Methods and apparatus to compensate impression data for misattribution and/or non-coverage by a database proprietor

Abstract

Methods and apparatus to compensate impression data for misattribution and non-coverage by a database proprietor are disclosed. An example method includes obtaining a count of media impressions occurring on a first type of computing device, a first portion of the media impressions corresponding to persons for whom demographic information is recognizable by a database proprietor and a second portion of the media impressions corresponding to persons for whom demographic information is unavailable to the database proprietor; and determining the demographic information for the second portion of the media impressions based on a first probability that media corresponding to the media impressions is accessed on the first type of computing device and based on a second probability that media is accessed on a second type of device.

What is claimed is: 
     
         1 . A method, comprising:
 receiving, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device;   sending a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request;   obtaining a count of media impressions occurring on the first type of computing device, a first portion of the media impressions corresponding to persons for whom demographic information is recognizable by a database proprietor and a second portion of the media impressions corresponding to persons for whom demographic information is unavailable to the database proprietor; and   determining, using a processor, the demographic information for the second portion of the media impressions based on a first probability that media corresponding to the media impressions is accessed on the first type of computing device and based on a second probability that media is accessed on a second type of device.   
     
     
         2 . A method as defined in  claim 1 , wherein determining the demographic information comprises multiplying a ratio of the first probability to the second probability by a number of the media impressions attributed to a first demographic group. 
     
     
         3 . A method as defined in  claim 2 , wherein the first probability is a probability that a person in the first demographic group accesses media on the first type of computing device and the second probability is a probability that the person in the first demographic group accesses the media on the second type of computing device. 
     
     
         4 . A method as defined in  claim 2 , further comprising adjusting the media impressions to compensate for incorrect attribution of a subset of the media impressions to second persons in a second demographic group, the number of the media impressions attributed to the first demographic group being determined from the subset of the media impressions that are adjusted to compensate for the incorrect attribution. 
     
     
         5 . A method as defined in  claim 1 , wherein the first type of computing device comprises a mobile device and the second type of device comprises a television. 
     
     
         6 . A method as defined in  claim 1 , wherein the first type of computing device comprises at least one of a smartphone, a tablet computer, or a portable media player. 
     
     
         7 . A method as defined in  claim 1 , wherein the first and second probabilities correspond to a media category of the media. 
     
     
         8 . A method as defined in  claim 7 , wherein the media category is at least one of comedy, drama, political, reality, or a combination media category. 
     
     
         9 . A method as defined in  claim 1 , further comprising, before determining the demographic information, adjusting the media impressions for ones of the media impressions being incorrectly attributed to persons not having caused the ones of the media impressions. 
     
     
         10 . A method as defined in  claim 1 , further comprising calculating the first and second probabilities based on survey responses to a survey of people, calculating the first probability comprising determining, from the survey responses, weights associated with at least one of a demographic group, a media category, a type of computing device, or a geographic region, the weights indicating respective probabilities of accessing the media associated with the media impressions on a device type of interest. 
     
     
         11 . A method as defined in  claim 10 , wherein the survey is of at least one of a random panel or a panel of audience members maintained by an audience measurement entity. 
     
     
         12 . A method as defined in  claim 1 , wherein determining the demographic information for the portion of the media impressions comprises:
 determining proportions of the media impressions attributable to different demographic groups corresponding to the persons; and   scaling the proportions of the media impressions to the portion of the media impressions.   
     
     
         13 . A method as defined in  claim 1 , further comprising providing instructions to a publisher, the instructions to be provided by the publisher to the computing device and, when executed by the computing device, to cause the computing device to send the first request. 
     
     
         14 . A method as defined in  claim 1 , further comprising conserving computer processing resources by not communicating with individual online users about their online media access activities and by not requesting survey responses from the online users to determine the first probability that the media corresponding to the media impressions is accessed on the first type of computing device or to determine the second probability that the media is accessed on the second type of device. 
     
     
         15 . A method as defined in  claim 1 , further comprising conserving network communication bandwidth by not communicating with individual online users about their online media access activities and by not requesting survey responses from the online users to determine the first probability that the media corresponding to the media impressions is accessed on the first type of computing device or to determine the second probability that the media is accessed on the second type of device. 
     
