Data-Driven Decision Making

Data-Driven Decision Making for Health Care Administration

 

Regression Models

 

How are regression models useful to healthcare administration practice? As a current or future healthcare administration leader, you may engage in conducting regression models for decision making.

 

Healthcare administration leaders may use regression models to explain the relationship between variables and to predict variations in these variables. When striving to continuously enhance healthcare delivery and minimize costs, healthcare administration leaders must be able to demonstrate how changes in certain variables impact their health services organization. Regression models are useful to help guide the healthcare administration leader in determining which variables most impact healthcare delivery.

 

1. This week, you explore regression models and apply regression models to healthcare administration practice problems. You also consider how you might integrate regression models for more advanced statistical analyses.

 

Learning Objectives

Students will:

 

· Analyze dependent and independent variables for regression analysis

· Analyze how to measure dependent and independent variables in a regression analysis

· Conduct regression models for healthcare administration practice

 

 

 

 

Learning Resources

Note: To access this week’s required library resources, please click on the link to the Course Readings List, found in the Course Materials section of your Syllabus.

 

Required Readings

Albright, S. C., & Winston, W. L. (2017). Business analytics: Data analysis and decision making (6th ed.). Stamford, CT: Cengage Learning.

 

Chapter 10, “Regression Analysis: Estimating Relationships”

Chapter 11, “Regression Analysis: Statistical Inference”

Fulton, L., Lasdon, L. S., & McDaniel, R. R. (2007). Cost drivers and resource allocation in military health care systems. Military Medicine, 172(3), 244–249.

 

Required Media

 

Lee, C., Famoye, F., & Shelden, B. (2008a). SPSS training workshop: Linear regression: Stats, diagnosis, plots [Video file]. Retrieved from http://calcnet.mth.cmich.edu/org/spss/V16_materials/Video_Clips_v16/21lin_regress1/21lin_regress1.swf

 

Lee, C., Famoye, F., & Shelden, B. (2008b). SPSS training workshop: Linear regression: Variable selections [Video file]. Retrieved from http://calcnet.mth.cmich.edu/org/spss/V16_materials/Video_Clips_v16/22lin_regress2/22lin_regress2.swf.

 

 

 

Discussion

 

 

Building Regression Models in Health Care

 

Finding evidence-based relationships among variables is an important tool for any healthcare administration leader. On a daily basis, healthcare administration leaders may want to see what variables are correlated so that they can implement quality improvement.

 

1. This week, you think of scenarios where building and interpreting regression models would be useful for healthcare administration leaders. You might consider building off of your Week 4 Discussion.

 

For example, Jenna, a healthcare administration leader, determined last week that patient satisfaction scores had fallen from the mean of 87. She wants to know why. She believes that it may have something to do with patient waiting time and time spent with the doctor. Thus, her dependent variable (y) is patient satisfaction and the independent variables are waiting time (x1) and time spent with the doctor (x2). She can evaluate the relationship between these two variables using correlation; bivariate scatterplots for y vs. x1 and y vs. x2; and regression techniques.

 

2. For this Discussion, think about a healthcare scenario where multiple regression might be useful in your organization or one with which you are familiar. Consider what your dependent and independent variables might be for conducting a multiple regression analysis. Build a small example, and run the regression analysis.

 

By Day 3

3. Post a description of the dependent and independent variables you will use for your multiple regression analysis, and then explain your regression model in terms of your dependent and independent variables. Explain how you might measure your variables. Be specific and provide examples.

 

By Day 5

Continue the Discussion and respond to your colleagues in one or more of the following ways:

 

· Ask a probing question, substantiated with additional background information, evidence, or research.

· Share an insight from having read your colleagues’ postings, synthesizing the information to provide new perspectives.

· Offer and support an alternative perspective, using readings from the classroom or from your own research in the Walden Library.

· Validate an idea with your own experience and additional research.

· Make a suggestion based on additional evidence drawn from readings or after synthesizing multiple postings.

