CIA Gliem - Part 3 - Forecasting Questions

[1] Gleim #: 1.4.67In the standard regression equation y = a + bx, how is the letter b best described?

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

Answer (A) is correct. In the standard regression equation, b represents the variable coefficient. For example, in acost determination regression, y equals total costs, b is the variable cost per unit, x is the number of units produced,and a is fixed cost.Answer (B) is incorrect because the constant coefficient is a.Answer (C) is incorrect because x is the independent variable.Answer (D) is incorrect because the dependent variable is y.

Gleim's CIA Test Prep: Part III: Business Analysis and Information Technology(33 questions)

Copyright 2008 Gleim Publications, Inc. Printed for The Saboteur@ dvd4arab.com

[2] Gleim #: 1.4.69Based upon the data derived from the regression analysis, 420 maintenance hours in a month would mean the maintenancecosts (rounded to the nearest dollar) would be budgeted at

$3,600A.$3,746B.$3,780C.$3,790D.

Answer (A) is incorrect because the budgeted maintenance costs are $3,746.Answer (B) is correct. Substituting the given data into the regression equation results in a budgeted cost of $3,746(rounded to the nearest dollar).

y = a + bxy = 684.65 + 7.2884(420)y = $3,746

Answer (C) is incorrect because the budgeted maintenance costs are $3,746.Answer (D) is incorrect because the budgeted maintenance costs are $3,746.



[3] Gleim #: 1.4.70What is the percentage of the total variance that can be explained by the regression equation?

99.724%A.69.613%B.99.862%C.80.982%D.

Answer (A) is correct. The coefficient of determination (r²) measures the percentage of the total variance in cost thatcan be explained by the regression equation. If the coefficient of determination is .99724, 99.724% of the variance isexplained by the regression equation. Thus, the values in the regression equation explain virtually the entire amountof total cost.Answer (B) is incorrect because the percentage of the total variance explained by the regression equation is 99.724%,which corresponds to the coefficient of determination (r²), or .99724.Answer (C) is incorrect because the percentage of the total variance explained by the regression equation is 99.724%,which corresponds to the coefficient of determination (r²), or .99724.Answer (D) is incorrect because the percentage of the total variance explained by the regression equation is 99.724%,which corresponds to the coefficient of determination (r²), or .99724.



[4] Gleim #: 1.4.72An internal auditor for a large automotive parts retailer wishes to perform a risk analysis and wants to use an appropriatestatistical tool to help identify stores that would be out of line compared to the majority of stores. The most appropriatestatistical tool to use is

Time series multiple regression analysis to identify changes in individual stores over time.A.Linear time series analysis.B.Cross-sectional regression analysis.C.Cross tabulations with chi-square analysis of significance.D.

Answer (A) is incorrect because the objective is to compare stores at one moment in time. Multiple regression timeseries analysis compares the performance of an individual store over a period of time.Answer (B) is incorrect because linear time series analysis is inapplicable. It is a simple model that compares data foran individual store over time.Answer (C) is correct. Time series data pertain to a given entity over a number of prior time periods. Cross-sectionaldata, however, pertain to different entities for a given time period or at a given time. Thus, cross-sectional regressionanalysis is the most appropriate statistical tool because it compares attributes of all stores’ operating statistics at onemoment in time.Answer (D) is incorrect because cross tabulations have to be built on a model of expectations. Unless the model isbuilt, the analysis is not useful.



[5] Gleim #: 1.4.73Quality control programs employ many tools for problem definition and analysis. A scatter diagram is one of these tools. Theobjective of a scatter diagram is to

Show frequency distribution in graphic form.A.Display a population of items for analysis.B.Show the vital trend and separate trivial items.C.Divide a universe of data into homogeneous groups.D.

Answer (A) is incorrect because the objective of a histogram is to show frequency distribution in graphic form.Answer (B) is correct. The objective of a scatter diagram is to demonstrate correlations. Each observation isrepresented by a dot on a graph corresponding to a particular value of X (the independent variable) and Y (thedependent variable).Answer (C) is incorrect because regression analysis is used to find trend lines.Answer (D) is incorrect because the objective of stratification is to divide a universe of data into homogeneous groups.