     
         16 . An apparatus, comprising:
 an impression collector to:
 receive, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device; and 
 send a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request; 
   an impression information collector to access a count of media impressions occurring on a first type of computing device, a first portion of the media impressions corresponding to persons for whom demographic information is recognizable by a database proprietor and a second portion of the media impressions corresponding to persons for whom demographic information is unavailable to the database proprietor; and   a non-coverage corrector to determine the demographic information for the portion of the media impressions based on a first probability that media corresponding to the media impressions is accessed on the first type of computing device and based on a second probability that media is accessed on a second type of device, at least one of the impression information collector or the non-coverage corrector being implemented by a logic circuit.   
     
     
         17 . An apparatus as defined in  claim 16 , further comprising a non-coverage calculator to multiply a ratio of the first probability to the second probability by a number of the media impressions attributed to a first demographic group. 
     
     
         18 . An apparatus as defined in  claim 17 , wherein the first probability is a probability that a person in the first demographic group accesses media on the first type of computing device and the second probability is a probability that the person in the first demographic group accesses the media on the second type of computing device. 
     
     
         19 . An apparatus as defined in  claim 17 , further comprising a misattribution corrector to adjust the media impressions to compensate for incorrect attribution of a subset of the media impressions to second persons in a second demographic group, the number of the media impressions attributed to the first demographic group being determined from the subset of the media impressions that are adjusted to compensate for the incorrect attribution. 
     
     
         20 . An apparatus as defined in  claim 17 , wherein the first type of computing device comprises a mobile device and the second type of computing device comprises a television. 
     
     
         21 . An apparatus as defined in  claim 17 , wherein the first type of computing device comprises at least one of a smartphone, a tablet computer, or a portable media player. 
     
     
         22 . An apparatus as defined in  claim 17 , wherein the non-coverage calculator is to calculate the first and second probabilities based on survey responses to a survey of people, the non-coverage calculator to calculate the first probability by determining, from the survey responses, weights associated with at least one of a demographic group, a media category, a type of computing device, or a geographic region, the weights indicating respective probabilities of accessing the media associated with the media impressions on a device type of interest. 
     
     
         23 . An apparatus as defined in  claim 22 , wherein the survey is of at least one of a random panel or a panel of audience members maintained by an audience measurement entity. 
     
     
         24 . An apparatus as defined in  claim 16 , wherein the first and second probabilities correspond to a media category of the media. 
     
     
         25 . An apparatus as defined in  claim 24 , wherein the media category is at least one of comedy, drama, political, reality, or a combination media category. 
     
     
         26 . An apparatus as defined in  claim 16 , wherein the non-coverage corrector is to determine the demographic information for the portion of the media impressions by:
 determining proportions of the media impressions attributable to different demographic groups corresponding to the persons; and   scaling the proportions of the media impressions to the portion of the media impressions.   
     
     
         27 . A tangible computer readable storage medium comprising computer readable instructions which, when executed, cause a processor to at least:
 access, at a first internet domain, a first request from a computing device, the first request indicative of access to media at the computing device; and   send a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request;   access a count of media impressions occurring on a first type of computing device, a first portion of the media impressions corresponding to persons for whom demographic information is recognizable by a database proprietor and a second portion of the media impressions corresponding to persons for whom demographic information is unavailable to the database proprietor; and   determining the demographic information for the portion of the media impressions based on a first probability that media corresponding to the media impressions is accessed on the first type of computing device and based on a second probability that media is accessed on a second type of device.   
     
     
         28 . A tangible computer readable storage medium as defined in  claim 27 , wherein the instructions are to cause the processor to determine the demographic information by multiplying a ratio of the first probability to the second probability by a number of the media impressions attributed to a first demographic group. 
     
     
         29 . A tangible computer readable storage medium as defined in  claim 28 , wherein the first probability is a probability that a person in the first demographic group accesses media on the first type of computing device and the second probability is a probability that the person in the first demographic group accesses the media on the second type of computing device. 
     
     
         30 . A tangible computer readable storage medium as defined in  claim 28 , wherein the instructions are further to cause the processor to adjust the media impressions to compensate for incorrect attribution of a subset of the media impressions to second persons in a second demographic group, the number of the media impressions attributed to the first demographic group being determined from the subset of the media impressions that are adjusted to compensate for the incorrect attribution. 
     
     
         31 . A tangible computer readable storage medium as defined in  claim 27 , wherein the first type of computing device comprises a mobile device and the second type of device comprises a television. 
     
     
         32 . A tangible computer readable storage medium as defined in  claim 27 , wherein the first type of computing device comprises at least one of a smartphone, a tablet computer, or a portable media player. 
     
     
         33 . A tangible computer readable storage medium as defined in  claim 27 , wherein the first and second probabilities correspond to a media category of the media. 
     
