Please enable JavaScript to view this site.

IBM® SPSS® Amos™ 28

Navigation: Appendices

Appendix B: Discrepancy Functions

Scroll Prev Top Next More

Amos minimizes discrepancy functions (Browne, 1982; Browne, 1984) of the form,

(D1) 7212.

Different discrepancy functions are obtained by changing the way f is defined. If means and intercepts are unconstrained and do not appear as explicit model parameters, 7213 and 7214 will be omitted and f will be written 7215.

The discrepancy functions 7216 and 7217 are obtained by taking f to be

7218.

Except for an additive constant that depends only on the sample size, 7219 is –2 times the Kullback-Leibler information quantity (Kullback & Leibler, 1951). Strictly speaking, 7216 and 7217 do not qualify as discrepancy functions according to Browne's definition since 7220.

For maximum likelihood estimation (Ml), 7222 are obtained by taking f  to be

(D2) 7221

For generalized least squares estimation (Gls), 7223 are obtained by taking f to be

(D3) 7224.

For asymptotically distribution-free estimation (Adf), 7225 are obtained by taking f to be

(D4) 7226,

where the elements of 7227 are given by Browne (1984) in Equations 3.1–3.4:

7228,

7229,

7230,

7231.

For 'scale free' least squares estimation (Sls), 7232 are obtained by taking f to be

(D5) 7233,

where 7234.

For unweighted least squares estimation (Uls), 7235 are obtained by taking f  to be

(D6) 7236.

The Emulisrel6 method can be used to replace (D1) with

(D1a) 7237.

F is then calculated as 7238.

When G = 1 and r = 1, (D1) and (D1a) are equivalent, giving

7239.

For maximum likelihood, asymptotically distribution-free, and generalized least squares estimation, both (D1) and (D1a) have a chi-square distribution for correctly specified models under appropriate distributional assumptions. Asymptotically, (D1) and (D1a) are equivalent. However, both formulas can exhibit some inconsistencies in finite samples. Suppose you have two independent samples and a model for each. Furthermore, suppose that you analyze the two samples simultaneously, but that, in doing so, you impose no constraints requiring any parameter in one model to equal any parameter in the other model. Then if you minimize (D1a), the parameter estimates obtained from the simultaneous analysis of both groups will be the same as from separate analyses of each group alone. Furthermore, the discrepancy function (D1a) obtained from the simultaneous analysis will be the sum of the discrepancy functions from the two separate analyses. Formula (D1) does not have this property when r is nonzero. Using formula (D1) to do a simultaneous analysis of the two groups will give the same parameter estimates as two separate analyses, but the discrepancy function from the simultaneous analysis will not be the sum of the individual discrepancy functions.

On the other hand, suppose you have a single sample to which you have fitted some model using Amos. Now suppose that you arbitrarily split the sample into two groups of unequal size and perform a simultaneous analysis of both groups, employing the original model for both groups, and constraining each parameter in the first group to be equal to the corresponding parameter in the second group. If you have minimized (D1) in both analyses, you will get the same results in both. However, if you use (D1a) in both analyses, the two analyses will produce different estimates and a different minimum value for F.

All of the inconsistencies just pointed out can be avoided by using (D1) with the choice r = 0, so that (D1) becomes

7240.

© 2021 Amos Development Corporation