Methods and apparatus to model on/off states of media presentation devices based on return path data
Methods and apparatus to model on/off states of media presentation devices based on return path data are disclosed. An example method includes generating a modelled tuning segment distribution indicative of modelled durations of modelled tuning segments. The modelled tuning segments is based on panel tuning segments during which panelists were exposed to first media. The example method further includes obtaining return path data (RPD) tuning information reported from an RPD device. The RPD tuning information is indicative of a reported RPD tuning segment during which the RPD device was accessing second media. The example method also includes estimating a set-on time for a media set associated with the RPD device based on the RPD tuning information and the modelled tuning segment distribution. The set-on time is indicative of a period of time when the media set is powered on.
1. An apparatus comprising:
a return path data (RPD) model generator, implemented via a processor, to:
determine actual durations of panel tuning segments during which panelists were exposed to first media; and
calculate modelled durations for modelled tuning segments by:
extending ones of the actual durations of the panel tuning segments by the shorter of (1) a substantial extension period and (2) a gap in time between ones of the panel tuning segments and a next subsequent panel tuning segment; and
reducing ones of the extended actual durations based on a standby timer length;
a distribution generator, implemented via the processor, to generate a modelled tuning segment distribution indicative of the modelled durations of the modelled tuning segments;
an RPD tuning information analyzer, implemented via the processor, to analyze RPD tuning information reported from an RPD device, the RPD tuning information indicative of a reported RPD tuning segment during which the RPD device was accessing second media, the standby timer length associated with the RPD device; and
a set-on time calculator, implemented via the processor, to estimate a set-on time for a media set associated with the RPD device based on the RPD tuning information and the modelled tuning segment distribution, the set-on time indicative of a period of time when the media set is powered on.
2. The apparatus of claim 1 , wherein the distribution generator is to generate a panel tuning segment distribution indicative of the actual durations of the panel tuning segments, the RPD tuning information analyzer to determine a probability percentage on the modelled tuning segment distribution corresponding to a reported duration of the reported RPD tuning segment and to determine a deterministic-estimated duration based on where the probability percentage falls on the panel tuning segment distribution, the set-on time estimated based on the deterministic-estimated duration.
3. The apparatus of claim 2 , wherein the RPD tuning information analyzer is to determine a probabilistic-estimated duration based on where a randomly generated number falls on the panel tuning segment distribution, the set-on time calculator to determine the set-on time based on a weighted average of the deterministic-estimated duration and the probabilistic-estimated duration.
4. The apparatus of claim 1 , wherein the ones of the extended actual durations reduced based on the standby timer length are associated with a first portion of the panel tuning segments, and the RPD model generator is to calculate the modelled durations by:
reducing ones of the extended actual durations associated with a second portion of the panel tuning segments to the actual durations of the corresponding panel tuning segments of the second portion.
5. The apparatus of claim 4 , wherein the RPD model generator is to identify the first portion of the panel tuning segments based on a comparison of a randomly generated number to a probability that RPD devices used to access the first media have enabled standby timers.
6. The apparatus of claim 4 , wherein the RPD model generator is to identify the second portion of the panel tuning segments based on a comparison of a randomly generated number to a probability that RPD devices used to access the first media are powered off at a same time that associated media sets are powered off.
7. An apparatus, comprising:
a return path data (RPD) model generator, implemented via a processor, to:
determine actual durations of panel tuning segments during which panelists were exposed to first media;
calculate modelled durations based on the actual durations of the panel tuning segments;
define modelled tuning segments based on the modelled durations; and
identify different series of consecutive ones of the panel tuning segments associated with a same media source and associated with contiguous modelled tuning segments;
a distribution generator, implemented via the processor, to:
generate a modelled tuning segment distribution indicative of the modelled durations of the modelled tuning segments; and
generate a tail-end panel tuning segment distribution indicative of the actual durations of the last panel tuning segments in the different series of consecutive panel tuning segments;
an RPD tuning information analyzer, implemented via the processor, to:
analyze RPD tuning information reported from an RPD device, the RPD tuning information indicative of a reported RPD tuning segment during which the RPD device was accessing second media; and
estimate a tail-end duration for the reported RPD tuning segment based on the tail-end panel tuning segment distribution; and
a set-on time calculator, implemented via the processor, to estimate a set-on time for a media set associated with the RPD device based on the RPD tuning information and the modelled tuning segment distribution, the set-on time indicative of a period of time when the media set is powered on.
