Fit index

Table 6 Goodness-of-fit indexes for the monthly calibrations and verifications...

A fit index (FI), defined as ratio between the CiTest fit and MFV, is used for the evaluation of each hypothesis and as a choice criterion for the identification of the best GBPM. 

If either a or fi is known for a given structure, eqs. (1)—(4) in Table 6.2.1 can be used to evaluate the remaining angle. Another possible use of these equations is in assessing the extent to which the cores of related compounds deviate from idealized Id symmetry. For this purpose we assume that there is no systematic variation in the observed M-Y bond distances and define a goodness-of-fit index S by the equation ... 

The fitting procedure is normally carried out consecutively, that is, shells are added to the fitting process as seems appropriate. Every shell should be checked for statistical significance, that is, if the addition of, normally, three parameters (o, R,N) is statistically viable. The check can be made by comparison of the change in the Fit index with F-test values, as outlined in ref. [12]. The oscillations are often very broad and with few features for oxides. In this case good statistical parameters are especially important. 

The level of agreement may be assessed by a fit index FI [e.g., Eq. (5)], summed over all n points. However, this should not be at the expense of deficiencies obvious from a visual inspection. The level of improvement achieved by addition of an extra shell needs to be carefully monitored and the statistical significance assessed (21). 

FIG. 3. Structural equation model of data re-analysed from Nettelbeck Rabbitt (1992 = 98). A latent speed of processing factor mediates the effect of age on Performance IQ subtests. Fit statistics are as follows average off-diagonal standardized residuals = 0.02 chi square = 15.7 (df= 13), P = 0.26 Bentler-Bonett normed fit index = 0.95 Bentler-Bonett non-normed fit index = 0.99 comparative fit index = 0.99 all parameters are significant. 

In a later study (MOD12), 14 subjects exposed to a Ct of 14.7 mg min m 3 of sarin (mean erythrocyte inhibition of 50%) carried one-third of their body weight up and down a 40.5-cm step 30 times a minute for 5 min (the Harvard pack test). This was done 45 min and 24 h after exposure. Their fitness index, which includes heart rate and other measures, did not differ from that of a group exposed to agent but not exercised. 

Fit index F defined as [(]t Xobs-Js 5Ccalc) /(Ndata-Nvar)] )/( k max-k min ) 100% where and Ny j. are the number of data points and number of variables, and Xmax Xmin maximum range for the filtered EXAFS data. 

AGFl Goodness of Fit Index Adjusted for degrees of Freedom >.90... 

TLI orNNFI Tucker-Lewis Index or Non-normed Fit Index >.90... 

Hu, L. and Bender, P.M. 1999. Cutoff criteria for fit indexes in covariance stracture analysis Conventional criteria versus new alternatives. Structural Equation Modeling A Multidisciplinary Journal, 6(1), 1-55. 

For validity evidence based on internal structure, confirmatory factor analysis was performed in Mplus 5.2 to estimate how well the designed two-factor correlated structure for the instrament fits the responses obtained with the sample (L. Muthen B. Muthen, 2007). Fit indices such as chi-square ( ), Comparative Fit Index (CFI), and the Standardized Root Mean Square Residual (SRMR) were examined to assess the fitness of the model to the data, and item loadings were also evaluated. The criteria of CFI value greater than 0.95 and SRMR value less than 0.08 were used to indicate a good model fit and CFI >0.90 as acceptable fit (Bentler, 1990 Hu Bentler, 1995). 

Bentler, P. M. (1990). Comparative fit indexes in structural models. Psychological Bulletin, 107 (2), 238-246. 

The next step in the analysis involved assessment of the model. Given that the multivariate kurtosis in the data was elevated, as indicated by the Mardia coefficient, the robust method was used in this analysis (Bentler, 2006). A specified model is generally indieated as a good fit with the data when the /df ratio is less than 3, the RCFI (Robust Comparative Fit Index) and NNFl (Bentler-Bonnet Non-Normed Fit Index) are above. 90, and when RMSEA (Root Mean-Square Error of Approximation) is below. 07 (Byrne, 2006). Two multi-sample analyses (Byrne, 2006) were carried out contrasting Canadian and Swedish students and, female and male students. 

The Fitting Index, F, for a particular process in the sequence of assembly is defined as ... 

---