Assume that the data mining task is to predict a person's age based on whether they play video games, enjoy gardening, and their preference on wearing hats. Training sample size is 9 and evaluation criteria is to minimize squared error. To help reduce squared error, a 2nd tree is fit on the residuals, to show improvements, calculated Tree 1, Tree 2, and combined predictions. Then calculate reduction in mean square error. PersonID LikesGardening FALSE FALSE FALSE TRUE FALSE TRUE TRUE TRUE TRUE PlaysVideoGames TRUE TRUE TRUE TRUE TRUE FALSE TRUE FALSE FALSE LikesHats TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE TRUE 13 2 15 25 35 49 68 71 73 5 7