8. The apparatus of claim 7 , wherein the RPD model generator is to merge the contiguous modelled tuning segments associated with the different series of consecutive panel tuning segments into different single modelled tuning segments, the set-on time calculator to calculate a second set-on time for the media set corresponding to the tail-end duration for the reported RPD tuning segment when a reported duration for the reported RPD tuning segment is greater than the sum of the tail-end duration for the reported RPD tuning segment and a front-end duration for the reported RPD tuning segment.
9. A method comprising:
determining actual durations of panel tuning segments during which panelists were exposed to first media;
calculating modelled durations for modelled tuning segments by:
extending ones of the actual durations of the panel tuning segments by the shorter of (1) a substantial extension period and (2) a gap in time between ones of the panel tuning segments and a next subsequent panel tuning segment; and
reducing ones of the extended actual durations based on a standby timer length;
generating a modelled tuning segment distribution indicative of the modelled durations of the modelled tuning segments;
obtaining return path data (RPD) tuning information reported from an RPD device, the RPD tuning information indicative of a reported RPD tuning segment during which the RPD device was accessing second media, the standby timer length associated with the RPD device; and
estimating a set-on time for a media set associated with the RPD device based on the RPD tuning information and the modelled tuning segment distribution, the set-on time indicative of a period of time when the media set is powered on.
10. The method of claim 9 , further including:
generating a panel tuning segment distribution indicative of the actual durations of the panel tuning segments;
determining a probability percentage on the modelled tuning segment distribution corresponding to a reported duration of the reported RPD tuning segment; and
determining a deterministic-estimated duration for the set-on time based on where the probability percentage falls on the panel tuning segment distribution.
11. The method of claim 10 , further including:
determining a probabilistic-estimated duration for the set-on time based on where a randomly generated number falls on the panel tuning segment distribution; and
determining the set-on time based on a weighted average of the deterministic-estimated duration and the probabilistic-estimated duration.
12. The method of claim 9 , wherein the ones of the extended actual durations reduced based on the standby timer length are associated with a first portion of the panel tuning segments, and the modelled durations are calculated by:
reducing ones of the extended actual durations associated with a second portion of the panel tuning segments to the actual durations of the corresponding panel tuning segments of the second portion.
13. The method of claim 12 , further including identifying the first portion of the panel tuning segments based on a comparison of a randomly generated number to a probability that RPD devices used to access the first media have enabled standby timers.
14. The method of claim 12 , further including identifying the second portion of the panel tuning segments based on a comparison of a randomly generated number to a probability that RPD devices used to access the first media are powered off at a same time that associated media sets are powered off.
15. A method comprising:
determining actual durations of panel tuning segments during which panelists were exposed to first media;
calculating modelled durations based on the actual durations of the panel tuning segments;
defining modelled tuning segments based on the modelled durations;
generating a modelled tuning segment distribution indicative of the modelled durations of the modelled tuning segments;
obtaining return path data (RPD) tuning information reported from an RPD device, the RPD tuning information indicative of a reported RPD tuning segment during which the RPD device was accessing second media;
estimating a set-on time for a media set associated with the RPD device based on the RPD tuning information and the modelled tuning segment distribution, the set-on time indicative of a period of time when the media set is powered on;
identifying different series of consecutive ones of the panel tuning segments associated with a same media source and associated with contiguous modelled tuning segments;
generating a tail-end panel tuning segment distribution indicative of actual durations of the last panel tuning segments in the different series of consecutive panel tuning segments; and
estimating a tail-end duration for the reported RPD tuning segment based on the tail-end panel tuning segment distribution.