· Expand on your colleagues’ postings by providing additional insights or contrasting perspectives based on readings and evidence.

 

Submission and Grading Information

Grading Criteria

To access your rubric:

 

Week 5 Discussion Rubric

 

Post by Day 3 and Respond by Day 5

To participate in this Discussion: Week 5 Discussion

 

 

 

 

Assignment (5 pages) APA format 7th ed.

 

 

Regression Modeling

 

Regression modeling is a foundational skill for those conducting secondary data analysis, much like you will encounter in the completion of the Doctor of Healthcare Administration (DHA) program. Additionally, regression modeling assists in finding connections among multiple variables and one dependent variable. Consider, for example, a healthcare administrator who may be asked to develop or interpret models of patient satisfaction based on other quantitative or dichotomous variables.

 

1. For this Assignment, review the resources for this week. Then, review your course text, and complete Case Study 11.2 on page 536 The case study is based on a real-world problem.

 

· For Chapter 11, case study 11.1, you will need to download the file C11_01.xlsx from the textbook companion website http://www.cengage.com/cgi-wadsworth/course_products_wp.pl?fid=M20b&product_isbn_issn=9781305947542. Under “Book Resources”, click on “Student Downloads” to view the downloadable files. Click “Case Files” and download the zipped file 1305947541_538884.zip. Open the zipped file to access the file C11_01.xlsx.

 

CASE 11.1: HEATING OIL AT DUPREE FUELS COMPANY 6

 

Dupree Fuels Company is facing a difficult problem. Dupree sells heating oil to residential customers. Given the amount of competition in the industry, both from other home heating oil suppliers and from electric and natural gas utilities, the price of the oil supplied and the level of service are critical in determining a company’s success. Unlike electric and natural gas customers. Oli customers are exposed to the risk of running out of fuel. Home heating oil suppliers therefore have to guarantee that the customer’s oil tank will not be allowed to run dry. In fact, Dupree’s service pledge is, “50 free gallons on us if we let you run dry” Beyond the cost of the oil, however, DUPREE is concerned about the perceived reliability of his service if a customer is allowed to run out of oil.

To estimate customer oil use, the home heating oil industry uses the concept of a degree-day, equal to the difference between the average daily temperature and 68 degrees Fahrenheit. So if the average temperature on a given day is 50, the degree-days for that day will be 18. (if the degree-day calculation results in a negative number, the degree-day number is recorded as 0.) By keeping track of the number of degree-days since the customer’s last oil, knowing the size of the customer’s oil tank, and estimating the customer’s oil consumption as a function of the number of degree-days, the oil supplier can estimate when the customer is getting low on fuel and then resupply the customer.

DUPREE has used this scheme in the past but is disappointed with the results and the computational burdens it places on the company. First, the system requires that a consumption-per-degree-day figure be estimated for each customer to reflect that customer’s consumption habits, size of home, quality of home insulation, and family size. Because DUPREE has more than 1,500 customers, the computational burden of keeping track of all these customers is enormous. Second, the system is crude and unreliable. The consumption per degree-day for each customer is computed by dividing the oil consumption during the preceding year by the degree-days during the preceding year. Customers have tended to use less fuel than estimated during the warmer months. This means that Dupree is making more deliveries than necessary during colder months and customers are running out of oil during the warmer months.

 

DUPREE wants to develop a consumption estimation model that is practical and more reliable. The following data are available in the file C11_01.xlsx:

· The number of degree-days since the last oil fill and the consumption amounts for 40 customers.

· The number of people residing in the homes of each of the 40 customers. DUPREE thinks that this might be important in predicting the oil consumption of customers using oil-fired water heaters because it provides an estimate of the hot water requirements of each customer. Each of the customers in this sample uses an oil-fired water heater.

· An assessment, provided by Dupree sales staff, of the home type of each of these 40 customers. The home type classification, which is a number between 1 and 5, is a composite index of the home size, age, exposure to wind, level of insulation, and furnace type. A low index implies a lower oil consumption per degree-day. Dupree thinks that the use of such an index will allow them to estimate a consumption model based on a sample data set and then to apply the same model to predict the oil demand of each of his customers.

