# Healthcare assignment for statistics

Please use the data, StatCrunch, (or Excel), and your knowledge of statistics to answer the questions below. *Download the provided CDC data into StatCrunch or Excel (located under this assignment on the class site).

Part I

1a. Calculate the correlation coefficient (the r value) between each of the independent (and quantitative) variables, and the variable called diabetes.

Fill in this TABLE that gives the r value (correlation) between each variable in the dataset and diabetes:

r values TABLEObesity Rates

Physical Activity

Poverty Rate

Smoking

DIABETESr value here r value here r value here r value here

1b. What does this value tell us about the relationship between each of the independent variables and diabetes?

Hint: In other words, looks at each r value you have calculated. Each r-value will be either positive or negative (or 0). Each r-value will be strong, medium, or weak. Describe each of the r values in terms of the relationship that each represents.

FILL IN THIS TABLE TO ANSWER #2:

r values TABLEObesity RatesPhysical ActivityPoverty RateSmoking

DIABETESdescribe r value (positive or negative?) (strong, medium, weak)? What does it tell about the relationship? describe r value (positive or negative?) (strong, medium, weak)? What does it tell about the relationship?describe r value (positive or negative?) (strong, medium, weak)? What does it tell about the relationship?describe r value (positive or negative?) (strong, medium, weak)? What does it tell about the relationship?

2a. Run a regression using diabetes as the dependent variable (y), and smoking as the independent variable (x).

HINT: Therefore, the variable called Diabetes is going to be your dependent or y variable and the variable called smoking will be the independent or x variable. If you create a scatterplot (with the x variable on the horizontal axis and the y variable on the vertical access, you can see the relationship).

PASTE THE SCATTERPLOT WITH THE TRENDLINE and EQUATION HERE

Make sure you have the regression equation included.

3a. Is there a statistically significant relationship between poverty rates and diabetes? Explain.

HINTS: This question is not related to the question above it. In the question above it, you are asked to run regression for Diabetes and Smoking.

For this question, you are looking at Poverty and Diabetes. You are asked to determine if the relationship between Poverty and Diabetes is significant.

Here are two great YouTube Videos for Regression and the p values for the correlation in Excel. Even if you use StatCrunch, the concepts are the same ðŸ™‚

https://www.youtube.com/watch?v=QWhsH1vcIaw

https://www.youtube.com/embed/vFcxExzLfZI?feature=oembed

Write out the regression equation calculated using the data. You can use Excel to get this.

Interpret the slope coefficient the value in front of the x.

HINTS: You can do this in Excel (or StatCrunch). As a note, I always use Excel because it is more common, better for a resume, and publically available (StatCrunch is not publically available).

Linear Regression Equation in Excel

https://www.youtube.com/embed/TkiB1xBnjn4?feature=oembed

Another look at prediction/regression equations from Ami:

HOW TO VIDEO Dr Ami Gates MOOT Intro Stats Correlation Scatterplots Prediction Trendline (Regression Line & Prediction) Excel

https://www.youtube.com/embed/P6LwhM_pDuA?feature=oembed

HOW TO VIDEO Dr Ami Gates Using Excel Correlation scatterplots regression

https://www.youtube.com/embed/nKAd1U_1yl8?feature=oembed

3b. Suppose a state raises the tobacco tax and the rate of smoking in the state falls from 21% to 18%. What would the decrease be in the rate of diabetes based on the regression results?

ANSWER HERE

Part II

Suppose you work for a local hospital. Your manager requests that you use the CDC data on diabetes and smoking, obesity rate, physical activity, and poverty rate to present a compelling argument to the board regarding the importance of creating state initiatives to reduce diabetes rates.

You must present statistical data in a written report to the board.

Include a minimum of four types of statistical tests to make your case. Examples include hypothesis tests, confidence intervals, correlations, regressions, etc. You may use statistical tests that you have completed in weeks 3 and 8 or develop your own.

*** Please follow exactly the outline below **

TEST 1

1) What is the name of the first test you plan to use?

2) What variables will be involved in this test?

3) What is the goal of this test what do you expect to show?

4) Run the test and show and explain the results?

TEST 2

1) What is the name of the second test you plan to use?

2) What variables will be involved in this test?

3) What is the goal of this test what do you expect to show?

4) Run the test and show and explain the results?

TEST 3

1) What is the name of the third test you plan to use?

2) What variables will be involved in this test?

3) What is the goal of this test what do you expect to show?

4) Run the test and show and explain the results?

TEST 4

1) What is the name of the first test you plan to use?

2) What variables will be involved in this test?

3) What is the goal of this test what do you expect to show?

4) Run the test and show and explain the results?

GRAPH 1

1. What is the name of the graph type?

2. What variable(s) will be included as part of this graph?

3. What do you expect the graph to show?

4. Paste the graph HERE

GRAPH 2

1. What is the name of the graph type?

2. What variable(s) will be included as part of this graph?

3. What do you expect the graph to show?

4. Paste the graph HERE

GRAPH 3

1. What is the name of the graph type?

2. What variable(s) will be included as part of this graph?

3. What do you expect the graph to show?

4. Paste the graph HERE

ESSAY: Write an essay using these statistics and graphs to make a convincing argument for the need to create an initiative to reduce the rate of diabetes. In your essay, explain the relationship between diabetes and obesity, smoking, physical activity, and poverty rates utilizing statistical data, tests, and graphs. Be sure to explain your results and how these results show there is a need to create an initiative to reduce the diabetes rates.

WRITE ESSAY HERE (3 paragraphs 21 sentences minimum)