     
         34 . A tangible computer readable storage medium as defined in  claim 33 , wherein the media category is at least one of comedy, drama, political, reality, or a combination media category. 
     
     
         35 . A tangible computer readable storage medium as defined in  claim 27 , wherein the instructions are further to cause the processor to, before determining the demographic information, adjust the media impressions for ones of the media impressions being incorrectly attributed to persons not having caused the ones of the media impressions. 
     
     
         36 . A tangible computer readable storage medium as defined in  claim 35 , wherein the instructions are further to cause the processor to calculate the first and second probabilities based on survey responses to a survey of people, the instructions to cause the processor to calculate the first probability by determining, from the survey responses, weights associated with at least one of a demographic group, a media category, a type of computing device, or a geographic region, the weights indicating respective probabilities of accessing the media associated with the media impressions on a device type of interest. 
     
     
         37 . A tangible computer readable storage medium as defined in  claim 36 , wherein the survey is of at least one of a random panel or a panel of audience members maintained by an audience measurement entity. 
     
     
         38 . A tangible computer readable storage medium as defined in  claim 27 , wherein the instructions are to cause the processor to determine the demographic information for the portion of the media impressions by:
 determining proportions of the media impressions attributable to different demographic groups corresponding to the persons; and   scaling the proportions of the media impressions to the portion of the media impressions.   
     
     
         39 . A method to compensate impressions of media for misattribution error, the method comprising:
 receiving, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device;   sending a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request;   generating, using a processor, an aggregated audience distribution including a first audience distribution of a first household aggregated with a second audience distribution of a second household, the first audience distribution comprising a distribution of first household members of the first household into demographic groups, based on a survey response of the first household, of ones of the household members who are registered with a database proprietor, the first audience distribution being based on accesses to first media by the first household members;   normalizing, using the processor, the aggregated audience distribution to generate a misattribution correction matrix, the misattribution correction matrix comprising a probability that an impression of the media is attributable to a first demographic group when the database proprietor determines the impression to correspond to a person in a second demographic group; and   compensating misattribution error in the impressions by re-assigning the impressions from the second demographic group to the first demographic group using the misattribution correction matrix.   
     
     
         40 . A method as defined in  claim 39 , further comprising generating a correction index to correct the aggregated audience distribution for at least one of oversampling or undersampling associated with a survey calibration data source, the survey calibration data source indicating the accesses to the media by the first household members and registration statuses of the first household members with the database proprietor. 
     
     
         41 . A method as defined in  claim 40 , wherein the correction index is based on a second probability that a first person in the first demographic group lives with a second person in the second demographic group. 
     
     
         42 . A method as defined in  claim 40 , wherein generating the correction index comprises:
 determining, based on first survey calibration data, a first quantity of first pairs of people representing ones of the first pairs of people including a first person in the first demographic group and a second person in the second demographic group living together;   determining, based on second survey calibration data, a second quantity of second pairs of people representing ones of the second pairs of people including a third person in the first demographic group and a fourth person in the second demographic group living together, the second survey calibration data having higher accuracy than the first survey calibration data; and   determining a ratio of the first quantity and the second quantity.   
     
     
         43 . A method as defined in  claim 39 , wherein the aggregated audience distribution describes, for each first demographic group, a number of people in the second demographic group who are to be attributed to that first demographic group, and normalizing the aggregated audience distribution comprises scaling respective numbers of people in the second demographic group such that a total of the number of people for the second demographic group is a designated value. 
     
     
         44 . A method as defined in  claim 39 , further comprising:
 determining a sharing pattern for the first household, the sharing pattern indicative of ones of the first household members who access a media category and other ones of the first household members who do not access the media category; and   determining a probability density function of device sharing probabilities for the first household members in the first household based on the sharing pattern for the media category, the probability density function indicative of respective probabilities that the first household members access media in the media category, the first audience distribution being based on the device sharing probabilities.   
     
     
         45 . A method as defined in  claim 44 , further comprising aggregating the device sharing probabilities for the first household members when the first household has two or more registered ones of the first household members who are in a same second demographic group. 
     
     
         46 . A method as defined in  claim 39 , further comprising generating the first audience distribution by distributing fractional numbers into the demographic groups, the fractional numbers totaling a count of those ones of the first household members who are registered with a database proprietor. 
     
     
         47 . A method as defined in  claim 46 , wherein generating the first audience distribution does not use cookies. 
     
     
         48 . A method as defined in  claim 46 , wherein generating the first audience distribution and generating the aggregated audience distribution do not use metering software to collect registration statuses of household members with the database proprietor or to collect media access data. 
     
