Methods and apparatus to assign demographic information to panelists
Methods and apparatus to assign demographic information to panelists are disclosed. An example disclosed method includes generating decoy database proprietor identifiers to protect privacies of members of panelist households corresponding to panelist database proprietor identifiers, the decoy database proprietor identifiers to be determined based on a probability density function so that a quantity of the decoy database proprietor identifiers is less than would be used if the decoy database proprietor identifiers were selected by a random selection process. The example method also includes querying a server at a database proprietor using the panelist database proprietor identifiers and the decoy database proprietor identifiers, to obtain demographic information and assigning, by executing an instruction with a processor, the panelist database proprietor identifiers to panelists in the panelist households based on the demographic information obtained from the server at the database proprietor.
1. A method comprising:
generating, by executing an instruction with a processor, decoy database proprietor identifiers to protect privacies of members of panelist households corresponding to panelist database proprietor identifiers, the decoy database proprietor identifiers to be determined based on a probability density function so that a quantity of the decoy database proprietor identifiers is less than would be used if the decoy database proprietor identifiers were selected by a random selection process;
querying, by executing an instruction with a processor, a server at a database proprietor using the panelist database proprietor identifiers and the decoy database proprietor identifiers, to obtain demographic information; and
assigning, by executing an instruction with a processor, the panelist database proprietor identifiers to panelists in the panelist households based on the demographic information obtained from the server at the database proprietor.
2. The method of claim 1 , further including arranging, randomly, the panelist database proprietor identifiers and the decoy database proprietor identifiers into a query to perform the querying of the server at the database proprietor.
3. The method of claim 1 , further including determining the probability density function based on independent distributions of numbers within the panelist database proprietor identifiers.
4. The method of claim 1 , further including determining the probability density function based on dependent distributions of numbers within the panelist database proprietor identifiers.
5. The method of claim 1 , further including generating the decoy database proprietor identifiers using a confidence level of the probability density function.
6. The method of claim 1 , further including generating a first one of the decoy database proprietor identifiers based on the probability density function by, for each of a plurality of digits of the first one of the decoy database proprietor identifiers, selecting a numeric value for the digit based on the probability density function.
7. The method of claim 1 , further including, in response to querying the server at the database proprietor using the panelist database proprietor identifiers and the decoy database proprietor identifiers:
receiving (a) the demographic information corresponding to the panelist database proprietor identifiers and the decoy database proprietor identifiers that are associated with subscribers to the database proprietor, and (b) errors indicating that particular ones of the decoy database proprietor identifiers are not associated with the subscribers to the database proprietor; and
regenerating the probability density function based on the panelist database proprietor identifiers and the decoy database proprietor identifiers that are associated with the subscribers to the database proprietor.
8. An apparatus comprising:
means for querying a database proprietor using panelist database proprietor identifiers and decoy database proprietor identifiers, the means for querying to:
obtain demographic information associated with the panelist database proprietor identifiers; and
obtain (a) at least some of the demographic information corresponding to the panelist database proprietor identifiers and the decoy database proprietor identifiers that are associated with subscribers to the database proprietor, and (b) errors indicating that particular ones of the decoy database proprietor identifiers are not associated with the subscribers to the database proprietor;
means for generating to:
generate decoy database proprietor identifiers based on probability density functions; and
in response to the means for querying querying the database proprietor, regenerate the probability density functions based on the panelist database proprietor identifiers and the decoy database proprietor identifiers that are associated with the subscribers to the database proprietor; and
means for assigning the panelist database proprietor identifiers to panelists based on the demographic information obtained from the database proprietor.
9. The apparatus of claim 8 , further including means for randomly arranging the panelist database proprietor identifiers and the decoy database proprietor identifiers into a query to perform the querying of the database proprietor.
10. The apparatus of claim 8 , wherein the means for generating is to regenerate the probability density functions based on independent distributions of numbers within the panelist database proprietor identifiers.
11. The apparatus of claim 8 , wherein the means for generating is to regenerate the probability density functions based on dependent distributions of numbers within the panelist database proprietor identifiers.
12. The apparatus of claim 8 , wherein to generate the decoy database proprietor identifiers based on the probability density functions, the means for generating is to, for ones of digits of a corresponding one of the decoy database proprietor identifiers, select a numeric value for the digit based on a corresponding one of the probability density functions.
13. The apparatus of claim 8 , wherein the means for generating is further to generate a quantity of the decoy database proprietor identifiers based on a confidence level of the probability density functions.
14. A non-transitory computer readable storage medium comprising instructions which, when executed, cause a machine to at least:
extract a panelist database proprietor identifier from a cookie, the panelist database proprietor identifier associated with credentials used by a panelist to access a website; and
send a message to a first server of an audience measurement entity, the message including the panelist database proprietor identifier and a panelist identifier associated with the panelist, the panelist database proprietor identifier to be distributed with decoy database proprietor identifiers in a query to a second server at a database proprietor to obtain demographic information, the decoy database proprietor identifiers determined based on a probability density function so that a quantity of the decoy database proprietor identifiers is less than would be used if the decoy database proprietor identifiers were selected by a random selection process, the panelist identifier to be used to associate the panelist with a portion of the demographic information.
15. The non-transitory computer readable storage medium of claim 14 , wherein the panelist database proprietor identifier and the decoy database proprietor identifiers are randomly distributed in the query.
16. The non-transitory computer readable storage medium of claim 14 , wherein (1) the panelist database proprietor identifier is a first panelist database proprietor identifier, (2) the query further includes a second panelist database proprietor identifier, and (3) the probability density function is based on independent distributions of numbers within the first panelist database proprietor identifier and the second panelist database identifier.
17. The non-transitory computer readable storage medium of claim 14 , wherein (1) the panelist database proprietor identifier is a first panelist database proprietor identifier, (2) the query further includes a second panelist database proprietor identifier, and (3) the probability density function based is based on dependent distributions of numbers within the first panelist database proprietor identifier and the second panelist database identifier.
18. The non-transitory computer readable storage medium of claim 14 , wherein the decoy database proprietor identifiers are generated using a confidence level of the probability density function.
19. The non-transitory computer readable storage medium of claim 14 , wherein the panelist identifier is provided by the audience measurement entity via a panelist registration website.
20. The non-transitory computer readable storage medium of claim 14 , wherein the demographic information includes errors corresponding to ones of the decoy database proprietor identifiers not associated with subscribers to the database proprietor.