Part 1 : 03/11/17 11:56:38

Question 1 - CMA 1290 4.28 - Regression Analysis

The letter x in the standard regression equation is best described as a(n)

A. Coefficient of determination.
B. Constant coefficient.
C. Dependent variable.
D. Independent variable.

A. The coefficient of determination is not a part of the standard regression equation at all. The coefficient of
determination is the percentage of the total amount of change in the dependent variable that can be explained by
changes in the independent variable.

B. The constant coefficient is represented by a letter that stands by itself, i.e., a letter without an x term next to it. It
represents the y intercept, because this is the value of y when x = 0.

C. In the standard regression equation, y represents the dependent variable.

D. In the standard regression equation x represents the independent variable.

Question 2 - CIA 597 I.31 - Regression Analysis

An international nonprofit organization finances medical research. The majority of its revenue and support comes from
fundraising activities, investments, and specific grants from an initial sponsoring corporation. The organization has
been in operation over 15 years and has a small internal auditing department. The organization has just finished a
major fund-raising drive that raised $500 million for the current fiscal period.

The following are selected data from recent financial statements (dollar figures in millions):
Current Past
Year Year
Revenue $500 $425
Investments (average balances) 210 185
Medical research grants made 418 325
Investment income 16 20
Administrative expense 10 8

The auditor wishes to determine if the change in investment income during the current year was due to (a) changes in
investment strategy, (b) changes in portfolio mix, or (c) other factors. Which of the following analytical review
procedures should the auditor use?

A. Trend analysis that compares the changes in investment income as a percentage of total assets and of investment
assets over the past 5 years.
B. Simple linear regression that compares investment income changes over the past 5 years to determine the nature of
the changes.
C. Multiple regression analysis that includes independent variables related to the nature of the investment portfolio and
market conditions.
D. Ratio analysis that compares changes in the investment portfolio on a monthly basis.

A. Trend analysis would be useful to measure the changes in investment income, but would not explain the reason for
the changes.

B. A simple linear regression is based just only on one independent variable. Therefore, it would not be useful for the
internal auditor to determine the reason in investment income.

C. Multiple regression analysis is the best analytical procedure for the internal auditor to use to explain the

(c) HOCK international, page 1

change in investment income. Multiple regression allows the auditor to explain the actions of the dependent
variable (investment income) in terms of one or more independent variables.

D. Ratio analysis would be useful to measure the changes in investment income, but would not explain the reason for
the changes.

Question 3 - CMA 1285 5.27 - Regression Analysis

The correlation coefficient that indicates the weakest linear association between two variables is

A. 0.12
B. -0.73
C. -0.11
D. 0.35

A. A coefficient of correlation that is close to zero usually means there is no, or very little, relationship between the
variables. Therefore, the weakest correlation coefficient is the one that is closest to zero. This is not the answer choice
that is closest to zero.

B. A coefficient of correlation that is close to zero usually means there is no, or very little, relationship between the
variables. Therefore, the weakest correlation coefficient is the one that is closest to zero. This is not the answer choice
that is closest to zero.

C. The coefficient of correlation is a numerical measure that measures both the direction (positive or negative)
and the strength of the linear association between the dependent and independent variables. The coefficient
of correlation lies between 1.0 and +1.0. When the correlation coefficient is positive (between 0 and +1), it
means the dependent and independent variables move in the same direction. When the correlation coefficient
is negative (between 0 and 1), it means they move in opposite directions, i.e., when the independent variable
goes up, the dependent variable goes down. When the coefficient of correlation is zero, it means either that
there is no correlation between the two variables, or that the relationship between them is not linear. To
identify the weakest correlation we need to determine the coefficient of correlation that is closest to 0. In this
case it is .11.

D. A coefficient of correlation that is close to zero usually means there is no, or very little, relationship between the
variables. Therefore, the weakest correlation coefficient is the one that is closest to zero. This is not the answer choice
that is closest to zero.

Question 4 - CIA 1194 II.46 - Regression Analysis

In regression analysis, which of the following correlation coefficients represents the strongest relationship between the
independent and dependent variables?

A. 1.03
B. .75
C. -.02
D. -.89

A. The coefficient of correlation lies between -1.0 and +1.0. Therefore, the coefficient of correlation could not be 1.03.

B. This is not the strongest correlation. The strongest relationship between the independent and dependent variables is
represented by a correlation coefficient that is closest to either +1 or 1. See the correct answer for a complete
explanation.

(c) HOCK international, page 2

C. The correlation coefficient representing the strongest relationship between the independent and dependent variable
is the one that is closest to either +1 or 1. This is the weakest correlation among the answer choices.