     
         49 . A method as defined in  claim 39 , wherein re-assigning the impressions comprises determining a product of the misattribution correction matrix and an impressions matrix, the impressions matrix indicating numbers of impressions determined by the database proprietor to correspond to respective ones of the demographic groups. 
     
     
         50 . A method as defined in  claim 49 , wherein re-assigning the impressions results in a same total number of impressions as a total of the numbers of impressions in the impressions matrix. 
     
     
         51 . A method as defined in  claim 39 , further comprising providing instructions to a publisher, the instructions to be provided by the publisher to the computing device and, when executed by the computing device, to cause the computing device to send the first request. 
     
     
         52 . A method as defined in  claim 39 , further comprising conserving computer processing resources by not communicating with individual online users about their online media access activities and by not requesting survey responses from the online users to generate the aggregated audience distribution. 
     
     
         53 . A method as defined in  claim 39 , further comprising conserving network communication bandwidth by not communicating with individual online users about their online media access activities and by not requesting survey responses from the online users to generate the aggregated audience distribution. 
     
     
         54 . An apparatus to compensate impressions of media for misattribution error, the apparatus comprising:
 an impression collector to:
 receive, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device; and 
 send a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request; 
   an aggregated distribution generator to generate an aggregated audience distribution including a first audience distribution of a first household aggregated with a second audience distribution of a second household, the first audience distribution comprising a distribution of first household members of the first household into demographic groups, based on a survey response of the first household, of ones of the first household members who are registered with a database proprietor, the first audience distribution being based on accesses to first media by the first household members;   a matrix normalizer to normalize the aggregated audience distribution to generate a misattribution correction matrix, the misattribution correction matrix comprising a probability that an impression of the media is attributable to a first demographic group when the database proprietor determines the impression to correspond to a person in a second demographic group; and   a misattribution corrector to compensate misattribution error in the impressions by re-assigning the impressions from the second demographic group to the first demographic group using the misattribution correction matrix, at least one of the aggregated distribution generator, the matrix normalizer, or the misattribution corrector being implemented by a logic circuit.   
     
     
         55 . An apparatus as defined in  claim 54 , further comprising a matrix corrector to generate a correction index to correct the aggregated audience distribution for at least one of oversampling or undersampling associated with a survey calibration data source, the survey calibration data source indicating the accesses to the media by the first household members and registration statuses of the first household members with the database proprietor. 
     
     
         56 . An apparatus as defined in  claim 55 , wherein the correction index is based on a second probability that a first person in the first demographic group lives with a second person in the second demographic group. 
     
     
         57 . An apparatus as defined in  claim 55 , wherein the matrix corrector is to generate the correction index by:
 determining, based on first survey calibration data, a first quantity of first pairs of people, respective ones of the first pairs of people including a first person in the first demographic group and a second person in the second demographic group living together;   determining, based on second survey calibration data, a second quantity of second pairs of people, respective ones of the second pairs of people including a third person in the first demographic group and a fourth person in the second demographic group living together, the second survey calibration data having higher accuracy than the first survey calibration data; and   determining a ratio of the first quantity and the second quantity.   
     
     
         58 . An apparatus as defined in  claim 54 , wherein the aggregated audience distribution describes, for each first demographic group, a number of people in the second demographic group who are to be attributed to that first demographic group, and the matrix normalizer is to normalize the aggregated audience distribution by scaling respective numbers of people in the second demographic group such that a total of the number of people for the second demographic group is a designated value. 
     
     
         59 . An apparatus as defined in  claim 54 , further comprising a household distribution generator to:
 determine a sharing pattern for the first household, the sharing pattern indicative of ones of the first household members who access a media category and other ones of the first household members who do not access the media category; and   determine a probability density function of device sharing probabilities for the first household members in the first household based on the sharing pattern for the media category, the probability density function indicative of respective probabilities that the first household members access media in the media category, the first audience distribution being based on the device sharing probabilities.   
     
     
         60 . An apparatus as defined in  claim 59 , wherein the aggregated distribution generator is to aggregate the device sharing probabilities for the first household members when the first household has two or more registered ones of the first household members who are in a same second demographic group. 
     
     
         61 . An apparatus as defined in  claim 54 , further comprising a household distribution generator to generate the first audience distribution by distributing fractional numbers into the demographic groups, the fractional numbers totaling a count of those ones of the first household members who are registered with a database proprietor. 
     
