Part 1 Forecasting Techniques Regression Analysis, Learning Curve, Expected Value, Sensitivity_Sol 1

.pdf

School

Cedar Mount Academy *

*We aren’t endorsed by this school

Course

AC1

Subject

Economics

Date

Jun 7, 2024

Type

pdf

Pages

Uploaded by HighnessRiverHerring36

6/14/22, 10:26 AM CMA Exam Review - Part 1 - Assessment Review https://app.efficientlearning.com/pv5/v8/5/app/cma/part1_2020.html?#assessmentReview 1/69 Question 1 1.B.3.f tb.lc.anal.015_1805 LOS: 1.B.3.f Lesson Reference: Expected Value Computations and Learning Curve Analysis Difficulty: medium Bloom Code: 2 Which of the following is not a limitation of learning curve analysis? Learning curve analysis assumes that the percentage improvement from learning only fully occurs when production doubles. Learning curve analysis cannot be used when it is difficult to accurately measure the impact of efficiency improvements. Rationale  Learning curve analysis assumes that the percentage improvement from learning only fully occurs when production doubles. Learning curve analysis assumes that the time and cost to perform an activity will decrease by a fixed percentage when production doubles. It does not allow for situations where the decrease occurs at intervals other than doubling. This lack of flexibility is a limitation of learning curve analysis; therefore, this is an incorrect answer. Rationale  Learning curve analysis cannot be used when it is difficult to accurately measure the impact of efficiency improvements. It can be difficult to measure the impact of the learning in a learning curve analysis. Since that is needed to analyze the expected decrease in time and cost, the fact that it is difficult to estimate means it is a limitation of learning curve analysis; therefore, this is an incorrect answer. Rationale  Learning curve analysis assumes all improvements in production efficiency are caused by employee learning. Learning curve analysis assumes that all improvements in efficiency are caused by employee learning. A different labor mix, improved machinery, and better-quality materials could also be the cause of improved efficiency. Because learning curve analysis ignores these factors, it is a limitation of learning curve analysis; therefore, this is an incorrect answer. Rationale  Learning curve analysis can only be used to predict performance that is within the range of data used to develop the analysis. Learning curve analysis is a way to estimate the time and cost to perform an activity under the assumption that people will learn to perform the activity more efficiently the more times they perform the task. Linear regression is a statistical technique where past data is used to develop an equation that can be used to predict something of interest. The data used to develop the regression equation define the “relevant range of activity” over which the equation is valid. Using the equation to predict costs for activity within the relevant range is valid; however, using the equation to predict costs for activity outside the relevant range is not valid. The need to stay within the relevant range limits the usefulness of regression analysis, which means it is a limitation of regression analysis, not learning curve analysis; therefore, this is the correct answer. Learning curve analysis can only be used to predict performance that is within the range of data used to develop the analysis. Correct Learning curve analysis assumes all improvements in production efficiency are caused by employee learning. Your Answer