[6] Gleim #: 1.4.74Violation of which assumption underlying regression analysis is prevalent in time series analysis?

Variance of error term is constant.A.Distribution of error terms is normal.B.Expected value of error term equals zero.C.Error terms are independent.D.

Answer (A) is incorrect because constant variance of the error term is usually met.Answer (B) is incorrect because normal distribution of the error term is usually met.Answer (C) is incorrect because an expected value of the error term equal to zero is usually met.Answer (D) is correct. Time series analysis is a regression model in which the independent variable is time. In timeseries analysis, the value of the next time period is frequently dependent on the value of the time period before that.Hence, the error terms are usually correlated or dependent on the prior period; i.e., they are characterized byautocorrelation (serial correlation).



[7] Gleim #: 1.4.76As part of a risk analysis, an auditor wishes to forecast the percentage growth in next month’s sales for a particular plantusing the past 30 months’ sales results. Significant changes in the organization affecting sales volumes were made within thelast 9 months. The most effective analysis technique to use would be

Unweighted moving average.A.Linear regression analysis.B.Exponential smoothing.C.Queuing theory.D.

Answer (A) is incorrect because an unweighted average will not give more importance to more recent data.Answer (B) is incorrect because linear regression analysis determines the equation for the relationship amongvariables. It does not give more importance to more recent data.Answer (C) is correct. Under exponential smoothing, each forecast equals the sum of the last observation times thesmoothing constant, plus the last forecast times one minus the constant. Thus, exponential means that greater weightis placed on the most recent data, with the weights of all data falling off exponentially as the data age. This feature isimportant because of the organizational changes that affected sales volume.Answer (D) is incorrect because queuing theory is used to minimize the cost of waiting lines.



[8] Gleim #: 1.4.77The average labor cost per unit for the first batch produced by a new process is $120. The cumulative average labor cost afterthe second batch is $72 per product. Using a batch size of 100 and assuming the learning curve continues, the total labor costof four batches will be

$17,280A.$10,368B.$2,592C.$4,320D.

Answer (A) is correct. The learning curve reflects the increased rate at which people perform tasks as they gainexperience. The time required to perform a given task becomes progressively shorter. Ordinarily, the curve isexpressed in a percentage of reduced time to complete a task for each doubling of cumulative production. Onecommon assumption in a learning curve model is that the cumulative average time (and labor cost) per unit is reducedby a certain percentage each time production doubles. Given a $120 cost per unit for the first 100 units and a $72 costper unit when cumulative production doubled to 200 units, the learning curve percentage must be 60% ($72 ÷ $120).If production is again doubled to 400 units (four batches), the average unit labor cost should be $43.20 ($72 × 60%).Hence, total labor cost for 400 units is estimated to be $17,280 (400 × $43.20).Answer (B) is incorrect because $10,368 is based on the assumption that the cumulative average unit labor cost isreduced by the learning curve percentage with each batch, not each doubling of output.Answer (C) is incorrect because $2,592 represents the labor cost of 100 units at the unit rate expected after anotherdoubling of production to eight batches.Answer (D) is incorrect because $4,320 equals the cost of the items in the fourth batch.



[9] Gleim #: 1.4.78If an 80% learning curve is applicable, Moss Point’s total cost on this order would be estimated at

$41,800A.$38,000B.$26,400C.$32,000D.