     
         62 . An apparatus as defined in  claim 54 , wherein the misattribution corrector is to re-assign the impressions by determining a product of the misattribution correction matrix and an impressions matrix, the impressions matrix indicating numbers of impressions determined by the database proprietor to correspond to respective ones of the demographic groups. 
     
     
         63 . An apparatus as defined in  claim 62 , wherein the misattribution corrector is to re-assign the impressions such that a total number of re-assigned impressions is a same total number of impressions as a total of the numbers of impressions in the impressions matrix. 
     
     
         64 . A computer readable storage medium comprising computer readable instructions which, when executed, cause a processor to at least:
 access, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device; and   send a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request;   generate an aggregated audience distribution including a first audience distribution of a first household aggregated with a second audience distribution of a second household, the first audience distribution comprising a distribution of first household members of the first household into demographic groups, based on a survey response of the first household, of ones of the first household members that are registered with a database proprietor, the first audience distribution being based on accesses to first media by the first household members;   normalize the aggregated audience distribution to generate a misattribution correction matrix, the misattribution correction matrix comprising a probability that an impression of the media is attributable to a first demographic group when the database proprietor determines the impression to correspond to a person in a second demographic group; and   compensate misattribution error in the impressions by re-assigning the impressions from the second demographic group to the first demographic group using the misattribution correction matrix.   
     
     
         65 . A storage medium as defined in  claim 64 , wherein the instructions are further to cause the processor to generate a correction index to correct the aggregated audience distribution for at least one of oversampling or undersampling associated with a survey calibration data source, the survey calibration data source indicating the accesses to of the media by the first household members and registration statuses of the first household members with the database proprietor. 
     
     
         66 . A storage medium as defined in  claim 65 , wherein the correction index is based on a second probability that a first person in the first demographic group lives with a second person in the second demographic group. 
     
     
         67 . A storage medium as defined in  claim 65 , wherein the instructions are to cause the processor to generate the correction index by:
 determining, based on first survey calibration data, a first quantity of first pairs of people, respective ones of the first pairs of people including a first person in the first demographic group and a second person in the second demographic group living together;   determining, based on second survey calibration data, a second quantity of second pairs of people, respective ones of the second pairs of people including a third person in the first demographic group and a fourth person in the second demographic group living together, the second survey calibration data having higher accuracy than the first survey calibration data; and   determining a ratio of the first quantity and the second quantity.   
     
     
         68 . A storage medium as defined in  claim 64 , wherein the aggregated audience distribution describes, for each first demographic group, a number of people in the second demographic group who are to be attributed to that first demographic group, and the instructions are to cause the processor to normalize the aggregated audience distribution by scaling respective numbers of people in the second demographic group such that a total of the number of people for the second demographic group is a designated value. 
     
     
         69 . A storage medium as defined in  claim 64 , wherein the instructions are further to cause the processor to:
 determine a sharing pattern for the first household, the sharing pattern indicative of ones of the first household members who access a media category and other ones of the first household members who do not access the media category; and   determine a probability density function of device sharing probabilities for the first household members in the first household based on the sharing pattern for the media category, the probability density function indicative of respective probabilities that the first household members access media in the media category, the first audience distribution being based on the device sharing probabilities.   
     
     
         70 . A storage medium as defined in  claim 69 , wherein the instructions are further to cause the processor to aggregate the device sharing probabilities for the first household members when the first household has two or more registered ones of the household members who are in a same second demographic group. 
     
     
         71 . A storage medium as defined in  claim 64 , wherein the instructions are to cause the processor to generate the first audience distribution by distributing fractional numbers into the demographic groups, the fractional numbers totaling a count of those ones of the first household members who are registered with a database proprietor. 
     
     
         72 . A storage medium as defined in  claim 64 , wherein the instructions are to cause the processor to re-assign the impressions by determining a product of the misattribution correction matrix and an impressions matrix, the impressions matrix indicating numbers of impressions determined by the database proprietor to correspond to respective ones of the demographic groups. 
     
     
         73 . A storage medium as defined in  claim 72 , wherein the instructions are to cause the processor to re-assign the impressions such that a total number of re-assigned impressions is a same total number of impressions as a total of the numbers of impressions in the impressions matrix. 
     