6/14/22, 10:26 AM CMA Exam Review - Part 1 - Assessment Review https://app.efficientlearning.com/pv5/v8/5/app/cma/part1_2020.html?#assessmentReview 2/69 Question 2 1.B.3.b tb.reg.anal.008_1805 LOS: 1.B.3.b Lesson Reference: Regression Analysis Difficulty: medium Bloom Code: 4 How does a multiple linear regression equation differ from a simple linear regression equation? More than one dependent variable is predicted by a multiple linear regression equation but only one dependent variable is predicted in a simple linear regression equation. A multiple linear regression is likely to be less accurate than a simple linear regression model. A multiple linear regression is likely to be less difficult to interpret than a simple linear regression model. Rationale  More than one independent variable is used to predict a dependent variable in a multiple linear regression equation but only one independent variable is used to predict a dependent variable in a simple linear regression equation. Linear regression is a statistical technique where past data is used to develop an equation that can be used to predict something of interest. The factor being predicted is the dependent variable and the factor or factors used to predict the dependent variable are the independent variables. In multiple linear regression two or more independent variables are used to predict the dependent variable while only one independent variable is used to predict the dependent variable in simple linear regression. Therefore, this is the correct answer. Rationale  More than one dependent variable is predicted by a multiple linear regression equation but only one dependent variable is predicted in a simple linear regression equation. There is only one dependent variable in both types of regression; therefore, this is an incorrect answer. Rationale  A multiple linear regression is likely to be less accurate than a simple linear regression model. In multiple linear regression two or more independent variables are used to predict the dependent variable while only one independent variable is used to predict the dependent variable in simple linear regression. Because multiple linear regression uses more than one independent variable to predict a dependent variable, it is likely to be more accurate, not less accurate, than a simple linear regression model that uses only one independent variable to predict a dependent variable. Therefore, this is an incorrect answer. Rationale  A multiple linear regression is likely to be less difficult to interpret than a simple linear regression model. In multiple linear regression two or more independent variables are used to predict the dependent variable while only one independent variable is used to predict the dependent variable in simple linear regression. Because multiple linear regression uses more than one independent variable to predict a dependent variable, it is likely to be more difficult, not less difficult, to interpret than a simple linear regression model because the relationship between the multiple independent variables must be taken into consideration (multi-collinearity). Therefore, this is an incorrect answer. More than one independent variable is used to predict a dependent variable in a multiple linear regression equation but only one independent variable is used to predict a dependent variable in a simple linear regression equation. Correct

6/14/22, 10:26 AM CMA Exam Review - Part 1 - Assessment Review https://app.efficientlearning.com/pv5/v8/5/app/cma/part1_2020.html?#assessmentReview 3/69 Question 3 1.B.3.i aq.lc.anal.005_0720 LOS: 1.B.3.i Lesson Reference: Expected Value Computations and Learning Curve Analysis Difficulty: hard Bloom Code: 5 Wall, Corp. (Wall) is the leading manufacturer of drywall in the United States. Wall is trying to predict cash flow for the next year. Depreciation of $1 million is included in cost of goods sold (COGS). There is no depreciation expense as part of selling, general and administration expense (SG&A). Wall is not forecasting any capital expenditures or change in net working capital. Wall's tax rate is 20%. Below are Wall's estimates in millions: Estimate 1 Probability Estimate 2 Probability Sales $19.00 30% $16.50 70% COGS $13.50 60% $14.00 40% SG&A $3.00 50% $4.00 50% Based on the above estimates, what will be Wall's after-tax cash flow for next year? $0.04 $17.25 Rationale  $0.04 This answer does not add back depreciation. Depreciation is added to Net Income to get cash flow as it is a non-cash expense. Rationale  $0.05 This answer does not consider tax or add back depreciation. Tax is a cash expense, so it is considered. Depreciation, a non-cash expense, is added back to Net Income to get cash flow. Rationale  $17.25 This answer only considers sales. COGS, SG&A, and Tax are also cash flows that must be considered. An adjustment must be made for depreciation as well. Rationale  $1.04 Cash flow for the next year is calculated as follows: Estimate 1 Probability Weighted Value Estimate 2 Probability Weighted Value Total Weighted Value Sales $19.00 30% $5.70 $16.50 70% $11.55 $17.25 COGS $13.50 60% $8.10 $14.00 40% $5.60 $13.70 SG&A $3.00 50% $1.50 $4.00 50% $2.00 $3.50 Operating Income $0.05 Tax $0.01 Net Income $0.04 Add Back Depreciation $1.00 Cash Flow $1.04 $1.04 Correct $0.05 Your Answer