Answer (A) is incorrect because $41,800 is the total cost for 200 units.Answer (B) is incorrect because $38,000 is the total variable cost for 200 units.Answer (C) is correct. Assuming that the cumulative average-time model applies, an 80% learning curve means thatthe cumulative average time per unit (and labor cost, given a constant labor rate) declines by 20% when unit outputdoubles in the early stages of production. The first lot size was 50 units, which was produced at a total cost of $15,400($1,500 for materials + $13,900 for labor and overhead). Materials costs are strictly variable and should remainproportional to production. The labor ($8,500) and variable overhead ($4,000) costs (labor-related), however, will beaffected by the learning curve. The average cost per lot for labor and variable overhead after 100 units have beenproduced should be 80% of the costs of the first lot of 50 units. Thus, the average labor and variable overhead cost per50-unit lot will be $10,000 ($12,500 × 80%). If production doubles again (to a total production of 200 units or fourlots of 50 each), the cumulative average cost for labor and variable overhead will be $8,000 per lot ($10,000 × 80%).Given four lots of 50 each, at an average cost of $8,000 per lot, the total cost for labor and variable overhead must be$32,000. Adding $6,000 for raw materials ($1,500 per 50-unit lot) gives a total variable cost of $38,000 for 200 units.Fixed overhead is 10% of total variable cost, so total cost is $41,800. The total cost for the last 150 units is $26,400($41,800 – $15,400).Answer (D) is incorrect because $32,000 is the total cost for labor and variable overhead for 200 units.



[10] Gleim #: 1.4.79If Moss Point had experienced a 70% learning curve, the bid for the 150 units would

Be 10% lower than the total bid at an 80% learning curve.A.Show a 30% reduction in the total direct labor hours required with no learning curve.B.Include increased fixed overhead costs.C.Include 6.40 direct labor hours per unit at $8.50 per hour.D.

Answer (A) is incorrect because no information about the bid (as opposed to costs) is given. Moreover, a reduction inthe learning curve from 80% to 70% will reduce total costs for the last 150 units from $26,400 to $18,150, a reductionof 31.25%.Answer (B) is incorrect because, with no learning curve effect, estimated total hours would be 4,000 instead of 1,960,a change of more than 50%.Answer (C) is incorrect because fixed costs applied per lot would decline because they are based on labor hours,which are declining.Answer (D) is correct. The sum of the direct labor hours for the initial lot of 50 units was 1,000. A second lot of 50would reduce the cumulative hours per lot to 700 (1,000 × 70%). A doubling to four lots would reduce the cumulativehours per lot to 490 (700 × 70%). Thus, for an output of 200 units, the total hours worked would be 1,960 (4 × 490).Subtracting the 1,000 hours required for the first 50 units from the 1,960-hour total gives 960 hours for the last 150units. Dividing 960 hours by 150 units produces a per-unit time of 6.4 hours.



[11] Gleim #: 1.4.82A firm is attempting to estimate the reserves for doubtful accounts. The probabilities of these doubtful accounts follow atransition process over time. They evolve from their starting value to a changed value. As such, the most effective techniqueto analyze the problem is

Dynamic programming.A.Markov chain analysis.B.Econometric theory.C.Monte Carlo analysis.D.

Answer (A) is incorrect because dynamic programming is a problem-solving approach that breaks a largemathematical model into a number of smaller, manageable problems.Answer (B) is correct. A Markov chain is a series of events in which the probability of an event depends on theimmediately preceding event. An example is the game of blackjack in which the probability of certain cards beingdealt is dependent upon what cards have already been dealt. In the analysis of bad debts, preceding events, such ascollections, credit policy changes, and writeoffs, affect the probabilities of future losses.Answer (C) is incorrect because econometrics forecasts the impact of different economic policies and conditions.Answer (D) is incorrect because Monte Carlo analysis is a simulation technique that uses random-number proceduresto create values for probabilistic components.



[12] Gleim #: 1.4.84The operating condition that cannot be identified by using a queuing model is the

Average percentage of time that a service facility is idle.A.Average number of units in the system and the mean length of the queue.B.Actual amount of time each unit spends in the queue.C.Probability of a specified number of units in the queue.D.

