Methods and apparatus to determine a conditional probability based on audience member probability distributions for media audience measurement
Methods, apparatus, systems to determine a conditional probability based on audience member probability distributions for media audience measurement are disclosed. Disclosed example methods for media audience measurement include determining a first audience probability distribution for a first member of a household and determining a second audience probability distribution for a second member of the household. Disclosed example methods also include calculating probabilities for audience combinations of the first member and the second member of the household based on the first audience probability distribution and the second audience probability distribution. Disclosed example methods further include determining a household audience characteristic probability based on the calculated probabilities of the audience combinations of the household. The household audience characteristic indicates likelihoods of different possible audience compositions of the household for a media event.
1. An apparatus for media audience measurement, the apparatus comprising:
a probability simulator to:
perform a first set of simulations that includes a first simulation for a first member of a household and a second simulation for a second member of the household, the first simulation to randomly select a first value from a first audience probability distribution, the second simulation to randomly select a second value from a second audience probability distribution;
determine a first probability of a first audience combination based on one of the randomly-selected values of the first set of simulations;
perform a second set of simulations that includes a third simulation for the first member and a fourth simulation for the second member, the third simulation to randomly select a third value from the first audience probability distribution, the fourth simulation to randomly select a fourth value from the second audience probability distribution of the second set of simulations; and
determine a second probability of the first audience combination based on the randomly-selected third value and the randomly-selected fourth value; and
a simulation averager to determine an average first audience combination probability based on the first probability and the second probability determined by the probability simulator to reduce a quantity of household data stored in a memory.
2. The apparatus as defined in claim 1 , further including:
a distribution determiner to:
determine the first audience probability distribution for the first member of the household based on the quantity of household data stored in the memory; and
determine the second audience probability distribution for the second member of the household based on the quantity of household data stored in the memory;
the simulation averager to determine the first probability for the first audience combination and a second probability for a second audience combination based on the first audience probability distribution and the second audience probability distribution; and
an audience characteristic determiner to determine a household audience characteristic probability based on the first audience combination and the second audience combination, the household audience characteristic indicating likelihoods of different possible audience compositions of the household for a media event.
3. The apparatus as defined in claim 2 , wherein the distribution determiner is to:
determine the first audience probability distribution based on a first count of a first audience parameter and a second count for a second audience parameter for the first member; and
determine the second audience probability distribution based on a third count of the first audience parameter and a fourth count for the second audience parameter for the second member, the first audience parameter corresponding to exposure to the media event and the second audience parameter corresponding to non-exposure to the media event.
4. The apparatus as defined in claim 3 , wherein the distribution determiner is to:
determine a first beta distribution for the first member to determine the first audience probability distribution; and
determine a second beta distribution for the second member to determine the second audience probability distribution.
5. The apparatus as defined in claim 2 , wherein the distribution determiner is to:
determine a first Dirichlet distribution for the first member to determine the first audience probability distribution, the first Dirichlet distribution being determined based on a first count of a first audience parameter, a second count for a second audience parameter, and a third count for a third audience parameter for the first member; and
determine a second Dirichlet distribution for the second member determine the second audience probability distribution, the second Dirichlet distribution being determined based on a fourth count of the first audience parameter, a fifth count for the second audience parameter, and a sixth count for the third audience parameter for the second member, the first audience parameter corresponding to exposure to the media event via a first media presentation device of the household, the second audience parameter corresponding to exposure to the media event via a second media presentation device of the household, and the third audience parameter corresponds to non-exposure to the media event.
6. The apparatus as defined in claim 2 , wherein, to determine the household audience characteristic probability, the audience characteristic determiner is to determine a conditional probability based on the first audience combination and the second audience combination, the conditional probability indicative of a probability of a second event given a first event has occurred.
7. A tangible computer readable storage medium comprising instructions which, when executed, cause a machine to at least:
perform a first set of simulations that includes a first simulation for a first member of a household and a second simulation for a second member of the household, the first simulation to randomly select a first value from a first audience probability distribution, the second simulation to randomly select a second value from a second audience probability distribution;
determine a first probability of a first audience combination based on a randomly-selected first value and a randomly-selected second value of the first set of simulations;
perform a second set of simulations that includes a third simulation for the first member and a fourth simulation for the second member, the third simulation to randomly select a third value from the first audience probability distribution, the fourth simulation to randomly select a fourth value from the second audience probability distribution of the second set of simulations;
determine a second probability of the first audience combination based on the randomly-selected third value and the randomly-selected fourth value; and
determine an average first audience combination probability based on the first probability and the second probability to reduce a quantity of household data stored in a memory.
8. The tangible computer readable storage medium as defined in claim 7 , the instructions further cause the machine to:
determine the first audience probability distribution for the first member of the household based on the quantity of household data stored in the memory; and
determine the second audience probability distribution for the second member of the household based on the quantity of household data stored in the memory;
determine the first probability for the first audience combination and a second probability for a second audience combination based on the first audience probability distribution and the second audience probability distribution; and
determine a household audience characteristic probability based on the first audience combination and the second audience combination, the household audience characteristic indicating likelihoods of different possible audience compositions of the household for a media event.
