Statistics Question

I need full help completing Problem Set #5 for PPD 303: Statistics for Policy, Planning, and Development. Please look over the PDF instructions very carefully and follow all of my professors exact instructions. I am also attaching the Excel data file, and you should use the Excel data to solve the questions when needed, especially for the descriptive statistics and regression parts. Please make sure every part is completed correctly and clearly.

---

Submission / Formatting Requirements (Professors Instructions)

• Final submission must be a single file: .pdf, .doc, or .docx
• If any work is handwritten, it must be neat, legible, and organized
• For questions requiring Excel:
  • Provide the formulas used
  • Copy/paste results from Excel into the document
• Do not submit the Excel file itself
• For regression output, copy/paste the relevant regression results into the document
• If Excel table formatting gets messed up when pasting into Word, paste it as an image instead

---

General Instructions

• Solve every question and subpart completely
• Show all calculations, formulas, and work clearly
• Include Excel formulas/functions used whenever requested
• Use proper statistical notation
• Explain the steps clearly so I can understand how the answer was found
• Organize the answers by question number and letter
• Make the final work clean and easy to copy into a document for submission

---

Question 1 Population Proportions [9 points total]

Use the referendum survey data and answer all parts ah.

Please include:

• The point estimate for the proportion supporting the referendum
• The standard error used for a confidence interval
• A 99% confidence interval using Excel
• The Excel formula used for the critical z-value in the margin of error
• A 95% confidence interval using Table C
• A brief explanation of how Table C was used
• The null and alternative hypotheses for testing whether support is greater than three-fifths (60%)
• The standard error for the hypothesis test
• The test statistic and p-value
• The final conclusion

My professor also notes that using Table C is less accurate because of rounding, and that Excel or statistical software is preferred in real life, but Table C may be needed for exams.

---

Question 2 Difference in Population Proportions [9 points total]

Use the female vs. male support data and answer all parts ah.

Please include:

• The point estimates for female and male support proportions
• The standard error used for the confidence interval
• A 90% confidence interval using Excel
• The Excel formula used
• A 99.9% confidence interval using Table C
• A brief explanation of how Table C was used
• The null and alternative hypotheses for testing whether support differs between women and men
• The standard error for the hypothesis test
• The test statistic and p-value
• The final conclusion on whether there is a statistically significant difference

Again, my professor notes that Table C is less accurate because of rounding, so please be precise.

---

Question 3 Simple Regression [14 points total]

Use the attached PS5 Data.xlsx file.

The dataset contains data on 119 commuting zones in the U.S. with population at least 500,000. The relevant variables are in columns D through H:

• Life expectancy at birth
• Median household income
• Share without health insurance
• Share who currently smoke
• Share who regularly exercise

We are using these data to run simple regressions predicting life expectancy using the other four variables.

Part A

Use Data Analysis Descriptive Statistics in Excel to calculate the following for the five variables in columns DH:

• Mean
• Median
• Standard deviation
• Standard error

Part B

Use Data Analysis Regression in Excel to run four simple regressions with life expectancy as the dependent variable and each of these as separate explanatory variables:

1. Median household income
2. Uninsured rate
3. Share who smoke
4. Share who exercise

Please paste the regression results.

Important professor instruction:

• Do not include the ANOVA panel

Part C

Interpret the slope coefficient from each regression in plain English.

Important professor instruction:

• Each interpretation must refer to the actual variables in this assignment
• Do not use generic wording like Y, X, dependent variable, or explanatory variable

Part D

State the null and alternative hypotheses for the slope coefficient in a simple regression, and explain in plain Englishwhat those hypotheses mean.

Part E

Identify which explanatory variables, if any, have a statistically significant linear relationship with life expectancy.

Important professor instruction:

• Any claim of statistical significance must state the significance level clearly, such as:
  • 10%
  • 5%
  • 1%
  • 0.1%

---

Attached Files

I am attaching:

• The PDF with the full assignment instructions please read this very carefully before answering
• The Excel data file please use this data to solve the questions where needed

WRITE MY PAPER