Abstract: Methods and apparatus to partition data are disclosed. An example apparatus to partition panelist data includes an indicator matrix generator to determine an indicator matrix including panelist vectors for panelists based on panelist data associated with the panelists, a first one of the panelist vectors for a first one of the panelists to indicate whether the first one of the panelists: has a first characteristic, meets a first criterion based on the first characteristic and a second characteristic, has a third characteristic, and meets a second criterion based on the third characteristic and a fourth characteristic. The example apparatus further includes a matrix reducer to reduce the indicator matrix to a set of unique panelist vectors that represent partitions of the panelist data, the partitions of the panelist data to utilize less storage capacity than the panelist data.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to identify co-relationships between media using social media. An example method includes obtaining media-exposure social media messages based on keywords and posting timestamps, and identifying a media-pairing including first media and second media. The example method also includes estimating a first audience of the first media based on a first set of media-exposure social media messages referencing the first media, and estimating a second audience of the second media based on a second set of media-exposure social media messages referencing the second media.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to determine a duration of media presentation based on tuning session duration. Example apparatus include a tuning session determiner to determine a first tuning session based on a period of time between channel changes of a first media presentation device; a presentation session determiner to determine first presentation session data within the determined first tuning session; a modeler to determine a model by relating the first tuning session with the first presentation session data; a receiver to determine a second tuning session for tuning data from a second media presentation device; and a presentation session estimator to: select the model for the second tuning session, based on a match of a first duration of the second tuning session and a second duration associated with the model, and estimate second presentation session data for the second tuning session based on the model.

Abstract: Methods and apparatus to apply household-level weights to audience measurement data at a household-member level are disclosed. An example method to determine demographics of populations to measure media audiences of populations includes determining demographics for members of a first household of a sub-population. First demographics of a first member of the first household are different than second demographics of a second member of the first household. The example method includes calculating a first household-level weight for the first household based on a demographics distribution of the sub-population and aggregate demographics of a population.

Abstract: Methods and apparatus to estimate media impression frequency distributions are disclosed. An example method includes logging a plurality of requests in a database, the plurality of requests obtained from a plurality of network communications from computing devices, the plurality of requests indicative of accesses to media at the computing devices. The method further includes obtaining a first impression frequency distribution from a database proprietor. The first impression frequency distribution corresponding to user-identified impressions of census impressions and exclusive of unidentified impressions of the census impressions. The user-identified impressions corresponding to user-identified individuals for whom first demographic information is stored by the database proprietor. The first impression frequency distribution including a plurality of impression frequency groups of user-identified audience sizes.

Abstract: Methods and apparatus to partition data are discloses. An example method includes generating, with a processor, an indicator matrix for a set of panelist data based on a set of matrix criteria corresponding to the panelist data. The entries in the indicator matrix are determined based on a conditional probability of a panelist having one or more characteristics. An indicator is placed in a panelist vector of the matrix if the panelist has the one or more characteristics. A set of unique panelist vectors is determined and redundant panelist vectors that are not unique are removed to determine a minimum set of mutually exclusive partitions of the panelist data.

Abstract: Methods and apparatus for calculating granular data of an audience of a target region. An example method includes utilizing minimum cross entropy to apportion aggregate demographics data and aggregate behavioral data of the target region based on granular data of a source region. The example further includes reducing an amount of computer memory resources by calculating the granular data of the audience without collecting person-specific data from audience members of the target region, the granular data of the audience including (A) a count of the audience of the target region satisfying a behavioral constraint and a first demographic constraint and (B) a count of the audience of the target region satisfying the behavioral constraint and a second demographic constraint, the calculated granular data based on the aggregate demographics data of the target region, the aggregate behavioral data of the target region, and the granular data of the source region.

Abstract: Methods and apparatus to estimate demographics of a household are disclosed. An example method to determine demographics for non-panelist households includes calculating a first demographic constraint average and a second demographic constraint average based on a first demographic distribution of a first tuning event of a household and a second demographic distribution of a second tuning event of the household. The household is a non-panelist household. The example method also includes, based on the first demographic constraint average, determining a first likelihood of the household being associated with a first demographic constraint. The example method also includes, based on the second demographic constraint average, determining a second likelihood of the household being associated with a second demographic constraint. The example method also includes estimating a household characteristic of the household based on the first likelihood and the second likelihood.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to monitor media presentation to determine a period of media presentation based on tuning session period are disclosed. Example methods disclosed herein include determining a first tuning session based on a period of time between channel changes of a first media presentation device, determining first presentation session data within the determined first tuning session, determining a model relating the first tuning session with the first presentation session data, determine a second tuning session for tuning data from a second media presentation device, selecting the model for the second tuning session, based on a match of a first duration of the second tuning session and a second duration associated with the model, and estimating second presentation session data for the second tuning session based on the model.

Abstract: Methods and apparatus to determine characteristics of media audiences are disclosed. An example method includes creating a constraint matrix based on a first activity associated with a first characteristic of a population, the first activity associated with a second characteristic of the population, and a first combination associated with at least one of the first activity, the first characteristic, and the second characteristic. The example method includes creating a combination total set based on a first measurement for the first activity associated with the first characteristic and a second measurement for the first activity associated with the second characteristic. The example method includes computing a first entropy probability based on the constraint matrix and the combination total set. The example method includes estimating a first portion of the population that matches the first combination based on the first entropy probability.

