SYM 506 Topic 4 normal distribution application example

Applied Business Probability and Statistics Grand Canyon University Free custom sample in 24 to 48h

This SYM 506 Topic 4 sample paper applies the normal model to a composite appliance repair company's daily service calls forward, backward and with checks. It was prepared for GCU SYM 506, Applied Business Probability and Statistics, catalog code SYM-506, a course in Grand Canyon University's MBA. With a mean of 84 calls and a standard deviation of 9 from 120 weekdays, more than 100 calls occur about 3.8 percent of the time and 75 to 95 calls about 73 percent. The 95th percentile, about 99 calls, sets staffing, verified against the log. The model is refused for skewed invoice amounts, where it would predict negative invoices.

CourseSYM 506 Applied Business Probability and Statistics
TopicTopic 4
Paper typeNormal distribution application
LengthAbout 1,030 words, 2 pages
FormatAPA 7 student paper
SchoolGrand Canyon University (GCU)
ProgramMBA
UpdatedOctober 2026

Free sample paper for SYM 506 Topic 4

1

Staffing for a 99-Call Day: Applying the Normal Model to Daily Service Calls Forward and Backward, and Refusing It for Invoice Amounts

[Author Name]

Colangelo College of Business, Grand Canyon University

SYM-506: Applied Business Probability and Statistics

Topic 4 Normal Distribution Application

[Instructor Name]

[Date]

The organization, setting and figures below are a composite written as a model document. No real employer, client, colleague or patient is described.

What this page is doingThe title states the backward calculation's result and the case where the model does not apply. The company and every figure are a composite; the sources are real.
2

Staffing for a 99-Call Day: Applying the Normal Model to Daily Service Calls Forward and Backward, and Refusing It for Invoice Amounts

The Measurement and Where Its Figures Come From

A composite appliance repair company records the number of service calls requested each weekday. Over the last 120 weekdays, excluding holidays, the mean was 84 calls and the standard deviation 9. Both figures come from the dispatch log, not from an assumption. Before using the normal model, the shape of the data was checked, as standard practice requires (Anderson et al., 2020): a histogram is roughly symmetric and single-peaked, the skewness is about 0.2, and the mean and median, 84 and 83, nearly coincide. Daily call counts are sums of many independent customer decisions, which tends to produce a roughly normal pattern (Montgomery & Runger, 2018). The model is therefore a reasonable description of this measurement, though not of every measurement the company keeps, as a later section shows.

Forward: The Chance of a Busy Day

How often will more than 100 calls arrive? Standardizing, z = (100 minus 84) / 9, about 1.78. The area to the right of z = 1.78 under the standard normal curve is about 0.038. Because the question asks for more than 100, the region is the upper tail, to the right of the value; reporting the area to the left, about 0.962, is the most common mechanical error and gives a nonsensical answer. About four weekdays in a hundred, roughly one a month, bring more than 100 calls.

Between Two Values

How often do calls fall between 75 and 95, the range the current staff of seven technicians handles comfortably? The two z-scores are (75 minus 84) / 9 = minus 1.00 and (95 minus 84) / 9, about 1.22. The cumulative area to the left of 1.22 is about 0.889, and to the left of minus 1.00 about 0.159. The probability of falling between them is the larger area minus the smaller: 0.889 minus 0.159, about 0.730. Subtracting in the other order would give a negative probability, an immediate sign of an error. About 73 percent of weekdays fall in the comfortable range.

Table 1

Normal Calculations for Daily Service Calls

QuestionCalculationRegionAnswer
More than 100 callsz = 1.78Upper tailAbout 0.038
Between 75 and 95 callsz from minus 1.00 to 1.22Between the two valuesAbout 0.730
Calls exceeded on only 5 percent of days84 + 1.645 times 9Value with 0.95 to its leftAbout 98.8, round to 99

Backward: The Staffing Level

The owners want enough technicians that the day's calls can be served on all but about one weekday in twenty. That reverses the calculation: find the call count with 95 percent of the distribution below it. The z-score with 0.95 to its left is about 1.645, so the value is 84 + 1.645 times 9, about 98.8, which rounds up to 99 calls. With each technician completing about 12 calls a day, 99 calls require 8.25 technicians, which means 9 on the schedule, or 8 technicians plus a part-time ninth on peak days. The current seven technicians can handle about 84 calls, the average day, which explains why the company falls behind on roughly half of all weekdays.

Checking the Answer

The backward result can be checked by running it forward: z = (99 minus 84) / 9, about 1.67, leaves about 4.8 percent of days above 99, consistent with the one-in-twenty target, with the small difference from 5 percent due to rounding 98.8 up to a whole call. The answer is also checked against the log: of the last 120 weekdays, 6 had more than 99 calls, 5 percent, matching the model.

Where the Normal Model Does Not Apply

The same company's invoice amounts look nothing like this. They are strongly skewed to the right, with a mean of 233 dollars, a standard deviation of about 148 and a long tail of large repairs. Applying the normal model to them produces answers that are internally consistent and practically wrong. It would put about 3.5 percent of invoices above 500 dollars, when the actual share is about 5.3 percent, and it would predict that about 5.7 percent of invoices are negative, which is impossible. Tukey (1977) argued that data should be examined before a model is chosen, and this comparison shows why: the model fits call counts because of how they arise and fails for invoices for the same reason.

A Spread That Belongs to a Different Quantity

One more caution applies. The standard deviation of 9 describes single days. If the owners want the chance that the average over a five-day week exceeds 90 calls, that average has a smaller spread, 9 divided by the square root of 5, about 4.0, and using 9 would overstate the chance considerably. The next topic develops this distinction; here it is enough to standardize every value against the spread of the quantity being asked about.

