby timer duration associated with the set top box;

accessing a modeled tuning segment duration distribution corresponding to the determined standby timer duration, wherein the modeled tuning segment duration distribution is based on modifications to at least some of a set of actual durations of second tuning segments representative of respective time durations during which monitored media presentation devices accessed respective media during the set of actual durations, wherein the modifications are based on the determined standby timer duration; and

estimating a presentation time duration corresponding to the first tuning segment during which the first media accessed by the set top box is presented on a media presentation device based on (i) the modeled tuning segment duration distribution, (ii) the set of actual durations, and (iii) the first tuning segment.

9 . The computer-implemented method of claim 8 , further comprising crediting the first media with exposure during the presentation time duration.

10 . The computer-implemented method of claim 8 , further comprising obtaining data indicative of the second tuning segments.

11 . The computer-implemented method of claim 10 , wherein the data indicative of the second tuning segments is obtained from meters associated with a set of panelists, and wherein ones of the meters are associated with respective ones of a set of media presentation devices disposed in respective media presentation environments.

12 . The computer-implemented method of claim 8 , further comprising:

identifying a device type of the set top box; and

determining the standby timer duration by associating the standby timer duration with the identified device type.

13 . The computer-implemented method of claim 8 , further comprising:

obtaining additional return path data indicative of a set of multiple tuning segments aggregated from a plurality of set top boxes including the set top box, each tuning segment in the set of multiple tuning segments having a corresponding reported duration; and

identifying a prominent reported duration over-represented among a distribution of the reported durations of the set of multiple tuning segments, wherein determining the standby timer duration associated with the set top box is based on the identified prominent reported duration.

14 . The computer-implemented method of claim 8 , further comprising:

generating the modeled tuning segment duration distribution by:

modifying ones of the set of actual durations of second tuning segments by extending the ones of the set of actual durations based on the standby timer duration; and

not modifying other ones of the set of actual durations of second tuning segments, wherein an amount of the other ones is based on a probability that the set top box has a standby timer feature enabled.

15 . A non-transitory computer-readable medium having stored thereon computer readable instructions that, when executed by a processor, cause performance of operations comprising:

obtaining return path data indicative of a first tuning segment during which a set top box accessed first media;

determining a standby timer duration associated with the set top box;

accessing a modeled tuning segment duration distribution corresponding to the determined standby timer duration, wherein the modeled tuning segment duration distribution is based on modifications to at least some of a set of actual durations of second tuning segments representative of respective time durations during which monitored media presentation devices accessed respective media during the set of actual durations, wherein the modifications are based on the determined standby timer duration; and

estimating a presentation time duration corresponding to the first tuning segment during which the first media accessed by the set top box is presented on a media presentation device based on (i) the modeled tuning segment duration distribution, (ii) the set of actual durations, and (iii) the first tuning segment.

16 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise crediting the first media with exposure during the presentation time duration.

17 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise obtaining data indicative of the second tuning segments from meters associated with a set of panelists, and wherein ones of the meters are associated with respective ones of a set of media presentation devices disposed in respective media presentation environments.

18 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:

identifying a device type of the set top box; and

determining the standby timer duration by associating the standby timer duration with the identified device type.

19 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:

obtaining additional return path data indicative of a set of multiple tuning segments aggregated from a plurality of set top boxes including the set top box, each tuning segment in the set of multiple tuning segments having a corresponding reported duration; and

identifying a prominent reported duration over-represented among a distribution of the reported durations of the set of multiple tuning segments, wherein determining the standby timer duration associated with the set top box is based on the identified prominent reported duration.

20 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise:

generating the modeled tuning segment duration distribution by:

modifying ones of the set of actual durations of second tuning segments by extending the ones of the set of actual durations based on the standby timer duration; and

not modifying other ones of the set of actual durations of second tuning segments, wherein an amount of the other ones is based on a probability that the set top box has a standby timer feature enabled.