6/14/22, 10:26 AM CMA Exam Review - Part 1 - Assessment Review https://app.efficientlearning.com/pv5/v8/5/app/cma/part1_2020.html?#assessmentReview 4/69 Question 4 1.B.3.c aq.reg.anal.006_0720 LOS: 1.B.3.c Lesson Reference: Regression Analysis Difficulty: hard Bloom Code: 5 Eight quarters of production data from Pear, Inc., a cell phone manufacturing company, are presented below. Pear, Inc. Quarter Phones Cost 1 2,331 $3,245,874 2 2,657 $3,474,318 3 1,987 $2,883,675 4 2,412 $3,287,621 5 2,583 $3,354,966 6 2,497 $3,428,752 7 2,285 $3,152,347 8 2,645 $3,271,899 The regression analysis results on these data are displayed below. Coefficients Standard Error t Stat P-value Lower 95% Upper 95% Intercept $1,473,119 $356,978 4.13 0.01 $599,625 $2,346,614 Phones $738 $147 5.03 0.00 $379 $1,097 Regression Statistics Multiple R 0.90 R Square 0.81 Adjusted R Square 0.78 Standard Error $87,127 Observations 8 Based on the regression analysis result above, and with approximately 68% confidence, predict the total cost to produce 2,500 phones next quarter. $3,318,119 Between $3,143,865 and $3,492,373 Rationale  $3,318,119 This answer calculates the estimated total cost using the regression equation (total cost equation): Total costs = ($738 × 2,500 phones) + $1,473,119 = $3,318,119. However, this answer does not provide a 68% confidence interval around that estimate. Rationale  Between $2,960,994 and $3,675,244 This answer calculates the estimated total cost using the regression equation (total cost equation) and then uses the standard error for both total fixed costs of $356,978 and variable cost per phone of $147 to develop a 68% confidence interval. However, the standard error for the total cost estimate is $87,127, and this amount should be used to calculate a 68% confidence interval. Rationale  Between $3,230,992 and $3,405,246 This answer calculates the estimated total cost using the regression equation (total cost equation): Total costs = ($738 × 2,500 phones) + $1,473,119 = $3,318,119. Then it calculates the 68% confidence interval, which is one standard error: $3,318,119 ± $87,127 = between $3,230,992 and Between $3,230,992 and $3,405,246 Correct Between $2,960,994 and $3,675,244 Your Answer

6/14/22, 10:26 AM CMA Exam Review - Part 1 - Assessment Review https://app.efficientlearning.com/pv5/v8/5/app/cma/part1_2020.html?#assessmentReview 5/69 $3,405,246. Rationale  Between $3,143,865 and $3,492,373 This answer calculates the estimated total cost using the regression equation (total cost equation): Total costs = ($738 × 2,500 phones) + $1,473,119 = $3,318,119. But it then calculates a 95% confidence interval instead of a 68% confidence interval by using two standard errors.

6/14/22, 10:26 AM CMA Exam Review - Part 1 - Assessment Review https://app.efficientlearning.com/pv5/v8/5/app/cma/part1_2020.html?#assessmentReview 6/69 Question 5 1.B.3.h aq.lc.anal.003_0720 LOS: 1.B.3.h Lesson Reference: Expected Value Computations and Learning Curve Analysis Difficulty: medium Bloom Code: 3 Which of the following is a benefit of expected value computations? The underlying probabilities used in the expected value formula are usually based on subjective judgments. The expected value computation is the most likely outcome in the future. Expected value computations incorporate multiple possibilities, making them more representative of a certain future. Rationale  The underlying probabilities used in the expected value formula are usually based on subjective judgments. This is actually a shortcoming of expected value computations. Rationale  The expected value computation reduces multiple outcomes down to a single value, which is easily understood and can be entered into a budget plan. This is a benefit of expected value computations. Rationale  The expected value computation is the most likely outcome in the future. The result of the EV formula is not actually the most likely outcome in the future. It is a weighted average of the possible results used in the computation. This shortcoming is particularly important if the possible outcomes are discrete events (rather than a continuous range of possibilities). Rationale  Expected value computations incorporate multiple possibilities, making them more representative of a certain future. This statement is incorrect. Expected value computations that incorporate multiple possibilities are generally more representative of an uncertain future compared to forecasts of a single outcome. The expected value computation reduces multiple outcomes down to a single value, which is easily understood and can be entered into a budget plan. Correct

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version