16. The method of claim 15 , further including:
merging the contiguous modelled tuning segments associated with the different series of consecutive panel tuning segments into different single modelled tuning segments; and
calculating a second set-on time for the media set corresponding to the tail-end duration for the reported RPD tuning segment when a reported duration for the reported RPD tuning segment is greater than the sum of the tail-end duration for the reported RPD tuning segment and a front-end duration for the reported RPD tuning segment.
17. A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to at least:
determine actual durations of panel tuning segments during which panelists were exposed to first media;
calculate modelled durations for modelled tuning segments by:
extending ones of the actual durations of the panel tuning segments by the shorter of (1) a substantial extension period and (2) a gap in time between ones of the panel tuning segments and a next subsequent panel tuning segment; and
reducing ones of the extended actual durations based on a standby timer length;
generate a modelled tuning segment distribution indicative of the modelled durations of the modelled tuning segments;
obtain return path data (RPD) tuning information reported from an RPD device, the RPD tuning information indicative of a reported RPD tuning segment during which the RPD device was accessing second media, the standby timer length associated with the RPD device; and
estimate a set-on time for a media set associated with the RPD device based on the RPD tuning information and the modelled tuning segment distribution, the set-on time indicative of a period of time when the media set is powered on.
18. The non-transitory computer readable medium of claim 17 , wherein the instructions further cause the machine to:
generate a panel tuning segment distribution indicative of actual durations of the panel tuning segments;
determine a probability percentage on the modelled tuning segment distribution corresponding to a reported duration of the reported RPD tuning segment; and
determine a deterministic-estimated duration for the set-on time based on where the probability percentage falls on the panel tuning segment distribution.
19. The non-transitory computer readable medium of claim 18 , wherein the instructions further cause the machine to:
determine a probabilistic-estimated duration for the set-on time based on where a randomly generated number falls on the panel tuning segment distribution; and
determine the set-on time based on a weighted average of the deterministic-estimated duration and the probabilistic-estimated duration.
20. The non-transitory computer readable medium of claim 17 , wherein the ones of the extended actual durations reduced based on the standby timer length are associated with a first portion of the panel tuning segments, the instructions to further cause the machine to calculate the modelled durations by reducing ones of the extended actual durations associated with a second portion of the panel tuning segments to the actual durations of the corresponding panel tuning segments of the second portion.
21. The non-transitory computer readable medium of claim 20 , wherein the instructions further cause the machine to identify the first portion of the panel tuning segments based on a comparison of a randomly generated number to a probability that RPD devices used to access the first media have enabled standby timers.
22. The non-transitory computer readable medium of claim 20 , wherein the instructions further cause the machine to identify the second portion of the panel tuning segments based on a comparison of a randomly generated number to a probability that RPD devices used to access the first media are powered off at a same time that associated media sets are powered off.
23. A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to at least:
determine actual durations of panel tuning segments during which panelists were exposed to first media;
calculate modelled durations based on the actual durations of the panel tuning segments;
define modelled tuning segments based on the modelled durations;
generate a modelled tuning segment distribution indicative of the modelled durations of the modelled tuning segments;
obtain return path data (RPD) tuning information reported from an RPD device, the RPD tuning information indicative of a reported RPD tuning segment during which the RPD device was accessing second media;
estimate a set-on time for a media set associated with the RPD device based on the RPD tuning information and the modelled tuning segment distribution, the set-on time indicative of a period of time when the media set is powered on;
identify different series of consecutive ones of the panel tuning segments associated with a same media source and associated with contiguous modelled tuning segments;
generate a tail-end panel tuning segment distribution indicative of actual durations of the last panel tuning segments in the different series of consecutive panel tuning segments; and
estimate a tail-end duration for the reported RPD tuning segment based on the tail-end panel tuning segment distribution.
24. The non-transitory computer readable medium of claim 23 , wherein the instructions further cause the machine to:
merge the contiguous modelled tuning segments associated with the different series of consecutive panel tuning segments into different single modelled tuning segments; and
calculate a second set-on time for the media set corresponding to the tail-end duration for the reported RPD tuning segment when a reported duration for the reported RPD tuning segment is greater than the sum of the tail-end duration for the reported RPD tuning segment and a front-end duration for the reported RPD tuning segment.