     
         74 . A method to compensate impressions of media for misattribution error, the method comprising:
 receiving, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device;   sending a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request;   generating, using a processor, an aggregated audience distribution including a first audience distribution of a first household aggregated with a second audience distribution of a second household, the first audience distribution comprising a distribution of first household members of the first household into demographic groups of ones of the first household members that are registered with a database proprietor, the first audience distribution being based on accesses to first media by the first household members, and the aggregated audience distribution being generated without using cookies;   normalizing, using the processor, the aggregated audience distribution to generate a misattribution correction matrix, the misattribution correction matrix comprising a probability that an impression of the media is attributable to a first demographic group when the database proprietor determines the impression to correspond to a person in a second demographic group; and   compensating misattribution error in the impressions by re-assigning the impressions to the first demographic group using the misattribution correction matrix, the impressions being indicative of media accessed on mobile devices.   
     
     
         75 . A method as defined in  claim 74 , further comprising generating a correction index to correct the aggregated audience distribution for at least one of oversampling or undersampling associated with a survey calibration data source, the survey calibration data source indicating the accesses to the media by the first household members and registration statuses of the first household members with the database proprietor. 
     
     
         76 . A method as defined in  claim 75 , wherein the correction index is based on a second probability that a first person in the first demographic group lives with a second person in the second demographic group. 
     
     
         77 . A method as defined in  claim 75 , wherein generating the correction index comprises:
 determining, based on first survey calibration data, a first quantity of first pairs of people, respective ones of the first pairs of people including a first person in the first demographic group and a second person in the second demographic group living together;   determining, based on second survey calibration data, a second quantity of second pairs of people, respective ones of the second pairs of people including a third person in the first demographic group and a fourth person in the second demographic group living together, the second survey calibration data having higher accuracy than the first survey calibration data; and   determining a ratio of the first quantity and the second quantity.   
     
     
         78 . A method as defined in  claim 74 , wherein the aggregated audience distribution describes, for each first demographic group, a number of people in the second demographic group who are to be attributed to that first demographic group, and normalizing the aggregated audience distribution comprises scaling respective numbers of people in the second demographic group such that a total of the number of people for the second demographic group is a designated value. 
     
     
         79 . A method as defined in  claim 74 , further comprising:
 determining a sharing pattern for the first household, the sharing pattern indicative of ones of the first household members who access a media category and other ones of the first household members who do not access the media category; and   determining a probability density function of device sharing probabilities for the first household members in the first household based on the sharing pattern for the media category, the probability density function indicative of respective probabilities that the first household members access media in the media category, the first audience distribution being based on the device sharing probabilities.   
     
     
         80 . A method as defined in  claim 79 , further comprising aggregating the device sharing probabilities for the first household members when the first household has two or more registered ones of the first household members who are in a same second demographic group. 
     
     
         81 . A method as defined in  claim 74 , further comprising generating the first audience distribution by distributing fractional numbers into the demographic groups, the fractional numbers totaling a count of those ones of the first household members who are registered with a database proprietor. 
     
     
         82 . A method as defined in  claim 81 , wherein generating the first audience distribution does not include using cookies. 
     
     
         83 . A method as defined in  claim 81 , wherein generating the first audience distribution and generating the aggregated audience distribution do not use an audience panel. 
     
     
         84 . A method as defined in  claim 74 , further comprising providing instructions to a publisher, the instructions to be provided by the publisher to the computing device and, when executed by the computing device, to cause the computing device to send the first request. 
     
     
         85 . A method as defined in  claim 74 , further comprising conserving computer processing resources by not communicating with individual online users about their online media access activities and by not requesting survey responses from the online users to generate the aggregated audience distribution. 
     
     
         86 . A method as defined in  claim 74 , further comprising conserving network communication bandwidth by not communicating with individual online users about their online media access activities and by not requesting survey responses from the online users to generate the aggregated audience distribution. 
     
     
         87 . An apparatus to compensate impressions of media for misattribution error, the apparatus comprising:
 an impression collector to:
 receive, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device; and 
 send a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request; 
   an aggregated distribution generator to generate an aggregated audience distribution including a first audience distribution of a first household aggregated with a second audience distribution of a second household, the first audience distribution comprising a distribution of first household members of the first household into demographic groups of ones of the first household members that are registered with a database proprietor, the first audience distribution being based on accesses to first media by the first household members, the aggregated distribution generator to generate the aggregated audience distribution without using cookies;   a matrix normalizer to normalize the aggregated audience distribution to generate a misattribution correction matrix, the misattribution correction matrix comprising a probability that an impression of the media is attributable to a first demographic group when the database proprietor determines the impression to correspond to a person in a second demographic group; and   a misattribution corrector to compensate misattribution error in the impressions by re-assigning the impressions to the first demographic group using the misattribution correction matrix, the impressions being indicative of media accessed on mobile devices, at least one of the aggregated distribution generator, the matrix normalizer, or the misattribution corrector being implemented by a logic circuit.   
     