Answer (A) is incorrect because the queuing model calculates the average percentage of time that a service facility isidle, the probability of a specified number of units in the queue, and the average number of units in the system and themean length of the queue.Answer (B) is incorrect because the queuing model calculates the average percentage of time that a service facility isidle, the probability of a specified number of units in the queue, and the average number of units in the system and themean length of the queue.Answer (C) is correct. Queuing models determine the operating characteristics of a waiting line: the probability thatno units are in the system, the average units in the line, the average units in the system, the average time a unit waits,the average time a unit is in the system, the probability that a unit must wait, and the probability of a given number ofunits in the system. However, the actual time spent in the queue cannot be determined from the model.Answer (D) is incorrect because the queuing model calculates the average percentage of time that a service facility isidle, the probability of a specified number of units in the queue, and the average number of units in the system and themean length of the queue.



[13] Gleim #: 1.4.90The time that car 3 will have to wait to be serviced (not including its own service time) is

5+ minutes.A.0-2 minutes.B.4 minutes.C.3 minutes.D.

Answer (A) is incorrect because car 3 must wait for 4 minutes.Answer (B) is incorrect because car 3 must wait for 4 minutes.Answer (C) is correct. Car 1 is at the attached window and will require 3 minutes to service. Car 2 must wait for car1 to be serviced (3 minutes in the queue + 3 minutes to be serviced = 6 minutes). Car 3 arrived at the attachedwindow 2 minutes after cars 1 and 2. It must wait 1 minute for car 1 to be serviced and 3 minutes for car 2 to beserviced, a waiting time of 4 minutes.Answer (D) is incorrect because car 3 must wait for 4 minutes.



[14] Gleim #: 1.4.91The time that car 4 will have to wait to be serviced (not including its own service time) is

4 minutes.A.3 minutes.B.0-2 minutes.C.5+ minutes.D.

Answer (A) is correct. Car 4 arrives at the just-vacated island window 4 minutes after car 3. It must wait 4 minutesfor car 3 to be serviced.Answer (B) is incorrect because car 4 must wait 4 minutes.Answer (C) is incorrect because car 4 must wait 4 minutes.Answer (D) is incorrect because car 4 must wait 4 minutes.



[15] Gleim #: 1.4.93Under conditions of risk, the rational, economic decision maker will use which one of the following decision criteria?

Maximax.A.Laplace.B.Expected monetary value.C.Minimum regret.D.

Answer (A) is incorrect because maximax is adopted by risk seekers.Answer (B) is incorrect because the insufficient reason (Laplace) criterion applies when the decision maker cannotassign probabilities to the states of nature arising after a decision.Answer (C) is correct. A rational economic decision maker (one completely guided by objective criteria) will useexpected monetary value to maximize gains under conditions of risk because (s)he is risk-neutral (the utility of a gainequals the disutility of a loss of the same absolute amount). Expected value represents the long-term average payofffor repeated trials. The best choice is the one having the highest expected value (sum of the products of the possibleoutcomes and their respective probabilities).Answer (D) is incorrect because the minimum regret criterion is used by a player who wishes to minimize the effect ofa bad decision in either direction.



[16] Gleim #: 1.4.94The decision rule that selects the strategy with the highest utility payoff if the worst state of nature occurs is the

Maximax rule.A.Maximize utility rule.B.Minimize regret rule.C.Maximin rule.D.

Answer (A) is incorrect because the maximax rule selects the choice that provides the greatest payoff if the mostfavorable state of nature occurs.Answer (B) is incorrect because the maximize utility rule is not a decision rule.Answer (C) is incorrect because the minimize regret rule selects the action that minimizes the maximum opportunitycost.Answer (D) is correct. The maximin rule determines the minimum payoff for each decision and then chooses thedecision with the maximum minimum payoff. It is a conservative criterion adopted by risk-averse players, that is,those for whom the disutility of a loss exceeds the utility of an equal gain.



[17] Gleim #: 1.4.96If the bank uses the maximax criterion for selecting the location of the branch, it will select

L1.A.L3.B.L2.C.L5.D.

