1. Using given data set (Assignment_1data in the folder)

a) Make scatterplot between "Years since first marriage" and "Total children ever born"

b) Make scatterplot between "Age at first birth" and "Total children ever born".

c) Describe the overall pattern of the relationship. Is the relationship reasonably strong or quite weak? Is it linear? Is there a positive or negative association, or neither? Do variables satisfy the assumption of normality and homoscedasticity?

2. Now use correlation analysis to assess the strength and the direction of the relationship between

a) "Years since first marriage" and "Total children ever born"

b) "Age at first birth" and "Total children ever born".

c) Do the sign and the magnitude of the correlation coefficient confirm the conclusions you reached in Question 1? Explain briefly.

3. Using Regression tool

a) Report the equation of the regression line to predict "Total children ever born" from "Age at first birth". What percent of the variation in "Total children ever born" is explained by "Age at first birth"? Predict total number of children born if age at first birth is 20 yrs.

b) Similarly, report the equation of the least-squares regression line to predict "Total children ever born" from "Years since first marriage". What percent of the variation in "Total children ever born" is explained by "Years since first marriage"? Predict total number of children born for 6 years since first marriage.

c) Explain which of the independent variables is a better predictor of the event and why?