Pedigree Vs. Grit
Predicting Mutual Funds Performance
Mukundapokhrel Y
7/13/2017
Data, Analytics and Learning – Assignment 1
Submitted by
Submitted to
Bhuvanesh Pareek
1.
(a) Why do you disagree with Jack’s comments about the uselessness of the regression
due to the low R-squared?
R-squared cannot determine whether the coefficient estimates and predictions are
biased, which is why you must assess the residual plots. R-squared does not indicate whether a
regression model is adequate. You can have a low R-squared value for a good model, or a high
R-squared value for a model that does not fit the data.
(b)
Can you think of a situation in which a useless regression has a high R-squared?
There might be situation when there is no logical relationship between two variables but with
high R-squared value. For example, no of professors in a college and no of customers visiting
a big bazaar shopping might get a R-squared value of 95% but logically the regression is
useless.
(c)
There are techniques to determine the validity of a regression model—in particular,
whether the relationship is linear and the error terms display equal variance
(homoskedasticity). Does the regression in Table 1 violate either of these two
