Microsoft Office Tutorials and References

In Depth Information

Fig. 6.12
Example of Using Excel’s

¼

correl Function to Compute the Correlation Coefﬁcient

2. The errors of measurement are independent of each other (e.g. the errors from a

speciﬁc time period are sometimes correlated with the errors in a previous time

period).

3. The errors ﬁt a normal distribution of Y-values at each of the X-values.

4. The variance of the errors is the same for all X-values (i.e., the variability of the

Y-values is the same for both low and high values of X).

A detailed explanation of these assumptions is beyond the scope of this topic, but

the interested reader can ﬁnd a detailed discussion of these assumptions in Levine

et al.
2011
, pp. 529-530).
(

Now, let’s create a chart summarizing these data.

Important note:
Whenever you are preparing a chart, we strongly recommend that

you put the predictor variable (X) on the left, and the criterion variable (Y) on the

right in your Excel spreadsheet, so that you do not get these variables backwards in

your Excel steps and make a mess of the problem in your computations. If you do

this as a habit, you will save yourself a lot of grief.

Search JabSto ::

Custom Search