Part IV: Managing and Analyzing Data
Two-factor with replication A two-way analysis of variance, with multiple samples (or
replications) for each group of data
Two-factor without replication A two-way analysis of variance, with a single sample (or
replication) for each group of data
Figure 33.2 shows the dialog box for a single-factor analysis of variance. Alpha represents
the statistical confidence level for the test.
FIGURE 33.2
Specifying parameters for a single-factor analysis of variance
The output for this test consists of the means and variances for each of the samples, the
value of F, the critical value of F, and the significance of F (P-value).
Correlation
Correlation is a widely used statistic that measures the degree to which two sets of values
vary together. For example, if higher values in one data set are typically associated with
higher values in the second data set, the two data sets have a positive correlation. The
degree of correlation is expressed as a coefficient that ranges from –1.0 (a perfect negative
correlation) to +1.0 (a perfect positive correlation). A correlation coefficient of 0 indicates
that the two variables aren’t correlated.
Figure 33.3 shows the Correlation dialog box. Specify the input range, which can include
any number of variables, arranged in rows or columns.
The output consists of a correlation matrix that shows the correlation coefficient for each
variable paired with every other variable.
