In our dataset, we have separate variables for implicit and explicit prejudice ## which help us identify those who consciously endorse negative stereotypes about Indians ## from those who might subconsciously hold biases against Indians. For this exercise, ## create a new variable named strong_prejudice. Assign it a value of 1 when both ## "expl.prejud" and "impl.prejud" are greater than their respective median values, ## and 0 otherwise. This new variable captures individuals who harbor pronounced ## prejudices on both explicit and implicit forms, allowing us to specifically ## examine the attitudes and behaviors of individuals who exhibit a more comprehensive ## form of prejudice, compared to those who might only show prejudice in one dimension ## or not at all. In essence, the new variable distinguishes between individuals ## with strong prejudice and the rest. Next, conduct two two-variable regression analyses, ## with attitudes towards H-1B visas and Indian immigration as the respective ## dependent variables, and the newly created strong_prejudice variable as the predictor. ## Interpret the estimated coefficients and their statistical significance, ## and the multiple R-squared statistic across the models. ## Based on the results, what can we infer about the influence of individuals ## with strong prejudice, compared to others, on attitudes towards H-1B visas ## and Indian immigration