Question: 39. Constructing Confidence Intervals for r When obtaining samples of n paired values from a population with a correlation coefficient of r, the distribution of
39. Constructing Confidence Intervals for r When obtaining samples of n paired values from a population with a correlation coefficient of r, the distribution of linear correlation coefficients r is not a normal distribution, but values of have a distribution that is approximately normal with mean and standard deviation . This conversion of r values to z values is referred to as a Fisher transformation. This Fisher transformation can be used to construct a confidence interval estimate of the population parameter r. Use the following procedure to construct a 95% confidence interval for r, given 50 pairs of data for which r 0.600.
Step
a. Use Table A-2 to find that corresponds to the desired degree of confidence.
Step
b. Evaluate the interval limits wL and wR:
Step
c. Now evaluate the confidence interval limits in the expression below.
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
