Question 1083135: Thank you so much for your help!!!
Computing correlations is appropriate when we have
A. categorical data
B. ratio data
C. measurement data
D. two of the above are correct
Two variables, X and Y, have a significant linear correlation. Under what conditions can the direction of causality be determined just from knowing the correlation coefficient?
A. when the correlation is negative
B. when the correlation is positive
C. neither a) nor b) are correct
D. both A and B are correct
If you conducted a study where you could account for 64% of the variability for one variable with another variable, which of the following correlation coefficients did you find?
A. .80
B. .64
C. .4096
D. none of the above are correct
Answer by jim_thompson5910(35256)   (Show Source):
You can put this solution on YOUR website! Question 1:
Answer: choice B) ratio data
Note: I'm not 100% sure on this one so I'd get a second opinion.
Explanation: The formulas used to compute the correlation coefficient r involve subtraction, squaring and division, among other operations, implying that we'll be computing ratios. With ratio data we are allowed to do this. Compare this to interval data sets where we can subtract but division and multiplication wouldn't make any sense.
--------------------------------------------------------------------
Question 2:
Answer: choice D) both A and B are correct
Explanation: If we know the correlation coefficient is positive, then we know that the regression line slopes upward. Likewise, if the correlation coefficient is negative, then we know that the regression line slopes downward.
--------------------------------------------------------------------
Question 3:
Answer: choice A) 0.80
Explanation: Take the square root of 0.64 to get 0.80. This works because
(coefficient of determination) = (correlation coefficient)^2
(coefficient of determination) = (0.80)^2
(coefficient of determination) = 0.64
Recall that the coefficient of determination tells us how much variability of Y can be explained by X.
|
|
|
