goodness-of-fit


Also found in: Dictionary, Encyclopedia.

goodness-of-fit

an assessment of the similarity between the observed results from an experiment and those expected from theory and supported by a stated NULL HYPOTHESIS. An example of such a statistic is the CHI-SQUARED TEST.
Mentioned in ?
References in periodicals archive ?
Goodness-of-fit value (p) of >0.05 is considered as good suitability of test.
The Goodness-Of-Fit Indexes were found to be around 0-1, which falls within an acceptable range.
Kolmogorov-Smimov goodness-of-fit tests was conducted to determine the degree of significance between the frequencies of the observed set of data with excepted data, and established that Lotka's inverse square law didn't fit to confirm.
The observed frequency of depression in a sample of infertile women was compared to the expected frequency of the population by chi-square goodness-of-fit test at alpha 0.05.
Evaluating the fit of structural equation models: tests of significance and descriptive goodness-of-fit measures.
CFA was performed, and goodness-of-fit statistics were analyzed for assessing whether the factor model obtained by EFA was fit for our sample (Table 3).
It is worthy to underline that the Pearson correlation (r) was used throughout this work as an index of the agreement (goodness-of-fit) between simulations and empirical data.
Here, we explore if any parameters can be fixed or removed entirely from the model without compromising the goodness of fit to the data by considering the following: (1) the 95% credible intervals for each fit parameter and (2) the extent to which a single parameter can deviate from its best-fit value and still give a goodness-of-fit metric (a value of [zeta]) within 10% of the optimal value (Table 1).
The ESEM model makes it possible to solve some of the problems associated with CFA, such as cases in which no satisfactory goodness-of-fit indexes are found or in which model modification (e.g., correlating error terms) is required (Marsh et al., 2014).
Calibration was evaluated by Hosmer-Lemeshow goodness-of-fit test through calculating the ratio of observed-to-expected numbers of deaths which is known as the standardized mortality ratio (SMR).
Based on the analyses of the whole sample and the self-construal subsamples, the statistical test indicators were in line with established requirements (see Table 2), with the numerical value of [chi square]/df between 1 and 3; values of normed fit index, comparative fit index, incremental fit index, goodness-of-fit index, and adjusted goodness-of-fit index all greater than .90; root mean square error of approximation at .058, which was less than .08; and numerical values of parsimony goodness-of-fit index and parsimony normed fit index greater than .50 (McDonald & Ho, 2002).