Table 3. Factor analysis; component loadings for presenting symptoms of bowel injury.
|
Pattern matrix |
Structure matrix |
|
|||||
|---|---|---|---|---|---|---|---|
| |
Component |
Component |
|
||||
| Symptoms/signs | 1 | 2 | 3 | 1 | 2 | 3 | Communalities |
| Nausea | 0.889 | 0.893 | 0.799 | ||||
| Vomitting | 0.869 | 0.874 | 0.767 | ||||
| SABO | 0.817 | 0.825 | 0.701 | ||||
| ABO | 0.547 | 0.548 | 0.352 | ||||
| BO>4 d | 0.915 | 0.895 | 0.794 | ||||
| BO<4 d | −0.847 | 0.333 | −0.808 | 0.849 | |||
| Diarrhoea | 0.545 | 0.562 | 0.34 | ||||
| FI | 0.507 | 0.543 | 0.308 | 0.401 | |||
| Bloating | 0.365 | 0.695 | 0.354 | 0.689 | 0.608 | ||
| Flatulence | 0.589 | 0.591 | 0.373 | ||||
| Abdo pain | 0.517 | 0.546 | 0.508 | 0.537 | 0.555 | ||
| Urgency | 0.367 | 0.460 | −0.341 | 0.427 | 0.486 | 0.479 | |
| PRB | −0.303 | −0.339 | −0.338 | 0.205 | |||
| PR mucus | 0.339 | 0.336 | 0.124 | ||||
Abbreviations: ABO=acute bowel obstruction; FI=faecal incontinence; PRB=per-rectal bleeding; PR mucus=per-rectal mucus; SABO=subacute bowel obstruction.
Factor analysis tells us what variables group or go together. Oblimin rotation generates both a pattern matrix and a structure matrix. The structure matrix is simply the factor loading matrix as in orthogonal rotation, representing the variance in a measured variable explained by a factor on both a unique and common contributions basis. The pattern matrix, in contrast, contains coefficients which just represent unique contributions (very similar to a correlation coefficient). For oblimin rotation, the researcher looks at both the structure and pattern coefficients when attributing a label to a factor. By one rule of thumb, a factor loading level over 0.3 in absolute value is considered to indicate that this variable belongs to a factor; in any event, factor loadings must be interpreted in the light of theory, not by arbitrary cutoff levels. In our case, we have highlighted with bold the loadings which indicated which variables where assigned to each component. Finally, the sum of the squared factor loadings for all factors for a given variable (row) is the variance in that variable accounted for by all the factors, and this is called the communality. The communality measures the percent of variance in a given variable explained by all the factors jointly and may be interpreted as the reliability of the indicator.