In a comparative analysis of smart watches, you extracted N messages from a smart watch forum where people discuss three products: Apple Watch, Fitbit Versa and Movado Connect (call this data set A). To boost the total amount of data, you also extracted an additional N messages posted on an Apple Watch forum, where every post mentions the Apple Watch, and where some (but not all) posts co-mention the other products (data set B). You want to calculate Lift(AppleWatch, battery) and Lift(MovadoConnect, battery) with data set A, and also with data set A+B (merging the two data sets). For simplicity assume (i) the proportion of posts mentioning battery is the same for data sets A and B, (ii) the proportion of MovadoConnect posts which also mention battery is the same for data sets A and B, (iii) Lift(AppleWatch, battery) > 1 for data set A. Is Lift(Applewatch, battery), calculated from data set A, GREATER THAN, EQUAL TO, OR LESS THAN (Choose one) Lift(Applewatch, battery) calculated using the combined data set A+B? Justify your response. You can use a numerical example, but must justify using logical arguments.