Answer (A) is incorrect because L1 is the choice based on the maximin criterion.Answer (B) is incorrect because L3 is the choice based on the Laplace criterion.Answer (C) is incorrect because L2 is the choice based on the minimax regret criterion.Answer (D) is correct. Under the maximax criterion, the decision maker selects the choice that maximizes themaximum profit. The maximum profits for the five locations are

Location L1 L2 L3 L4 L5Maximum Profit 15 21 17 26 29

The location with the greatest potential profit is L5.



[18] Gleim #: 1.4.97If the bank uses the minimax regret criterion for selecting the location of the branch, it will select

L1.A.L5.B.L2.C.L3.D.

Answer (A) is incorrect because L1 is the choice based on the maximin criterion.Answer (B) is incorrect because L5 is the choice based on the maximax criterion.Answer (C) is correct. Under the minimax regret criterion, the decision maker selects the choice that minimizes themaximum regret (opportunity cost). The maximum regret for each location is determined from the opportunity lossmatrix . The maximum regret for each location is the highest number in each column as indicated below.

Location L1 L2 L3 L4 L5Maximum Regret 14 9 12 10 13

The location with the minimum regret is L2. If demand is low, L2 has a payoff of –2, whereas L1 has a payoff of 7.Answer (D) is incorrect because L3 is the choice based on the Laplace criterion.



[19] Gleim #: 1.4.98If, in addition to the estimated profits, management of the bank assesses the probabilities of high, medium, and low demandsto be 0.3, 0.4, and 0.3, respectively, what is the expected opportunity loss from selecting location L4?

7.50A.7.90B.5.00C.5.50D.

Answer (A) is incorrect because 7.50 is the expected opportunity loss from selecting location L2.Answer (B) is incorrect because 7.90 is the expected opportunity loss from selecting location L5.Answer (C) is incorrect because 5.00 is the expected opportunity loss from selecting location L1.Answer (D) is correct. The opportunity loss matrix is as follows:

Location L1 L2 L3 L4 L5

Demand: High 14 = 29–15 8 = 29–21 12 = 29–17 3 = 29–26 0 = 29-29

Medium 2 = 14–12 6 = 14–8 0 = 14–14 4 = 14–10 10 = 14–4

Low 0 = 7–7 9 = 7–(–2) 3 = 7–4 10 = 7–(–3) 13 = 7–(–6)

The expected opportunity loss from selecting location L4 is 5.50 [(3 × 0.3) + (4 × 0.4) + (10 × 0.3)].



[20] Gleim #: 1.4.101The expected value of perfect information is the

Difference between the expected profit under certainty and the expected opportunity loss.A.Difference between the expected profit under certainty and the expected monetary value of the best act underuncertainty.

B.

Sum of the conditional profit (loss) for the best event of each act times the probability of each event occurring.C.Same as the expected profit under certainty.D.

Answer (A) is incorrect because there is no expected opportunity loss under conditions of certainty.Answer (B) is correct. Perfect information permits certainty that a future state of nature will occur. The expectedvalue of perfect information determines the maximum amount a decision maker is willing to pay for information. It isthe difference between the expected value without perfect information, that is, the expected value of the best actionunder uncertainty and the expected value under certainty. Under certainty, a decision maker knows in each case whichstate of nature will occur and can act accordingly.Answer (C) is incorrect because the expected value of perfect information is the excess of the total conditional profitsunder certainty over the profit from the best decision under uncertainty.Answer (D) is incorrect because the expected value of perfect information is the difference between the expectedprofit under certainty and the profit from the best decision under uncertainty.



[21] Gleim #: 1.4.102The estimated demand for pretzels at the next home football game using an expected value approach is

4,000 pretzels.A.4,400 pretzels.B.5,000 pretzels.C.Some amount other than those given.D.

Answer (A) is incorrect because 4,000 pretzels assumes each outcome is equally likely.Answer (B) is correct. The calculation using an expected value approach weights each possible sales volume by itsprobability. Thus, the estimated demand is 4,400 pretzels.