     
         88 . An apparatus as defined in  claim 87 , further comprising a matrix corrector to generate a correction index to correct the aggregated audience distribution for at least one of oversampling or undersampling associated with a survey calibration data source, the survey calibration data source indicating the accesses to the media by the first household members and registration statuses of the first household members with the database proprietor. 
     
     
         89 . An apparatus as defined in  claim 88 , wherein the correction index is based on a second probability that a first person in the first demographic group lives with a second person in the second demographic group. 
     
     
         90 . An apparatus as defined in  claim 88 , wherein the matrix corrector is to generate the correction index by:
 determining, based on first survey calibration data, a first quantity of first pairs of people, respective ones of the first pairs of people including a first person in the first demographic group and a second person in the second demographic group living together;   determining, based on second survey calibration data, a second quantity of second pairs of people, respective ones of the second pairs of people including a third person in the first demographic group and a fourth person in the second demographic group living together, the second survey calibration data having higher accuracy than the first survey calibration data; and   determining a ratio of the first quantity and the second quantity.   
     
     
         91 . An apparatus as defined in  claim 87 , wherein the aggregated audience distribution describes, for each first demographic group, a number of people in the second demographic group who are to be attributed to that first demographic group, and the matrix normalizer is to normalize the aggregated audience distribution by scaling respective numbers of people in the second demographic group such that a total of the number of people for the second demographic group is a designated value. 
     
     
         92 . An apparatus as defined in  claim 87 , further comprising a household distribution generator to:
 determine a sharing pattern for the first household, the sharing pattern indicative of ones of the first household members who access a media category and other ones of the first household members who do not access the media category; and   determine a probability density function of device sharing probabilities for the first household members in the first household based on the sharing pattern for the media category, the probability density function indicative of respective probabilities that the first household members access media in the media category, the first audience distribution being based on the device sharing probabilities.   
     
     
         93 . An apparatus as defined in  claim 92 , wherein the aggregated distribution generator is to aggregate the device sharing probabilities for the first household members when the first household has two or more registered ones of the household members who are in a same second demographic group. 
     
     
         94 . An apparatus as defined in  claim 87 , further comprising a household distribution generator to generate the first audience distribution by distributing fractional numbers into the demographic groups, the fractional numbers totaling a count of those ones of the first household members who are registered with a database proprietor. 
     
     
         95 . An apparatus as defined in  claim 87 , wherein the misattribution corrector is to re-assign the impressions by determining a product of the misattribution correction matrix and an impressions matrix, the impressions matrix indicating numbers of impressions determined by the database proprietor to correspond to respective ones of the demographic groups. 
     
     
         96 . An apparatus as defined in  claim 95 , wherein the misattribution corrector is to re-assign the impressions such that a total number of re-assigned impressions is a same total number of impressions as a total of the numbers of impressions in the impressions matrix. 
     
     
         97 . A computer readable storage medium comprising computer readable instructions which, when executed, cause a processor to at least:
 access, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device; and   send a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the first request;   generate an aggregated audience distribution including a first audience distribution of a first household aggregated with a second audience distribution of a second household, the first audience distribution comprising a distribution of first household members of the first household into demographic groups of ones of the first household members that are registered with a database proprietor, the first audience distribution being based on accesses to first media by the first household members, and the aggregated audience distribution being generated without using cookies;   normalize the aggregated audience distribution to generate a misattribution correction matrix, the misattribution correction matrix comprising a probability that an impression of the media is attributable to a first demographic group when the database proprietor determines the impression to correspond to a person in a second demographic group; and   compensate misattribution error in the impressions by re-assigning the impressions to the first demographic group using the misattribution correction matrix, the impressions being indicative of media accessed on mobile devices.   
     
     
         98 . A storage medium as defined in  claim 97 , wherein the instructions are further to cause the processor to generate a correction index to correct the aggregated audience distribution for at least one of oversampling or undersampling associated with a survey calibration data source, the survey calibration data source indicating the accesses to the media by the first household members and registration statuses of the first household members with the database proprietor. 
     
     
         99 . A storage medium as defined in  claim 98 , wherein the correction index is based on a second probability that a first person in the first demographic group lives with a second person in the second demographic group. 
     
