Consider the following model used to predict combined SAT scores from other test
ID: 3223915 • Letter: C
Question
Consider the following model used to predict combined SAT scores from other test scores:
SATi = o + 1HSRANKi + 2READINGi +3VOCABi + 4PICTi
+ 5LGSCi +6MATHi +7MOSAICi + ui
where:
The variables READING, VOCAB, PICT, LGSC, MATH, and MOSAIC are standardized test scores on exams administered to all participants in the National Longitudinal Study of the High School Class of 1972. (Each of these tests is scaled so that the mean is 50 and the standard deviation is 10.)
What predictions can you make about the sign of each coefficient?
What predictions can you make about the sign of each of the slope parameters?
SATi = combined verbal and math SAT scores for person i HSRANKi = high school rank (expressed as percentile) for person i READINGi = scaled reading score for person i VOCABi = scaled vocabulary score for person i PICTi = scaled picture-number score for person i LGSCi = scaled letter groups score for person i MATHi = scaled math score for person i MOSAICi = scaled mosaic comparison score for person iExplanation / Answer
(a) The intercept term is meaningless in this context. The other coefficients are meaningful.
(b) The signs of all the slope parameters are positive. This means there is a direct correlation between the respective standardized test scores and the SAT score.