Question 1089225: The correlation between the salary of the nurse and the number of days missed at work in a sample of 100 nurses was found to be r = - 0.68, p = 0.001.
Interpret what this correlation indicates (r value) and the p value? What does this correlation mean in terms of salary and missed work days?
Answer by Theo(13342)   (Show Source):
You can put this solution on YOUR website! i wasn't sure what the answer should be so i did a little searching and came up with the following link that appears to be reasonable clear in its explanation. lots of other references can make you head spin trying to figure out what they're talking about.
http://www1.udel.edu/johnmack/frec834/regression_intro.htm
if r = .68, this means there is a negative correlation between nurses salaries and number of days worked.
you can assume that, as the nurse's salary goes up, the number of days missed at work goes down.
a very strong correlation would be an r of -1.
an r of 0 would mean no correlation.
r^2 is usually used to determine how close the data is to the regression line.
here's a reference on that.
http://blog.minitab.com/blog/adventures-in-statistics-2/regression-analysis-how-do-i-interpret-r-squared-and-assess-the-goodness-of-fit
if you take an r of -.68 and square it, you get an r^2 of .4624.
this means that roughly half of the data can be explained by the model.
if you looked at the graph of the data and the regression line created by it, you would probably see that the data points are not as closly fit around the regression line as if the r^2 was more like .8 or .9.
if r^2 was .9, then r would have been plus or minus square root of .9 = .948, which would have indicated a very strong correlation.
bottom line is that an 4 of -.68 indicated a negative correlation but not a very strong one.
the p-value gives you the probability that not fall within certain limits.
if your p-value is equal to .0001, then there is a very small probability that your data will not fall within the prescribed limits, which means there is a very large probability that it will.
i can't give you a better explanation than that because my knowledge is very hazy.
hopefully it's good enough to give you a general idea of what these statistics are used for.
the references i found should help you understand better.
|
|
|
