[Felix The Cat]

Hi Everyone,

Thought I would attempt some BEC practice questions from Wiley.

Here is the question in full:

“The internal auditor of a bank has developed a multiple
regression model which has been used for a number of years
to estimate the amount of interest income from commercial
loans. During the current year, the auditor applies the model
and dis covers that the r2 value has decreased dramatically, but
the model otherwise seems to be working okay. Which of the
following conclusions are justif ed by the change?

a. Changing to a cross-sectional regression analysis
should cause r2 to increase.
b. Regression analysis is no longer an appropriate technique to estimate interest income.
c. Some new factors, not included in the model, are
caus ing interest income to change.
d. A linear regression analysis would increase the
model’s reliability.”

Really have a tough time comprehending the answer:

“The requirement is to provide an explanation for
a drop in r2. The coeffcient of determination (r2) provides
a measure of amount of variation in the dependent variable
(inter est income) explained by the independent variables. If
there is a dramatic decrease in the coeff cient of determination,
the impli cation is that there are some new factors that are
causing interest income to change. Therefore, answer (c)
is correct. Answer (a) is incorrect because cross-sectional
regression is not appropriate. Management is attempting to
estimate interest income over time. Answer (b) is incorrect
because regression analysis may still be appropriate. Answer
(d) is incorrect because multiple regression is a linear model.
Management may want to try other models such as nonlinear
multiple regression.”

Questions:
1. Why is cross-sectional REG not appropriate?
2. Why would regression analysis still be appropriate? (answer b) b/c the model is still working ok?

Thanks to those that help out!

FTC

[Felix The Cat]

Anyone? Help please…

[Zeo]

Here's my reasoning.

Answer B is wrong because regression analysis (the concept/tool) is still appropriate to use because we're estimating a total (dependent variable). However, our specific model, based on our assumptions, appears to be wrong. So the tool of regression analysis itself can still be used but our specific model and assumptions need to be updated.

Looking up what cross-sectional REG analysis is, I came up with that it involves an evaluation at a period or point in time? So since we're going to be estimating interest income for an indefinite period of time, cross-sectional REG doesn't really make sense? That's my best guess/explanation.

Ultimately, our independent variables (that we have chosen/estimated) don't strongly explain the variation in our dependent variable. So something else is causing the variation.

Hope I helped a bit!

[Felix The Cat]

Hi Zeo!

Thank you for taking the time to reply to my question, if you're in Ontario let me buy you a beer!

Further question:

1) You mention ‘Reg analysis is appropriate to use b/c we are estimating a total'….what does a total have to do with it?

Can anyone else explain please?

Have a great day!

[Felix The Cat]

Zeo??

[Author]

Replies