9. The tangible computer readable storage medium as defined in claim 8 , the instructions further cause the machine to:
determine the first audience probability distribution based on a first count of a first audience parameter and a second count for a second audience parameter for the first member; and
determine the second audience probability distribution based on a third count of the first audience parameter and a fourth count for the second audience parameter for the second member, the first audience parameter corresponding to exposure to the media event and the second audience parameter corresponding to non-exposure to the media event.
10. The tangible computer readable storage medium as defined in claim 9 , the instructions further cause the machine to:
determine a first beta distribution for the first member to determine the first audience probability distribution; and
determine a second beta distribution for the second member to determine the second audience probability distribution.
11. The tangible computer readable storage medium as defined in claim 8 , the instructions further cause the machine to:
determine a first Dirichlet distribution for the first member to determine the first audience probability distribution, the first Dirichlet distribution being determined based on a first count of a first audience parameter, a second count for a second audience parameter, and a third count for a third audience parameter for the first member; and
determine a second Dirichlet distribution for the second member determine the second audience probability distribution, the second Dirichlet distribution being determined based on a fourth count of the first audience parameter, a fifth count for the second audience parameter, and a sixth count for the third audience parameter for the second member, the first audience parameter corresponding to exposure to the media event via a first media presentation device of the household, the second audience parameter corresponding to exposure to the media event via a second media presentation device of the household, and the third audience parameter corresponds to non-exposure to the media event.
12. The tangible computer readable storage medium as defined in claim 8 , the instructions further cause the machine to determine a conditional probability based on the first audience combination and the second audience combination, the conditional probability indicative of a probability of a second event given a first event has occurred.
13. The tangible computer readable storage medium as defined in claim 8 , wherein the determining of the household audience characteristic probability based on the first audience probability distribution and the second audience probability distribution reduces an amount of data collected by computer networked data collection systems for the first member and the second member of the household.
14. An apparatus for media audience measurement, the apparatus comprising:
means for simulating to:
perform a first set of simulations that includes a first simulation for a first member of a household and a second simulation for a second member of the household, the first simulation to randomly select a first value from a first audience probability distribution, the second simulation to randomly select a second value from a second audience probability distribution;
determine a first probability of a first audience combination based on one of the randomly-selected values of the first set of simulations;
perform a second set of simulations that includes a third simulation for the first member and a fourth simulation for the second member, the third simulation to randomly select a third value from the first audience probability distribution, the fourth simulation to randomly select a fourth value from the second audience probability distribution of the second set of simulations; and
determine a second probability of the first audience combination based on the randomly-selected third value and the randomly-selected fourth value; and
means for averaging a simulation to determine an average first audience combination probability based on the first probability and the second probability determined by the means for simulating to reduce a quantity of household data stored in a memory.
15. The apparatus as defined in claim 14 , further including:
means for determining a distribution to:
determine the first audience probability distribution for the first member of the household based on the quantity of household data stored in the memory; and
determine the second audience probability distribution for the second member of the household based on the quantity of household data stored in the memory;
the means for averaging a simulation to determine the first probability for the first audience combination and a second probability for a second audience combination based on the first audience probability distribution and the second audience probability distribution; and
means for determining an audience characteristic to determine a household audience characteristic probability based on the first audience combination and the second audience combination, the household audience characteristic indicating likelihoods of different possible audience compositions of the household for a media event.
16. The apparatus as defined in claim 15 , wherein the means for determining a distribution is to:
determine the first audience probability distribution based on a first count of a first audience parameter and a second count for a second audience parameter for the first member; and
determine the second audience probability distribution based on a third count of the first audience parameter and a fourth count for the second audience parameter for the second member, the first audience parameter corresponding to exposure to the media event and the second audience parameter corresponding to non-exposure to the media event.
17. The apparatus as defined in claim 15 , wherein the means for determining a distribution is to:
determine a first beta distribution for the first member to determine the first audience probability distribution; and
determine a second beta distribution for the second member to determine the second audience probability distribution.
18. The apparatus as defined in claim 15 , wherein the means for determining a distribution is to:
determine a first Dirichlet distribution for the first member to determine the first audience probability distribution, the first Dirichlet distribution being determined based on a first count of a first audience parameter, a second count for a second audience parameter, and a third count for a third audience parameter for the first member; and
determine a second Dirichlet distribution for the second member determine the second audience probability distribution, the second Dirichlet distribution being determined based on a fourth count of the first audience parameter, a fifth count for the second audience parameter, and a sixth count for the third audience parameter for the second member, the first audience parameter corresponding to exposure to the media event via a first media presentation device of the household, the second audience parameter corresponding to exposure to the media event via a second media presentation device of the household, and the third audience parameter corresponds to non-exposure to the media event.
19. The apparatus as defined in claim 15 , wherein, to determine the household audience characteristic probability, the means for determining an audience characteristic is to determine a conditional probability based on the first audience combination and the second audience combination, the conditional probability indicative of a probability of a second event given a first event has occurred.