People are living much longer worldwide than they were two decades ago, as death rates from infectious diseases and cardiovascular diseases have fallen. The average age of death increased from 46.7 in 1990 to 59.3 in 2013, as a result of declining fertility and a demographic shift in the world's population to older ages.

This study examines the association between life expectancy, socioeconomic status, health related issues, and lifestyle choices in the United States. The data are at the state level for years 2000, 2005, 2008, and 2010. The factors affecting the life expectancy considered in this study are education, income, diabetes, tobacco usage, obesity, alcohol consumption and exercise engagement.

Life expectancy at birth is calculated by Measures of America, using data from two principal sources. Mortality data were obtained by arrangement with the National Center for Health Statistics (NCHS) at the Centers for Disease Control and Prevention (CDC), and the National Association for Public Health Statistics and Information Systems Vital Statistics Cooperative Program. Bridged?race population estimates were obtained from the CDC WONDER Database. Life expectancy is calculated based on a widely used method developed by C. L. Chiang. This method involves the construction of abridged life tables that use population and mortality counts by age group as inputs.

The Education Index is based on two sub?indices: an Educational Attainment Index and an Enrollment Index. The Educational Attainment Index measures the overall level of educational attainment achieved by the adult population. It takes into account the percentage of the population age 25 years and older who have earned at least a high school diploma or equivalent, at least a bachelor's degree, or an advanced degree (master's, professional, doctoral, etc.). The Enrollment Index is based on a net enrollment calculation that takes into account the total number of students enrolled in school (of any age at any level) divided by the total school?aged population of 3 to 24?year?olds (inclusive). The index is calculated by Measures of America. All the required data is collected from the U.S. Census Bureau, ACS.

The Income Index is based on the median personal earning and is calculated by Measures of America. The required data is collected from U.S. Census Bureau, ACS.

Other factors included in this study are: diabetes, smoking (being a permanent smoker), obesity, binge drinking (drinking 5 or more drinks on an occasion for men or 4 or more drinks on an occasion for women), exercise (measured by the percentage of individuals who have participated in a physical activity during the past 30 days), and whether or not an individual has healthcare coverage. Data are collected from the Behavioral Risk Factor Surveillance System (BRFSS), which is a CDC related surveillance system.

1. Summarize the data related to life expectancy (consider only life expectancy and not the other variables) in a way that will help the audience see a basic picture of life expectancy in the US. Use standard statistical devices, including graphs. Make this a concise readable summary of the data that will help your audience understand it. (Descriptive Statistics)

2. To find the association between life expectancy and the independent variables, perform the following steps.

a. Consider all the data provided, use regression (in Minitab) and specify and estimate an equation that adequately predicts life expectancy in the US.

Present the relevant statistical results in a neat, understandable way that will enable your audience to learn about life expectancy in the US from your model.

Interpret the regression coefficients and the R². (This is very important for grading)

Specify the significant variables in predicting the life expectancy.

b. Introduce a proper cross-product term that can identify the interaction between obesity rate and alcohol consumption. Using regression methods (in Minitab) specify and estimate an equation that adequately describes life expectancy in the US.

Present the relevant statistical results in a neat, understandable way that will enable your audience to learn about life expectancy from your model.

Interpret the regression coefficients and the R². (This is very important for grading)

Specify the significant variables in predicting the life expectancy.

c. Compare the model you built in part (b) with the model you built in part (a). What is the effect of the cross-product term?

d. Using the model built in part (b), determine the factors that are considered statistically significant in predicting the life expectancy in the US. Determine which factor is a more significant predictor of life expectancy.

e. What are the main results of this study?

f. What can you do to improve this model (adding/removing any independent variable or interaction term, different analysis methods...)?

Regression Analysis: Li... ~ x #WORKSHEET 1 Regression Analysis: Life Expectancy at Birth Years versus Educ Coefficients Term Coef SE Coef T-Value P-Value VIF Constant 75.00 2.76 27.19 0.000 Education Index 0.049 0.227 0.22 0.828 4. 18 Income Index -0. 118 0. 1 18 -1.00 0.317 2.52 Diabetes (% age 18 and older) -0.2929 0.0904 -3.24 0.001 4.00 Smoking (Yes) -0.2689 0.0287 -9.38 0.000 2.45 Obesity (Obese BMI 30%+) 0.0475 0.0324 1.47 0.144 3.85 Binge Drinking (Yes) 0.1126 0.0263 4.28 0.000 1.56 Exercise (Yes) 0.0598 0.0241 2.48 0.014 2.27 Health Care Coverage (Yes) 0.0401 0.0220 1.83 0.070 1.95 Model Summary S R-sq R-sq(adj) R-sq(pred) 0.971858 70.79% 69.59% 67.33% Analysis of Variance Source DF Adj SS Adj MS F-Value P-Value Regression 8 446.328 55.7911 59.07 0.000 Education Index 0.045 0.0449 0.05 0.828 Income Index 0.952 0.9520 1.01 0.317 Diabetes (% age 18 and older) 9.915 9.9150 10.50 0.001 Smoking (Yes) 83.179 83.1787 88.07 0.000 Obesity (Obese BMI 30%+) 2.029 2.0292 2.15 0.144 Binge Drinking (Yes) 17.314 17.3139 18.33 0.000 Exercise (Yes) 5.812 5.8125 6.15 0.014 Health Care Coverage (Yes) 1 3.146 3.1463 3.33 0.070 Error 195 184.179 0.9445 C1 C2-T C3 C4 C5 Year State Life Expectancy at Birth Years Education.. Income I... Dia + Worksheet 1