Methods and apparatus to correct errors in audience measurements for media accessed using over the top devices

1. An apparatus to predict demographics for impressions, the apparatus comprising:

a prediction manager to access matched demographic impression data when a database proprietor subscriber does not match user data corresponding to a media delivery device, the matched demographic impression data corresponding to an impression of media accessed via the media delivery device, the matched demographic impression data including first demographic data stored by a database proprietor in association with a device identifier of the media delivery device;

a linear scaler to linearly scale the matched demographic impression data when the matched demographic impression data covers all demographic categories under consideration;

a differential scaler to differentially scale the matched demographic impression data when the matched demographic impression data does not cover at least one of the demographic categories; and

a modeler to:

generate a model representative of the matched demographic impression data linearly scaled or the matched demographic impression data differentially scaled; and

generate predicted demographic impression data by applying the model to second impression data, the predicted demographic impression data to correct for the database proprietor not storing second demographic data corresponding to the second impression data.

2. The apparatus of claim 1 , wherein the linear scaler applies a constant scaling factor to the matched demographic impression data.

3. The apparatus of claim 1 , further including a viewership assigner to identify impressions corresponding to co-viewing, the co-viewing including an impression of media accessed via the media delivery device by two or more demographic categories.

4. The apparatus of claim 3 , wherein the viewership assigner provides the impressions corresponding to the co-viewing to the prediction manager.

5. The apparatus of claim 4 , wherein the linear scaler and the differential scaler generate a co-viewing rate based on a comparison between the matched demographic impression data and the impressions corresponding to the co-viewing from the viewership assigner, a number of the impressions corresponding to the co-viewing is different than a number of matched demographic impression data.

6. The apparatus of claim 5 , wherein the linear scaler scales the second impression data based on the co-viewing rate to account for co-viewing.

7. The apparatus of claim 1 , wherein the differential scaler applies a variable scaling factor to the matched demographic impression data.

8. A non-transitory computer readable storage medium comprising instructions that, when executed, cause a processor to at least:

access matched demographic impression data when a database proprietor subscriber does not match user data corresponding to a media delivery device, the matched demographic impression data corresponding to an impression of media accessed via the media delivery device, the matched demographic impression data including first demographic data stored by a database proprietor in association with a device identifier of the media delivery device;

linearly scale the matched demographic impression data when the matched demographic impression data covers all demographic categories under consideration;

differentially scale the matched demographic impression data when the matched demographic impression data does not cover at least one of the demographic categories;

generate a model representative of the matched demographic impression data linearly scaled or the matched demographic impression data differentially scaled; and

generate predicted demographic impression data by applying the model to second impression data, the predicted demographic impression data to correct for the database proprietor not storing second demographic data corresponding to the second impression data.

9. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, cause the processor to apply a constant scaling factor to the matched demographic impression data.

10. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, cause the processor to identify impressions corresponding to co-viewing, the co-viewing including an impression of media accessed via the media delivery device by two or more demographic categories.

11. The non-transitory computer readable storage medium of claim 10 , wherein the instructions, when executed, cause the processor to provide the impressions corresponding to the co-viewing for scaling.

12. The non-transitory computer readable storage medium of claim 11 , wherein the instructions, when executed, cause the processor to generate a co-viewing rate based on a comparison between the matched demographic impression data and the impressions corresponding to the co-viewing, a number of the impressions corresponding to the co-viewing is different than a number of matched demographic impression data.

13. The non-transitory computer readable storage medium of claim 12 , wherein the instructions, when executed, cause the processor to scale the second impression data based on the co-viewing rate to account for co-viewing.

14. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, cause the processor to apply a variable scaling factor to the matched demographic impression data.

15. A method comprising

accessing matched demographic impression data when a database proprietor subscriber does not match user data corresponding to a media delivery device, the matched demographic impression data corresponding to an impression of media accessed via the media delivery device, the matched demographic impression data including first demographic data stored by a database proprietor in association with device identifier of the media delivery device;

linearly scaling the matched demographic impression data when the matched demographic impression data covers all demographic categories under consideration;

differentially scaling the matched demographic impression data when the matched demographic impression data does not cover at least one of the demographic categories;

generating a model representative of the matched demographic impression data linearly scaled or the matched demographic impression data differentially scaled; and

generating predicted demographic impression data by applying the model to second impression data, the predicted demographic impression data to correct for the database proprietor not storing second demographic data corresponding to the second impression data.

16. The method of claim 15 , wherein linearly scaling includes applying a constant scaling factor to the matched demographic impression data.

17. The method of claim 15 , further including identifying impressions corresponding to co-viewing, the co-viewing including an impression of media accessed via the media delivery device by two or more demographic categories.

18. The method of claim 17 , further including generating a co-viewing rate based on a comparison between the matched demographic impression data and the impressions corresponding to the co-viewing, a number of the impressions corresponding to the co-viewing is different than a number of matched demographic impression data.

19. The method of claim 18 , further including scaling the second impression data based on the co-viewing rate to account for the co-viewing.

20. The method of claim 15 , further including applying a variable scaling factor to the matched demographic impression data.