QUESTION 3

The fertility rate of a country is defined as the number of children a woman citizen bears, on average, in her lifetime. The fertility rate and contraceptive prevalence(measured as the percentage of married women who use contraception) for each 27 countries were recorded. The correlation coefficient between the two variables is calculated and is -0.38. Which of the following is (or are) correct based on this correlation coefficient? (There are two correct answers. No partical credit for this question.)

	A.	The contraceptive prevalence is the cause for the increase of decrease of fertility rate.
	B.	The correlation between the two quantitative variables is negative and is linear.
	C.	If one uses the linear regression to model the relation between two variables, the coefficient of determination for this simple linear regression model is -.38.
	D.	We need to see a scatter plot to know whether the relation is better described as linear or non-linear. Just a correlation coefficient is not enough for judging the relation is linear or non-linear.
	E.	If one uses the linear regression to model the relation between two variables, the coefficient of determination for this simple linear regression model is .1444.

QUESTION 6

Which of the following methods is the better way to examine the correlation between two quantitative variables.

	A.	Cluster bar chart
	B.	Histogram
	C.	Scatter plot
	D.	Side-by-side boxplot.

QUESTION 10

A researcher wants to predict bodoy mass index (BMI) using minutes exercised per week. Both of the variables are continuous variables. The researcher wants to predict BMI using thelength of time of exercise. Which of the following methods is your best choice for answering the above research question?

	A.	Two independent sample t-test.
	B.	Cox proportional hazards regression.
	C.	A simple linear regression.
	D.	Multiple or multivariate linear regression.
	E.	Logistic regression.