Use of regression to see whether a statistically reliable oil consumption model can be estimated from the data.

 

The Assignment: (5 pages)

 

· Complete Case Study 11.2, “Heating Oil at Dupree Fuel Company” on page 536 of your course text using SPSS.

Note: This case study is real. The name of the company is changed for purposes of anonymity.

 

 

CASE STUDY: Developing A Flexible Budget at The GUNDERSON Plant.

The Gunderson plant manufactures the industrial product line of FGT Industries. Plant management wants to be able to get a good, yet quick estimate of the manufacturing overhead costs that can be expected each month. The easiest and simplest method to accomplish this task is to develop a flexible budget formula for the manufacturing overhead costs. The plant’s accounting staff has suggested that simple linear regression be used to determine the behavior pattern of the overhead costs. The regression data can provide the basis for the flexible budget formula. Sufficient evidence is available to conclude that manufacturing overhead costs vary with direct labor hours. The actual direct labor hours and the corresponding manufacturing overhead costs for each month of the last three years have been used in the linear regression analysis.

The three-year period contained various occurrences not uncommon to many businesses. During the first year, production was severely curtailed during two months due to wildcat strikes. In the second year, production was reduced in one month because of material shortages, and increased significantly (scheduled overtime) during two months to meet the units required for a one-time sales . At the end of the second year, employee benefits were raised significantly as the result of a labor agreement. Production during the third year was not affected by any special circumstances. Various members of Gunderson’s accounting staff raised some issues regarding the historical data collected for the regression analysis. These issues were as follows.

· Some members of the accounting staff believed that the use of data from all 36 months would provide a more accurate portrayal of the cost behavior. While they recognized that any of the monthly data could include efficiencies and inefficiencies, they believed these efficiencies and inefficiencies would tend to balance out over a longer period of time.

· Other members of the accounting staff suggested that only those months that were considered normal should be used so that the regression would not be distorted.

· Still other members felt that only the most recent 12 months should be used because they were the most current.

· Some members questioned whether historical data should be used at all to form the basis for a flexible budget formula.

 

The accounting department ran two regression analyses of the data-one using the data from all 36 months and the other using only the data from the last 12 months. The information derived from the two linear regressions is shown below (t-values shown in parentheses). The 36-month regression is

OHt=123,810 + 1.60 DLHt + R2=0.32

(1.64)

The 12-month regression is

OHt=109,020 + 3.00 DLHt + R2=0.48

(3.01)

 

Questions

1. Which of the two results (12 months versus 36 months) would you use as a basis for the flexible budget formular?

2. How would the four specific issues raised by the members of GUNDERSON’S accounting staff influence your willingness to use the results of the statistical analyses as the basis for the flexible budget formula? Explain your answer.

 

 

 

 

By Day 7

· Submit your answers and embedded analysis (SPSS and other analysis) as a Microsoft Word management report.

 

Submission and Grading Information

To submit your completed Assignment for review and grading, do the following:

 

· Please save your Assignment using the naming convention “WK5Assgn+last name+first initial. (extension)” as the name.

· Click the Week 5 Assignment Rubric to review the Grading Criteria for the Assignment.

· Click the Week 5 Assignment link. You will also be able to “View Rubric” for grading criteria from this area.

· Next, from the Attach File area, click on the Browse My Computer button. Find the document you saved as “WK5Assgn+last name+first initial. (extension)” and click Open.

· If applicable: From the Plagiarism Tools area, click the checkbox for I agree to submit my paper(s) to the Global Reference Database.

Click on the Submit button to complete your submission.

Grading Criteria

To access your rubric:

 

Week 5 Assignment Rubric

 

Check Your Assignment Draft for Authenticity

To check your Assignment draft for authenticity:

 

Submit your Week 5 Assignment draft and review the originality report.

 

Submit Your Assignment by Day 7

To submit your Assignment: Week 5 Assignment