Volume Probability Result2,000 × .10 = 2003,000 × .15 = 4504,000 × .20 = 8005,000 × .35 = 1,7506,000 × .20 = 1,200

Expected value 4,400

Answer (C) is incorrect because 5,000 pretzels is the estimated demand using a deterministic approach based on themost likely outcome.Answer (D) is incorrect because 4,400 pretzels is among the responses given.



[22] Gleim #: 1.4.104The expected payoff if the vendor has perfect information is

$1,960A.$3,900B.$2,200C.$1,360D.

Answer (A) is incorrect because the least the vendor could make by having perfect information is $2,000 on cold days.Answer (B) is incorrect because the most the vendor can make is $2,500 per day.Answer (C) is correct. The vendor would like to sell coffee on cold days ($2,000) and soft drinks on hot days($2,500). Hot days are expected 40% of the time. Hence, the probability is 40% of making $2,500 by selling softdrinks. The chance of making $2,000 by selling coffee is 60%. The payoff equation is:

.4($2,500) + .6($2,000) = $2,200

Answer (D) is incorrect because the least the vendor could make by having perfect information is $2,000 on cold days.



[23] Gleim #: 1.4.106An audit manager has just returned from an executive training program and has suggested that the audit department developa mathematical model to help identify factors that may be causing changes in the cost of production. According to themanager, the model should recognize that the company currently has three separate production (cost) centers. Which of thefollowing approaches would best provide the analysis suggested by the audit manager?

Develop a linear regression analysis relating the cost of production to the cost of goods sold.A.Develop a classical variables sampling estimate of cost of production per department, with the sample stratified by thedollar value of each product produced.

B.

Develop a 3-year ratio analysis of the cost of production compared to the cost of raw inventory across the threedepartments.

C.

Develop a multiple regression analysis of production costs, including such variables as raw material inventory costs,number of employees in the department, and overtime pay.

D.

Answer (A) is incorrect because like ratio analysis, a linear regression addresses only one possible cause of the costincrease.Answer (B) is incorrect because a classical variables sampling estimate does not help quantify the reasons for thechange in production costs.Answer (C) is incorrect because a ratio analysis of raw inventory could only identify one possible cause for the costincrease.Answer (D) is correct. Regression analysis extends correlation to find an equation for the linear relationship amongvariables. The behavior of a dependent variable, such as cost of production, is explained in terms of one or moreindependent variables (for example, raw material costs, employees, overtime). Thus, multiple regression analysisdetermines functional relationships among quantitative variables.



[24] Gleim #: 1.4.107The following data on variables x and y was collected from June to October:

June July August September Octoberx 24 31 19 15 22y 104 76 124 140 112

The correlation coefficient between variables x and y is nearest to

-1.00A.0.50B.1.00C.0.00D.

Answer (A) is correct. A correlation coefficient of -1.00 implies a perfect inverse correlation; that is, the observationsfall exactly along a straight line and the value of one variable increases (decreases) as the other decreases (increases).In the example to the left, the equation of the straight line is

y = 200 – 4xor x = 50 – 1y

4

Answer (B) is incorrect because a positive correlation coefficient implies that one variable increases (decreases) asthe other increases (decreases). The data clearly do not support this conclusion.Answer (C) is incorrect because a positive correlation coefficient implies that one variable increases (decreases) asthe other increases (decreases). The data clearly do not support this conclusion.Answer (D) is incorrect because a correlation coefficient of zero implies that the two variables are unrelated. The dataclearly indicate that the two variables move in opposite directions.



[25] Gleim #: 1.4.111The technique used in analyzing the problem is best described as

Simulation theory.A.Differential calculus.B.Linear programming.C.Integrated autoregressive-moving average (ARIMA) modeling.D.

Answer (A) is correct. Simulation is a technique for experimenting with logical/mathematical models using acomputer. Despite the power of mathematics, many problems cannot be solved by known analytical methods becauseof the behavior of the variables and the complexity of their interactions. However, the performance of a quantitativemodel under uncertainty may be investigated by randomly selecting values for each of the variables in the model(based on the probability distribution of each variable) and then calculating the value of the solution. If this process isperformed a large number of times, the distribution of results from the model will be obtained.Answer (B) is incorrect because differential calculus is used to establish optimization points.Answer (C) is incorrect because linear programming optimizes outputs given scarce resources.Answer (D) is incorrect because ARIMA modeling is a time-series technique.



