This new CFI are 0.953, above the necessary 0.95 standard for an excellent complement. The brand new TLI are 0.945, below the needed 0.95 practical to have good fit. Although not, CFI and you will TLI are often sensed acceptable whenever higher than 0.90, while the TLI property value 0.945 is actually thought adequate. Thus, the hypothesized a couple of-foundation Peplau design put a reasonable to good fit into the investigation.
IOM model
In contrast to the acceptable fit of the Peplau model, the nine-factor IOM model performed extremely well. As with the Peplau model, all items loaded onto their anticipated latent factors, and no outliers were identified (Cook’s Ds < 1.00; range = 0.0-0.16). In contrast to the mediocre to good score ranges found in the Peplau model, overall indicators of the nine-factor model fit were excellent. The RMSEA was 0.027, 90% CI (0.024, 0.028), well below the cutoff of 0.05 for a good model fit. The calculated probability that the true RMSEA value was <0.05 was 1.00, confirming the strong fit of the model. The CFI was 0.995, which was above the recommended 0.95 standard for excellent. The TLI was 0.993, also above the recommended 0.95 standard for excellent.
Specialized model comparison
The BIC, which accounts for the number of items in a model, can be used to compare the relative fit of two models to the exact same data-as was the case in the current study. The BIC for the Peplau model, 276,596, was slightly larger than the BIC for the IOM-based model, 270,482, suggesting that the IOM-based model fit these data better than the Peplau-based model. The two models were also compared using log likelihood, which further supported the better fit of the IOM-based model (? 2 = , df = 20, p < .0001).
Ancillary Analyses
During the white of those conclusions and you will influence Peplau’s amazing three-stage design planned, modification indices (MIs) had been examined to determine improvements to the a couple of-factor Peplau-built design that would boost their match. In particular, correlations ranging from items’ recurring variances were sensed when technically related. A correlation within recurring variances (MI = ) try discover between the solutions to HCAHPS Goods 1 (“During this hospital stay, how frequently did nurses dump you which have through and admiration?”) and you will Items dos (“With this healthcare stand, how often performed nurses tune in cautiously for you?”). Which relationship was consistent with the positioning phase inside Peplau’s () totally new around three-stage idea. It actually was ergo believed that the new to begin with hypothesized two-basis design was diminished which the fresh positioning phase are a beneficial stand-by yourself phase and can even not be subsumed by most other one or two levels.
The two-factor Peplau-based model was therefore modified to include a third latent factor (orientation), and a CFA was run on this new model (see Figure 3 ). The three-factor model resulted in an improved fit (RMSEA = 0.068 [CI 0.066, 0.069; probability of RMSEA ? .05 = 1.00], CFI/TLI 0.958/0.950, ? 2 = 5,, df = 101, p < .0001).
The three-factor model’s MIs were then inspected to identify adjustments to the three-factor model that would improve the fit. Inspection of the MIs revealed relevant relationships between six items’ residual variances: (a) items 13 and 14 (MI = 3,) (pain management), (b) items 16 and 17 (MI = ) (medication teaching), and (c) items 2 and 3 (MI = ) (nurses listening carefully and explaining). The inclusion of these relationships further improved the fit of the three-phase Peplau model (RMSEA = 0.039 [CI 0.038, 0.041; probability of RMSEA ? .05 ? 1.00], CFI/TLI = 0.986/0.983, ? 2 = 1,, df = 98, p < .0001). As noted previously, a RMSEA score of 0.01 is considered excellent, 0.05 good, and 0.08 mediocre. The RMSEA score of 0.039 for the three-factor model is within the excellent to good score range of 0.01 to 0.05.