     
         100 . A storage medium as defined in  claim 98 , wherein the instructions are to cause the processor to generate the correction index by:
 determining, based on first survey calibration data, a first quantity of first pairs of people, respective ones of the first pairs of people including a first person in the first demographic group and a second person in the second demographic group living together;   determining, based on second survey calibration data, a second quantity of second pairs of people, respective ones of the second pairs of people including a third person in the first demographic group and a fourth person in the second demographic group living together, the second survey calibration data having higher accuracy than the first survey calibration data; and   determining a ratio of the first quantity and the second quantity.   
     
     
         101 . A storage medium as defined in  claim 97 , wherein the aggregated audience distribution describes, for each first demographic group, a number of people in the second demographic group who are to be attributed to that first demographic group, and the instructions are to cause the processor to normalize the aggregated audience distribution by scaling respective numbers of people in the second demographic group such that a total of the number of people for the second demographic group is a designated value. 
     
     
         102 . A storage medium as defined in  claim 97 , wherein the instructions are further to cause the processor to:
 determine a sharing pattern for the first household, the sharing pattern indicative of ones of the first household members who access a media category and other ones of the first household members who do not access the media category; and   determine a probability density function of device sharing probabilities for the first household members in the first household based on the sharing pattern for the media category, the probability density function indicative of respective probabilities that the first household members access media in the media category, the first audience distribution being based on the device sharing probabilities.   
     
     
         103 . A storage medium as defined in  claim 102 , wherein the instructions are further to cause the processor to aggregate the device sharing probabilities for the first household members when the first household has two or more registered ones of the first household members who are in a same second demographic group. 
     
     
         104 . A storage medium as defined in  claim 97 , wherein the instructions are to cause the processor to generate the first audience distribution by distributing fractional numbers into the demographic groups, the fractional numbers totaling a count of those ones of the first household members who are registered with a database proprietor. 
     
     
         105 . A storage medium as defined in  claim 97 , wherein the instructions are to cause the processor to re-assign the impressions by determining a product of the misattribution correction matrix and an impressions matrix, the impressions matrix indicating numbers of impressions determined by the database proprietor to correspond to respective ones of the demographic groups. 
     
     
         106 . A storage medium as defined in  claim 105 , wherein the instructions are to cause the processor to re-assign the impressions such that a total number of re-assigned impressions is a same total number of impressions as a total of the numbers of impressions in the impressions matrix. 
     
     
         107 . A method, comprising:
 collecting, using a processor, media impressions from a first type of computing device;   requesting, using the processor, demographic information for the media impressions from a database proprietor, a first portion of the media impressions corresponding to persons for whom demographic information is stored by a database proprietor and a second portion of the media impressions corresponding to persons for whom demographic information is unavailable to the database proprietor   receiving the demographic information corresponding to the first portion of the media impressions from the database proprietor;   determining, using the processor, a number of media impressions in the second portion of the media impressions; and   determining, using the processor, the demographic information for the second portion of the media impressions based on a first probability that media corresponding to the media impressions is accessed on the first type of computing device and based on a second probability that media is accessed on a second type of device.   
     
     
         108 . A method, comprising:
 receiving, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device;   receiving, at the first internet domain, a second request from the computing device, the second request indicative of access to a duration unit of the media at the computing device;   sending a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the second request;   obtaining a count of duration units occurring on the first type of computing device, a first portion of the duration units corresponding to persons for whom demographic information is recognizable by a database proprietor and a second portion of the duration units corresponding to persons for whom demographic information is unavailable to the database proprietor; and   determining, using a processor, the demographic information for the second portion of the duration units based on a first probability that media corresponding to the duration units is accessed on the first type of computing device and based on a second probability that media is accessed on a second type of device.   
     
     
         109 . An apparatus, comprising:
 an impression collector to:
 receive, at a first internet domain, a first request from a first type of computing device, the first request indicative of access to media at the computing device; 
 receive, at the first internet domain, a second request from the computing device, the second request indicative of access to a duration unit of the media at the computing device; and 
 send a request for demographic information corresponding to requests received at the first internet domain from the first type of computing device, the requests including the second request; 
   an impression information collector to access a count of duration units occurring on a first type of computing device, a first portion of the duration units corresponding to persons for whom demographic information is recognizable by a database proprietor and a second portion of the duration units corresponding to persons for whom demographic information is unavailable to the database proprietor; and   a non-coverage corrector to determine the demographic information for the portion of the duration units based on a first probability that media corresponding to the duration units is accessed on the first type of computing device and based on a second probability that media is accessed on a second type of device, at least one of the impression information collector or the non-coverage corrector being implemented by a logic circuit.