Methods and apparatus to generate corrected online audience measurement data

An audience measurement apparatus to generate corrected online audience measurement data, comprising:

• a first impressions collector to collect network communications at a first server from computing devices, the network communications indicative of impressions of streaming media delivered to the computing devices via an Internet;
• a second impressions collector to receive, from a second server of a database proprietor, a first audience count indicative of first numbers of the impressions corresponding to the network communications attributed to the streaming media for a demographic group, a second audience count indicative of second numbers of the impressions corresponding to the network communications attributed to text accessed by the demographic group, and a third audience count describing third numbers of the impressions corresponding to the network communications attributed to the streaming media and the text accessed by the demographic group, the first audience count including a duplicated audience count introduced by the second server of the database proprietor;
• a factor generator to calculate a deduplication factor for the demographic group using the first audience count, the second audience count, and the third audience count;
• an audience calculator to determine a corrected audience count of the streaming media for the demographic group to correct the duplicated audience count generated by the second server of the database proprietor, the corrected audience count determined by:
• estimating a fourth audience count for the demographic group, the fourth audience count indicative of a first number of people who accessed the streaming media;
• estimating a fifth audience count for the demographic group, the fifth audience count indicative of a second number of people who accessed the text;
• and
• applying the deduplication factor to a sum of the fourth audience count and the fifth audience count;
• and
• a ratings data generator to generate ratings information for the streaming media based on subtracting the corrected audience count from the first audience count.

A tangible computer readable storage medium comprising computer readable instructions which, when executed cause a processor to at least:

• collect, at a first server of an audience measurement entity, network communications from computing devices, the network communications indicative of impressions of streaming media delivered to the computing devices via an Internet;
• receive, from a second server of a database proprietor, at the processor of the audience measurement entity, a first audience count indicative of first numbers of the impressions corresponding to the network communications attributed to the streaming media for a demographic group, a second audience count indicative of second numbers of the impressions corresponding to the network communications attributed to text accessed by the demographic group, and a third audience count indicative of third numbers of the impressions corresponding to the network communications attributed to the streaming media and the text accessed by the demographic group, the first audience count including a duplicated audience count introduced by the second server of the database proprietor;
• determine a corrected audience count of the streaming media for the demographic group to correct the duplicated audience count generated by the second server of the database proprietor, the corrected audience count determined by:
• estimating a fourth audience count for the demographic group, the fourth audience count indicative of a first number of people who accessed the streaming media;
• estimating a fifth audience count for the demographic group, the fifth audience count indicative of a second number of people who accessed the text;
• calculating a deduplication factor for the demographic group based on the first audience count, the second audience count, and the third audience count;
• and
• applying the deduplication factor to a sum of the fourth audience count and the fifth audience count to determine the corrected audience count;
• and
• generate ratings information for the streaming media based on subtracting the corrected audience count from the first audience count.