Abstract: Methods, apparatus, systems and articles of manufacture to estimate ratings for media assets using social media are disclosed. An example method includes accessing media exposure data and social media activity data corresponding to a plurality of media assets in a media bundle, the media assets included in the media bundle having audience demographics that overlap with a first media asset, determining a first credibility factor for the first media asset and average exposure for social media activity count values for respective ones of the media assets in the media bundle based on the media exposure data and the social media activity data, and applying the first credibility factor to an average exposure per social media activity count value determined for the first media asset to estimate the ratings for the first media asset.

Abstract: Methods and apparatus for calculating granular data of an audience of a target region. An example method includes utilizing minimum cross entropy to apportion aggregate demographics data and aggregate behavioral data of the target region based on granular data of a source region. The example further includes reducing an amount of computer memory resources by calculating the granular data of the audience without collecting person-specific data from audience members of the target region, the granular data of the audience including (A) a count of the audience of the target region satisfying a behavioral constraint and a first demographic constraint and (B) a count of the audience of the target region satisfying the behavioral constraint and a second demographic constraint, the calculated granular data based on the aggregate demographics data of the target region, the aggregate behavioral data of the target region, and the granular data of the source region.

Abstract: Methods and apparatus to estimate demographics of a household are disclosed. An example method to determine demographics for non-panelist households includes calculating a first demographic constraint average and a second demographic constraint average based on a first demographic distribution of a first tuning event of a household and a second demographic distribution of a second tuning event of the household. The household is a non-panelist household. The example method also includes, based on the first demographic constraint average, determining a first likelihood of the household being associated with a first demographic constraint. The example method also includes, based on the second demographic constraint average, determining a second likelihood of the household being associated with a second demographic constraint. The example method also includes estimating a household characteristic of the household based on the first likelihood and the second likelihood.

Abstract: Methods, apparatus, systems and articles of manufacture to estimate ratings for media assets using social media are disclosed. An example method includes accessing media exposure data and social media activity data corresponding to a plurality of media assets in a media bundle, the media assets included in the media bundle having audience demographics that overlap with a first media asset, determining a first credibility factor for the first media asset and average exposure for social media activity count values for respective ones of the media assets in the media bundle based on the media exposure data and the social media activity data, and applying the first credibility factor to an average exposure per social media activity count value determined for the first media asset to estimate the ratings for the first media asset.

Abstract: Methods and apparatus to utilize a minimum cross entropy to calculate granular data of a region based on another region for media audience measurement. An example method for calculating granular data of a region for media audience measurement includes determining, by executing first instructions via a processor, aggregate behavioral data associated with a measurement of a media audience of a target region; determining, by executing second instructions via the processor, aggregate demographics data of the target region; and determining, by executing third instructions via the processor, granular data of a source region. The example method includes calculating, by executing fourth instructions via the processor, granular data of the media audience of the target region by utilizing minimum cross entropy to apportion the aggregate demographics data and the aggregate behavioral data of the target region based on the granular data of the source region to determine.

Abstract: Methods and apparatus to utilize a minimum cross entropy to calculate granular data of a region based on another region for media audience measurement. An example method for calculating granular data of a region for media audience measurement includes determining, by executing first instructions via a processor, aggregate behavioral data associated with a measurement of a media audience of a target region; determining, by executing second instructions via the processor, aggregate demographics data of the target region; and determining, by executing third instructions via the processor, granular data of a source region. The example method includes calculating, by executing fourth instructions via the processor, granular data of the media audience of the target region by utilizing minimum cross entropy to apportion the aggregate demographics data and the aggregate behavioral data of the target region based on the granular data of the source region to determine.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for a viewing condition probability calculator. The viewing condition probability calculator enumerates a list of all viewing combinations for a tuning event, for a number of people N at a location. A probability for each of the viewing combinations is determined, using an independent probability of viewing for each of the N people at the location. A probability of a viewing condition is determined using the probabilities of a first set of viewing combinations that have a first common characteristic.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to determine a causal effect of observation data without reference data.

Abstract: Methods and apparatus to facilitate dynamic classification for market research are disclosed. Example disclosed methods include constructing, using a programmed processor based on data for a sample population and a first set of input variables, a self-organizing map classifying the sample population according to a plurality of classes defined in the map using fuzzy class membership. Example disclosed methods include extracting the fuzzy class membership for the sample population from the map. Example disclosed methods include correlating fuzzy class membership with behavior data for the sample population to determine a likely class behavior for the plurality of classes. Example disclosed methods include using fuzzy class membership and the likely class behavior to provide a predictive market output in response to a query.

Abstract: Methods and apparatus to determine characteristics of media audiences are disclosed. An example method includes creating a constraint matrix based on a first activity associated with a first characteristic of a population, the first activity associated with a second characteristic of the population, and a first combination associated with at least one of the first activity, the first characteristic, and the second characteristic. The example method includes creating a combination total set based on a first measurement for the first activity associated with the first characteristic and a second measurement for the first activity associated with the second characteristic. The example method includes computing a first entropy probability based on the constraint matrix and the combination total set. The example method includes estimating a first portion of the population that matches the first combination based on the first entropy probability.