Various tests were used for household-level variables: a McNemar test
for paired binary variables; a Friedman test for clustered categorical variables with > 2 levels; and a Wilcoxon signed-rank test for paired continuous variables (Tables 1, 2).
The McNemar test
is a "maximally pooled" test of symmetry where all squared differences of the values of the contingency table on each size of the diagonal are added and that result is divided by the sum of the values on each size of the diagonal; the Evans and Hoenig method is a diagonally projected test of symmetry, in which the values are summed along a series of diagonal cells that project outward from the central diagonal (Hoening et al.
If there was a statistically significant result, then a pairwise comparison was made using a McNemar test
A McNemar test
revealed that this difference was significant [[chi square](1)=6.
Following case matching, we evaluated the unadjusted differences between treatment groups using the McNemar test
The paired t-test was used for comparisons of paired parametric data and the McNemar test
for paired categorical data.
According to the results of McNemar test
, no significant difference was found in the control group before and after the intervention (57.
The McNemar test
and Cohen's kappa was used to assess the significance of differences in classification between the population-based and customised growth charts.
Proportions of LE tenderness between groups were compared with McNemar test
For questions with binary responses (yes/no) the McNemar test
, for all other questions the Wilcoxon signed-rank test was used.
Comparison of the levels of expressed emotion obtained by CFI and EES was performed with McNemar test
To assess changes in injury rates pre- and post-implementation of the physical training programs, the McNemar test
was used to compare injury incidence among Soldiers in the 6 months before the new programs were initiated (November 2009 to April 2010) with injury incidence in the 6 months following full implementation of the program (May 2010 to October 2010) for the overall, overuse, and traumatic injury categories.