Bus 625 Discussion Posts

Bus 625 Week 2 DQ-1 Assignment

Children in Multigenerational Households

Q1: Post the URL and the distribution graph from the website.

Q2: Discuss who you believe generated the data. Do you think it is credible?

I believe the United States Census Bureau generated this data in collaboration with the U.S. Department of Commerce. The U.S. Census Bureau provides data about the nation’s people and economy. The department of commerce provides the data necessary to support commerce and constitutional democracy and conduct foundational research and development. I believe the data is credible because the two sources are government agencies. Most of the governemnt data is either state-sponsored or collected and processed for continuous periods before it is made public.

Q3: Discuss what the graph reveals about the variable.

The graph indicates the percentage of children under 18 years living in multigenerational households by race and Hispanic origin. It compares the data for 2018 and 2008 on the same variable. According to this graph, the number of children living in multigenerational households is highest for native Hawaiian and other Pacific Islanders alone. The second-ranking race is American Indian and Alaska Native, followed by Asian. The race that records the lowest number of under-18’s living in multigenerational households is the white, not Hispanic or Latino, followed by white alone.

Q3: Explain any unusual aspects, as well as the shape, center, and spread of the distribution.

It is crucial to note that some races could have a high percentage of children living in multigenerational households but still have a small number compared to others depending on the entire population in consideration. For instance, with millions of whites, the number of children living in multigenerational households could be high but, if converted into a percentage, be smaller than, for instance, Asians. The bigger the population, the smaller the percentage of children in multigenerational households. Another thing I took note of is that there has been a sharp increase, in most instances, in the ten years (2008-2018). At the middle of the distribution, we have the Black or African American Alone category of children with almost the same percentage (15.2% in 2018) as Hispanic or Latino (14.9% in 2018).

Q4: Discuss your own interpretation of the distribution.

Several variables could influence this percentage. For instance, it would be crucial to understand the mortality rate of the same races recorded. Another variable could be the level of income or financial stability measures of families in these races, as high income could correlate to low mortality rates, better health care access for the elderly, and many other factors. Yet, the data is significant in differentiating the growth rate of multigenerational households and how the variable compares racially. The percentage does not indicate the exact population. Hence, it would be hard to derive exact change when comparing these groups to their total population. Even with the same percentage, two races could differ in the population number. However, it is such a crucial piece of data as far as race is concerned.

BUS 625 Week 6 DQ 1 Profit Payoff Decision Role Play Activity

As a business executive, it is necessary to understand the products and their probabilities to make accurate decisions. There should be a good understanding of the data. In my efforts, I will analyze data for toy 1 and toy 2 and note the differences as both cannot be approached at the same time.

Helpful techniques to use in analysis:

• Insightful chain of importance measure using AHP to solve complex choices: Analytic Hierarchy Process (AHP) method will help in moderating any subjectivity or instinct that goes into a choice. This technique has several benefits in its usability, being an effortlessly reasonable system, separating complex issues into smaller steps, and does not require information sets (Canco et al., 2021).
• Conjoint investigation for statistical surveying
• Cost examination to assess monetary dynamics
• Dynamic decision trees to survey different preceding extreme dynamic
• Game hypothesis for settling on essential choices that include outsiders.
• Multi-casting a ballot to settle on reasonable and adjusted collective choices.

Toy 1

This product has been manufactured just recently and has not yet been introduced into the market. This is a crucial benefit because if the marketing is done right, demand could be higher than the old toys. The possibility of competition is low because it may take time before other producers develop a replica. To determine product viability, it is necessary to have a test or trial session with actual customers. Giving them a chance to use the toy and understand their perception. Gather their opinions through surveys and reviews and analyze them later.

Toy 2

I would approximate the profitability of this toy using decision analysis such decision tree method. I would consider both the good and bad possibilities to understand the product potential. Toy 2 will be successful because there is high demand. However, it is necessary to figure out whether the demand will remain seasonal or not. If seasonal, the company has to customize production to match the expected demand for each season.

References

Canco, I., Kruja, D., & Iancu, T. (2021). AHP, a reliable method for quality decision making: A case study in business. Sustainability, 13(24), 13932. https://doi.org/10.3390/su132413932

BUS 625 Week 5 DQ 1 Quality Control Role Play Activity 1

1. Based on your research, identify the acceptable weight range tolerance for the candy packages (i.e., plus or minus 1 ounce). Support your decision with credible sources.
2. Explain in detail the quality control process you recommend.
3. Explain why the process will be acceptable by government regulators.
4. Explain how your technique would reject the out of limit packages.

