CPC H04N 21/25883 (2013.01) [H04N 21/44204 (2013.01); H04N 21/44226 (2020.08); H04N 21/4661 (2013.01); H04N 21/4665 (2013.01); H04N 21/4667 (2013.01)] | 21 Claims |
1. A method to determine demographics for a non-panelist household, the method comprising:
calculating, by executing an instruction with a processor, a first demographic constraint average and a second demographic constraint average based on a first demographic distribution of a first media event of the non-panelist household and a second demographic distribution of a second media event of the non-panelist household, the first demographic distribution includes a first probability that the first media event is associated with a first demographic constraint and a second probability that the first media event is associated with a second demographic constraint, the second demographic distribution includes a third probability that the second media event is associated with the first demographic constraint and a fourth probability that the second media event is associated with the second demographic constraint;
based on the first demographic constraint average and a first constraint probability, determining, by executing an instruction with the processor, a first likelihood of the non-panelist household being associated with the first demographic constraint, the first constraint probability based on the first probability of the first demographic distribution and the third probability of the second demographic distribution;
based on the second demographic constraint average and a second constraint probability, determining, by executing an instruction with the processor, a second likelihood of the non-panelist household being associated with the second demographic constraint, the second constraint probability based on the second probability of the first demographic distribution and the fourth probability of the second demographic distribution; and
estimating, by executing an instruction with the processor, a household characteristic of the non-panelist household based on the first likelihood and the second likelihood.
|