[26] Gleim #: 1.4.117Which of the following is not true about simulation models?

They are deterministic in nature.A.They emulate stochastic systems.B.They mathematically estimate what actual performance would be.C.The may involve sampling.D.

Answer (A) is correct. Simulation is a technique for experimenting with logical/mathematical models using acomputer. The simulation procedure has five steps: define the objectives, formulate the model, validate the model,design the experiment, and conduct the simulation and evaluate the results. A simulation uses the laws of probabilityto generate values for random variables. Thus, simulation models are probabilistic, not deterministic.Answer (B) is incorrect because simulation models are by definition stochastic or probabilistic models.Answer (C) is incorrect because simulation models mathematically estimate what performance would be undervarious conditions.Answer (D) is incorrect because simulation modeling samples the operation of a system.



[27] Gleim #: 1.4.118A cost-volume-profit model developed in a dynamic environment determined that the estimated parameters used may varybetween limits. Subsequent testing of the model with respect to all possible values of the estimated parameters is termed

Statistical hypothesis testing.A.A time-series study.B.Statistical estimation.C.A sensitivity analysis.D.

Answer (A) is incorrect because statistical hypothesis testing calculates the conditional probability that both thehypothesis is true and the sample results have occurred.Answer (B) is incorrect because a time-series study involves forecasting data over time.Answer (C) is incorrect because statistical estimation involves the estimation of parameters.Answer (D) is correct. After a problem has been formulated into any mathematical model, it may be subjected tosensitivity analysis. Sensitivity analysis is a method for studying the effects of changes in one or more variables on theresults of a decision model.



[28] Gleim #: 1.4.120A company is deciding whether to purchase an automated machine to manufacture one of its products. Expected net cashflows from this decision depend on several factors, interactions among those factors, and the probabilities associated withdifferent levels of those factors. The method that the company should use to evaluate the distribution of net cash flows fromthis decision and changes in net cash flows resulting from changes in levels of various factors is

Linear programming.A.Differential analysis.B.Simulation and sensitivity analysis.C.Correlation analysis.D.

Answer (A) is incorrect because linear programming is a mathematical technique for optimizing a given objectivefunction subject to certain constraints.Answer (B) is incorrect because differential analysis is used for decision making that compares differences in costs(revenues) of two or more options.Answer (C) is correct. Simulation is a technique used to describe the behavior of a real-world system over time. Thistechnique usually employs a computer program to perform the simulation computations. Sensitivity analysis examineshow outcomes change as the model parameters change.Answer (D) is incorrect because correlation analysis is a statistical procedure for studying the relation betweenvariables.



[29] Gleim #: 1.4.122A regression equation

Estimates the independent variable.A.Encompasses factors outside the relevant range.B.Is based on objective and constraint functions.C.Estimates the dependent variables.D.

Answer (A) is incorrect because the dependent variable is estimated using regression analysis.Answer (B) is incorrect because regression results are limited to observations within the relevant range.Answer (C) is incorrect because regression analysis does not use constraint functions.Answer (D) is correct. Regression analysis is used to find an equation for the linear relationship among variables.The behavior of the dependent variable is explained in terms of one or more independent variables. Regressionanalysis is often used to estimate a dependent variable (such as cost) given a known independent variable (such asproduction).



[30] Gleim #: 1.4.125The four components of time series data are secular trend, cyclical variation, seasonality, and random variation. Theseasonality in the data can be removed by

Ignoring it.A.Taking the weighted average over four time periods.B.Subtracting a seasonality factor from the data.C.Multiplying the data by a seasonality factor.D.