Sharpe et al. (2018) define quality control as a tool that manufacturing and service industries use in the larger effort of the continual improvement process. Thus, a company can use several methods to ensure package weights are in the acceptable range. For instance, the National Institute of Standards and Technology (NIST) is responsible for developing rules on package requirements, including but not limited to maximum allowable variation, individual packages requirements, and average requirements (NIST, 2019). Referring to Table 2-5, Maximum Allowable Variations (MAVs) for Packages Labeled by Weight on page 156 of the NIST handbook, there is an allowable MAV threshold of 9/16 ounces for packages weighing between 11.20 oz to 13.44 oz. Hence, for a 12-ounce candy package, there can be an allowance of +/- 0.5625, which translates to a range of 11.44 to 12.5 ounces.

The production line process should get automated to accept absolute values to achieve a median 12-ounce package. Thus, the machines would get calibrated to the individual weight of candy needed and the exact amount of candy required for the 12-ounces. Through this, some candy packages would only deviate from the 12-ounce mark by an insignificant amount. In manufacturing large quantities, packages often run through the conveyer belt and under funnels that operators can input a specific number of candies per package to meet the weight requirement. As seen in various production factories, laser counting technology could eliminate any package that deviates from the limits. When used in an automated process, it allows only a requisite number of candies to fall through the funnel before the counter shuts the funnel.

It is necessary to keep a control chart to ensure accurately weighed packages. If the output is below or above the required weight, the machines can get fine-tuned to ensure the limits are within NIST requirements. Control charts can get monitored to see if the process is within the limit (NIST, 2019). One employee could be assigned to take random samples from the output to ensure they do not deviate from the NIST guidelines. Thus, knowing the weight of each candy, implementing an automatic counting system, and effecting a control chart could ensure consistency in package weights.

The proposed quality control will save money while getting a consistent weight for the packages. It will maintain quality standards by avoiding problems before they arise. Showing that the company is ready to solve package-related concerns before they occur could convince the government regulators to see its effectiveness. Additionally, the guidelines used in the automation process are per the National Institute of Standards and Technology (NIST). As explained in the control process, out-of-limit packages would be rejected before packaging by laser counting technology or through detection by random sampling. If a package gets to the final production phase and is detected to be out of the limit, it would have to be returned to the initial production process for recalibration by repackaging machines.

References

NIST. (2019). Checking the Net Contents of Packaged Goods. National Institute of Standards and Technology | NIST. https://www.nist.gov/system/files/documents/2019/12/17/2020-NIST-HB133-Final.pdf

Sharpe, N. R., Sharpe, N. D., Veaux, R. D., & Velleman, P. F. (2018). Business statistics (4th ed.).

Bus 625 Week 2 DQ 2: Causation Correlation and Lurking Variables Peer Feedback

Experiment:

Mandatory Gym Sessions and Average Blood Pressure Levels

Lurking variables are important explanatory variables that might well escape attention in a routine statistical analysis. In experimental studies, the focus is mainly on the independent and dependent variables. Yet, the effect of a lurking variable could influence the reliability of findings. A lurking variable is defined as a variable that has an important effect and yet is not included among the predictor variables under consideration (Asiamah et al., 2019). It may get omitted from the analysis because its presence is unknown or its existence is thought to be negligible. 

In Company Z, the management made it compulsory for the employees to provide proof of gym membership every month. The company continued to sensitize employees to improve their exercise routines for a healthy life, reduce absenteeism caused by fatigue and increase productivity. The management kept a record of each employee’s blood pressure level to assess health improvements.

Compared to the period before all employees were required to attend gym sessions by the company (week 0 on the graph), blood pressure levels recorded were gradually decreasing over time. After plotting the period (weekly) on the X-axis against the average blood pressure on the Y-axis, the increased attendance to the gym was contributing positively to improved blood pressure levels towards 120/80 mmHg (120 representing the cystolic pressure and 80 the diastolic pressure).

The independent variable in the experiment was exercise (continued mandatory attendance to gym sessions). The dependent variable was improved average blood pressure levels. Conclusion; mandatory gym participation contributed to better blood pressure levels.

References

Asiamah, N., Mends-Brew, E., & Boison, B. K. (2019). A spotlight on cross-sectional research: Addressing the issues of confounding and adjustment. International Journal of Healthcare Management, 14(1), 183-196. https://doi.org/10.1080/20479700.2019.1621022

BUS 625 Week 1 DQ 2 Data Visualization Reflection

Data visualization refers to the conversion of raw data into insights easily interpreted by a reader. The insight from the data is then conveyed using plots, charts, and smooths, making it effective for surfacing abnormalities or any data changes. It also removes a layer of noise. The five types of big data visualization categories.

