The file LIFEEXPECTANCY contains data for Life Expectancy across 145 countries (

Question

The file LIFEEXPECTANCY contains data for Life Expectancy across 145 countries (average for the years 1960-2015) and It is shared at

Data File Link :https://drive.google.com/file/d/0BwrnNVBanbKXRWU5RWxNYTFNbGs/view?usp=sharing

The variables used in this file are described below:

Lifeexp - Life expectancy at birth, total (years)

Literacy - Adult literacy rate, population 15+ years, both sexes (%)

GDPpc - GDP per capita (constant 2010 US$)

Hosbed - Hospital beds (per 1000 people)

Sanit - Improved sanitation facilities (% of population with access)

Water - Improved water source (% of population with access)

Physician - Physicians (per 1000 people)

Question : Use these data to examine the determinants of the Life Expectancy at birth. In doing so, first present your preferred specification results, explaining why you prefer this specification over the other specifications you may have considered, and then proceed to explore the hypothesis in question using your preferred specification.

If you want to use anyother software , you can , please post the answer as soon as possible. Can you please provide me below details:

Please use other functional forms ( Semi- Log and Double- Log)

1. Which variables should I omit ?

2. Which model should I use to do the analysis?

Share stata ( commands and results) with the answer. Do not directly copy and paste the commands and results here. if possible.

Explanation / Answer

we are using minitab software, the output using multiple regression is

Regression Analysis: lifeexp versus healthexp, hosbed, ...

The regression equation is
lifeexp = 30.8 + 0.046 healthexp - 0.229 hosbed + 0.0893 sanit + 0.167 water
+ 1.59 physician + 0.124 literacy + 0.000035 gdppc

Predictor Coef SE Coef T P
Constant 30.792 1.950 15.79 0.000
healthexp 0.0460 0.1547 0.30 0.767
hosbed -0.2286 0.1741 -1.31 0.191
sanit 0.08930 0.02186 4.09 0.000
water 0.16732 0.02968 5.64 0.000
physician 1.5906 0.4665 3.41 0.001
literacy 0.12404 0.02602 4.77 0.000
gdppc 0.00003521 0.00003849 0.91 0.362

S = 3.61833 R-Sq = 86.3% R-Sq(adj) = 85.7%

1) by this result

healthexp hosbed gdppc has p-value>0.05 so we can drop this variables from the regression.

2) here we will use multiple regression after omiting healthexp hosbed gdppc these variables, and we got the output as

Regression Analysis: lifeexp versus sanit, water, physician, literacy

The regression equation is
lifeexp = 31.1 + 0.0993 sanit + 0.171 water + 1.27 physician + 0.110 literacy

Predictor Coef SE Coef T P
Constant 31.058 1.879 16.53 0.000
sanit 0.09927 0.02081 4.77 0.000
water 0.17072 0.02918 5.85 0.000
physician 1.2715 0.3361 3.78 0.000
literacy 0.10991 0.02455 4.48 0.000

S = 3.62117 R-Sq = 86.0% R-Sq(adj) = 85.6%

here all variables are significantly effective as all having p-value<0.05.

Related Questions

Navigate

• Browse (All)
• Browse T
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.