Answer (A) is incorrect because seasonality factors cannot be ignored; they are reflected in the data and must beconsidered for a model to be accurate.Answer (B) is correct. Time series analysis relies on past experience. Changes in the value of a variable may haveseveral possible components including secular trends, cyclical variation, seasonality, and random variation. Seasonalvariations are common in many businesses. A variety of methods exist for including seasonal variations in aforecasting model, but most methods use a seasonal index. Alternatively, seasonal variations can be removed fromdata by using a weighted average of several time periods instead of data from individual periods.Answer (C) is incorrect because the seasonality adjustment for a single season’s data may be an increase or adecrease.Answer (D) is incorrect because adding a seasonality factor to, or subtracting it from, a forecast based on trendanalysis is a means of adjusting for seasonality.



[31] Gleim #: 1.4.126A widely used approach that managers use to recognize uncertainty about individual items and to obtain an immediatefinancial estimate of the consequences of possible prediction errors is

Expected value analysis.A.Sensitivity analysis.B.Learning curve analysis.C.Regression analysis.D.

Answer (A) is incorrect because expected value is the probabilistically weighted average of the outcomes of an action.Answer (B) is correct. Sensitivity analysis determines how a result varies with changes in a given variable orparameter in a mathematical decision model. For example, in a present value analysis, a manager might first calculatethe net present value or internal rate of return assuming that a new asset has a 10-year life. The NPV or IRR can thenbe recalculated using a 5-year life to determine how sensitive the result is to the change in the assumption.Answer (C) is incorrect because learning curve analysis quantifies how labor costs decline as employees learn theirjobs through repetition.Answer (D) is incorrect because regression, or least squares, analysis determines the average change in the dependentvariable given a unit change in one or more independent variables.



[32] Gleim #: 1.4.128Which of the following will allow a manufacturer with limited resources to maximize profits?

Linear programming.A.Regression analysis.B.The Delphi technique.C.Exponential smoothing.D.

Answer (A) is correct. Linear programming is a technique used to optimize an objective function, that is, to maximizea revenue or profit function or to minimize a cost function, subject to constraints, e.g., limited (scarce) resources orminimum/maximum levels of production, performance, etc. In business, linear programming is used for planningresource allocations. Managers are often faced with problems of selecting the most profitable or least costly way touse available resources.Answer (B) is incorrect because regression analysis is used to fit a linear trend line to a dependent variable based onone or more independent variables.Answer (C) is incorrect because the Delphi technique is an approach in which the manager solicits opinions on aproblem from experts, summarizes the opinions, and feeds the summaries back to the experts (without revealing anyof the participants to each other). The process is reiterated until the opinions converge on an optimal solution.Answer (D) is incorrect because under exponential smoothing, each forecast equals the sum of the last observationtimes the smoothing constant, plus the last forecast times one minus the constant. Thus, exponential means thatgreater weight is placed on the most recent data, with the weights of all data falling off exponentially as the data age.



[33] Gleim #: 1.4.130The sales manager for a builder of custom yachts developed the following conditional table for annual production and sales

Demand 10 20 30 50Probability 0.1 0.2 0.5 0.2

Yachts Built Expected Profit10 10 10 10 1020 0 20 20 2030 -10 10 30 3050 -30 -10 10 50

According to the table, how many yachts should be built?

30A.10B.50C.20D.

Answer (A) is correct. To achieve the maximum expected profit, 30 yachts should be built. For each level ofproduction, multiply the probability of demand by the expected profit. The computation is: 0.1(-$10) + 0.2($10) + 0.5($30) + 0.2($30) = $22.Answer (B) is incorrect because of the following computation: 0.1($10) + 0.2($10) + 0.5($10) + 0.2($10) = $10.Answer (C) is incorrect because of the following computation: 0.1(-$30) + 0.2(-$10) + 0.5($10) + 0.2($50) = $10.Answer (D) is incorrect because of the following computation: 0.1($0) + 0.2($20) + 0.5($20) + 0.2($20) = $18.



CIA Gliem - Part 3 - Forecasting Questions

Documents

Transcript of CIA Gliem - Part 3 - Forecasting Questions