Suppose you were asked to investigate which predictors explainthe number of minutes that 10- to18-year-old students spend onTwitter. To do so, you build a linear regression model with Twitterusage (Y) measured as the number of minutes per week. The fourpredictors you include in the model are Height, Weight, GradeLevel, and Age of each student. You build four simplelinear regression models with Y regressed separately on eachpredictor, and each predictor is statistically significant. Thenyou build a multiple linear regression model with Y regressed onall four predictors, but only one predictor, Age, is statisticallysignificant, and the others are not. What is likely going on amongthe four predictors? If you include more than one of thesepredictors in the model, what are some problems that canresult?