The Staffing Decision

The calculations support a specific change. Hiring two full-time technicians would cover the 95th percentile day but leave them underused on most days, when calls average 84. A cheaper arrangement is to hire one full-time technician, bringing capacity to about 96 calls, and contract a part-time technician for the busiest days, which the model and the log both show occur about one day in twenty. Because summer raises call volume, the mean and standard deviation should be recomputed for June through August separately, and staffing for those months set from the summer figures rather than the annual ones. The model gives a defensible starting point; the dispatch log, updated monthly, keeps it honest.

Conclusion

Daily service calls are roughly normal, with a mean of 84 and a standard deviation of 9, and the model answers forward questions, such as how often more than 100 calls arrive, and backward ones, such as the 99-call day the company should staff for. Every answer marks its region of the curve and is checked against the log. The same model applied to invoice amounts gives impossible results, because those data are skewed, and a weekly average must be standardized against its own smaller spread.

References

Anderson, D. R., Sweeney, D. J., Williams, T. A., Camm, J. D., Cochran, J. J., Fry, M. J., & Ohlmann, J. W. (2020). Statistics for business and economics (14th ed.). Cengage.

Montgomery, D. C., & Runger, G. C. (2018). Applied statistics and probability for engineers (7th ed.). Wiley.

Tukey, J. W. (1977). Exploratory data analysis. Addison-Wesley.

The SYM-506 Topic 4 assignment instructions

Topic 4 in SYM-506 asks MBA students to apply the normal distribution to a business measurement. Strong applications state where the mean and standard deviation came from and check that the data are roughly normal before using the model. Students should standardize values and mark the tail explicitly, handle the between-two-values case with the subtraction in the right order, reverse the process to find a value for a target proportion, check answers against the data and explain where the normal model would not apply. Every answer should name the region of the curve it uses, since reporting the wrong tail is the commonest mechanical error. Summer figures should be computed separately where the season shifts the mean.

How the SYM-506 Topic 4 example is put together

The finished example runs the calculation both ways. Given a value, it standardizes and reports the proportion of the population above or below, with the direction of the tail made unambiguous by a described shaded region. Given a target proportion, it works backward to the value, which is the harder direction and the one businesses actually need for setting service levels and thresholds. The normality assumption is examined rather than assumed, since business data are frequently skewed and applying the curve to a skewed distribution produces confident nonsense. Every answer is read as an operational statement, a service level, a warranty threshold, a specification limit or a stock cover figure.

SYM 506 Topic 4 rubric: what Excellent looks like

Faculty reward the right region of the curve and the right spread. An Excellent paper checks symmetry and skewness before using the model, citing Tukey on looking first. Credit goes to upper-tail and between-values calculations with regions named, and a backward calculation of 99 calls for staffing. The rubric values checking that answer forward and against the dispatch log, following Anderson and colleagues. Strong papers show the model failing for skewed invoices. Top marks go to standardizing a weekly average against its own smaller spread. Faculty also value a staffing decision that uses the model and the log together rather than either alone. Strong papers recompute the inputs for seasons that differ.

Common SYM 506 Topic 4 mistakes, and how to avoid them

Reporting the area on the wrong side of the curve is the mechanical error that dominates this topic, and a sketch or a described region prevents almost all of it. A second failure is applying the normal model to visibly skewed business data, which produces answers that are internally consistent and practically wrong. Papers lose marks for standardizing against a spread belonging to a different quantity, which the following topic will make explicit and which is easy to do without noticing. Answers reported as decimals with no operational statement leave the business content unused. Rounding standardized scores heavily before looking up the proportion introduces avoidable error into the final figure.

Get an SYM-506 Topic 4 example written to your instructions

Send the SYM-506 Topic 4 problems and the rubric from your classroom, with the measurement and parameters your section supplied. We write a custom example to those criteria, with tail direction shown, the reverse calculation demonstrated, the normality assumption examined and each answer stated as an operational rule, in 24 to 48 hours. The first is free.

More SYM 506 papers and MBA samples

SYM 506 Topic 4 questions, answered

How do I avoid getting the tail direction wrong?

Sketch the curve and shade what the question asked for before you look anything up. Standard tables give the area to one side by convention, and half the errors in this topic come from reporting that area when the question wanted the other one. The sketch takes ten seconds and converts a memory problem into a visual one that is difficult to get wrong.

What if my business data are not normal?

Say so, and either transform, use a different approach, or proceed with the limitation stated. Many business measures are right skewed because they are bounded below at zero and unbounded above, which is true of spend, duration and time to resolution. Applying the normal model anyway is defensible for some purposes if you say what you assumed, and indefensible if you say nothing.

How do I work backward from a percentage?

Find the standardized score corresponding to that proportion first, then convert it back to the original units using the mean and standard deviation. This is the direction used for setting service levels and specification limits, since a business usually starts from what percentage it wants to cover rather than from a value. Practicing it separately is worthwhile because it appears more often in real work.

Where can I find a free SYM 506 Topic 4 sample paper?

The normal application is printed here in full: the measurement, a busy day, between two values, staffing backward, checking the answer, where the model fails, a different spread, the staffing decision and the conclusion. Send your measurement's mean and spread and a worked application follows at no charge.

Why not apply the normal model to invoices in SYM 506 Topic 4?

Invoices are strongly skewed. The normal model would understate large invoices and predict that about 5.7 percent are negative, which is impossible.