D. The coefficient of correlation is a numerical measure that measures both the direction (positive or negative)
and the strength of the linear association between the dependent and independent variables. The coefficient
of correlation lies between -1.0 and +1.0. When the correlation coefficient is positive (between 0 and +1), it
means the dependent and independent variables move in the same direction. When the correlation coefficient
is negative (between 0 and 1), it means they move in opposite directions, i.e., when the independent variable
goes up, the dependent variable goes down. When the coefficient of correlation is 0, it means either that there
is no correlation between the two variables, or that the relationship between them is not linear. To identify the
strongest correlation we need to determine the coefficient of correlation that is closest to either +1 or 1. In
this case it is .89.

Question 5 - CMA 1289 5.14 - Regression Analysis

Correlation is a term frequently used in conjunction with regression analysis, and is measured by the value of the
coefficient of correlation, r. The best explanation of the value r is that it

A. Interprets variances in terms of the independent variable.

A. The coefficient of correlation relates two variables to each other. It does not interpret variances.

B. The coefficient of correlation can be either positive and negative.

C. The value of coefficient of correlation lies between +1.0 and 1.0.

D. The coefficient of correlation is a numerical measure that measures both the direction (positive or negative)
and the strength of the linear association between the dependent and independent variables.

Question 6 - CIA 594 2.39 - Regression Analysis

A chain retailer has outlets in forty non-over lapping though similar local markets. Recently, the retailer conducted its
largest promotional campaign ever. Each outlet was unrestricted in allocating its promotional budget between local
print, radio, or television advertising or in underspending the budget. The internal auditor wishes to evaluate the
effectiveness of these tactics. In this case

A. Since the relationships between promotional expenditures and sales is probably non-linear, regression analysis
should not be used.
B. Discriminant analysis would be the best tool for discriminating between effective and ineffective promotional tactics.
C. Time series analysis should be used since the promotion occurred over time.
D. Multiple regression analysis may be an effective tool for modeling the relationship between sales and promotional
tactics.

A. The linearity of the relationships cannot be assessed before the data is analyzed.

B. The dependent variable, sales, is continuous.

C. The data are cross sectional.

(c) HOCK international, page 3

D. Multiple regression is the most effective because we are trying to determine the relative effect of four
different variables.

Question 7 - CIA 593 III.64 - Regression Analysis

What coefficient of correlation results from the following data?

A. +1
B. Cannot be determined from the data given.
C. 0
D. -1

A. A perfectly inverse relationship exists, not a direct relationship.

B. A linear relationship between X and Y can be determined.

C. The data represents a negative correlation. As X is increasing, Y is decreasing.

D. This data represents a perfect negative correlation. As X is increasing by 1, Y is decreasing by 2. Thus, this
is an inverse relationship, and r must be equal to 1.

Question 8 - CIA 594 H10 - Regression Analysis

A chain retailer has outlets in forty non-overlapping though similar local markets. Recently, the retailer conducted its
largest promotional campaign ever. Each outlet was unrestricted in allocating its promotional budget between local
print, radio, or television advertising or in underspending the budget. The internal auditor wishes to evaluate the
effectiveness of these tactics. In this case

A. Multiple regression analysis may be an effective tool for modeling the relationship between sales and promotional
tactics.
B. Discriminant analysis would be the best tool for discriminating between effective and ineffective promotional tactics.
C. Time series analysis should be used since the promotion occurred over time.
D. Since the relationships between promotional expenditures and sales is probably non-linear, regression analysis
should not be used.

A. Multiple regression is the most effective because we are trying to determine the relative effect of four
different variables.

B. The dependent variable, sales, is continuous.

C. The data are cross sectional.

D. The linearity of the relationships cannot be assessed before the data is analyzed.

(c) HOCK international, page 4

Question 9 - CMA 1290 4.27 - Regression Analysis

In the standard regression equation y = a + b(x), the letter b is best described as a(n)

A. Independent variable.
B. Constant coefficient.
C. Dependent variable.
D. Variable coefficient.

A. The independent variable is represented by x in the equation given.

B. The constant coefficient is represented by a in the equation given. It represents the y intercept, because this is the
value of y when x = 0.

C. The dependent variable is represented by y in the equation given.

D. In the standard regression as represented here, the b in the equation represents the variable coefficient. It
represents the amount of increase in y for each unit of increase in x, or the slope of the line.

Question 10 - CIA 1194 2.47 - Regression Analysis

An internal auditor used regression analysis to evaluate the relationship between utility costs and machine hours. The
following information was developed using a computer software program:
Constant coefficient - 2,050
Variable coefficient - 0.825
Correlation coefficient - 0.800
Standard error of the estimate - 200
Number of observations - 36

What is the expected utility cost if the company's 10 machines will be used 2,400 hours next month?

A. $3,970.
B. $4,030.
C. $3,930.
D. $4,050.

A. [$2,050 + .825(2,400)] - 100 [Incorrectly uses the standard error of the estimate].

B. y = $2,050 + .825(2,400).

C. $2,050 + .800(2,400) [Incorrectly uses the correlation coefficient instead of the variable coefficient].

D. $2,050 + 10(200) [Incorrectly uses the standard error of the estimate].

(c) HOCK international, page 5