Temporal: Data visualizations belong to this category if they satisfy two conditions: being linear and one-dimensional. This category features lines that either stand-alone or overlap with each other, having the start and finish time. Examples of temporal data visualization include scatter plots, polar area diagrams, and timelines.

Hierarchical: This category includes visualizations that order groups within larger groups. They are best suited when displaying information clusters, especially those flowing from a single origin point. The drawback of these visualizations is that they could be complex and challenging to read. Examples include tree diagrams, ring charts, and sunbursts diagrams.

Network: Network data visualizations show how they relate to each other within a network, demonstrating between datasets with simple explanations. Examples include matrix charts, word clouds, and alluvial diagrams.

Multidimensional: These visualizations have multiple dimensions meaning there are often two or more variables to create a 3D data visualization. These are the most eye-catching ones because of the many datasets. Examples include scatter plots, pie charts, and histograms.

Geospatial: This category relates to real-life physical locations overlying familiar maps with different data points. They are popular in displaying sales over time and are often employed in campaigns or displaying market penetration for major companies. Examples include density maps and heat maps.

Simpson’s paradox

It refers to an effect that occurs when the marginal association between two categorical variables is qualitatively different from the partial association between the same two variables after holding one as constant. Simpson’s paradox is crucial for three purposes. First, people expect statistical relationships to be immutable, but they are not. The association between two variables can change in any direction depending on the controlled variables. Second, Simpson’s paradox is not a mere phenomenon of interest to a few statisticians. Instead, it is one of a large class of association paradoxes. Finally, it reminds researchers that causal inferences can be damaging.

Examples

A university is concerned about the sex bias in the admission process to graduate school. The data could be inconsistent with sex bias, taking, for instance, men more likely to get admitted with 35 percent than women with 25 percent. To understand the cause of the bias, the university could divide the applicants into various categories. For instance, whether they applied for natural sciences courses or social sciences. It could be possible that this time, the bias gets reversed. For instance, women are more likely to get admitted with 80 percent than men with 46 percent in natural science departments. In social science, it could be possible that women with 20 percent were more likely to be admitted than men with 4 percent. In this case, the reversal in the association occurred because both sex and admissions were related to a third variable, the department. Women were more likely to apply for the social science departments. Because of the low expected acceptance rates in some programs, the applicants ignored some departments.

BUS 625 Week 1 DQ 1 Data Description Reflection

Company: Microsoft (Considering the years 2020 and 2019)

Gross Margin: This value indicates the profits available to set off operating, non-operating, and tax expenses in the income statement.

2020: $96,937 million

2019: $82,933 million

• Gross margin percentage change = 16.9%. This significant change can help raise the net profit of Microsoft and the EPS of stockholders. Management performance is also dependent on gross margin.

Research & Development (Operating Expense): Research and development expenditure indicates the efforts by a company to innovate or improve its products, and this variable is useful for customers knowing which new product is in line for launching.

2020: $19,269 million

2019: $16,876 million

• There was a 14% increase in that year. But, when taken as a percentage of revenue, it has 13% in both years. The R&D is useful for management to have a competitive advantage over other firms in the industry. It is also crucial for customers to know any new developments of new or existing products in the future.

Diluted EPS: This indicates the position of earnings for the stockholders for the convertible securities

2020: $5.76

2019: $5.06

• Diluted EPS represents the stockholder’s earnings per share if convertible securities get turned to equity. It is, therefore, important for stockholders. In 2020, Diluted EPS was 5.76, higher than in 2019 (5.06), indicating improvement.

• All the variables are based on time-series data.

Gross margin

• Defines the balance that arrived after reducing the expenses directly attributable to the product and services from the company’s revenue. It is categorical.

Research and development

• It defines the expenditure incurred by a firm in developing or innovating new or existing products and is crucial in the IT sector. It is categorical.

Diluted EPS

• It defines the stockholder’s earnings on a share if the convertible securities become equity. It is calculated by taking the weighted average number of equity shares as a denominator and earnings available for stockholders as of the numerator. It is a quantitative measure on a per-share basis.

The important factors in the dataset are profitability, liquidity, and leverage. Profitability determines the entity’s performance financially and is used by investors in making investment decisions. Liquidity determines whether an entity can settle its debts and also determines the working capital. Leverage determines the amount of debt the entity has taken to run the business, and a high leverage ratio could imply some risk to lenders and creditors.

If any data is missing from the financial statement, the management can address it by mentioning using notes below the statements. Sometimes it is possible to make a reasonable estimate hence the need to indicate any data as an “estimate” as required by accounting standards.