MplusWizard: 2. Calculating model fit indices by hand in a structural equation model скачать в хорошем качестве

MplusWizard: 2. Calculating model fit indices by hand in a structural equation model

This video is part of the mpluswizard.com course series. If you like this, please like and subscribe. ;) Course files can be downloaded from: https://www.dropbox.com/sh/qf9iz8ogqs... !!! Next video!!!:    • MplusWizard: 3. The mplus data file   **Course notes:** ** Watch this video after you have completed the entire section on Path Analysis.** Ever wondered how to calculate the CFI, TLI and RMSEA by hand? I’m guessing perhaps “not really”, but maybe “yes”? Well, here’s a video about it anyway. Because it’s so cool to know how to do it! Model fit indices: CFI: The CFI is a comparative fit index. In other words, it compares the hypothesized model with a more restricted baseline model. Its values range between 0 and 1 (i.e., it is normed). TLI: Like the CFI, the TLI is a comparative fit index. However, unlike the CFI, the TLI is not normed and can take values above 1. It also includes a penalty function for overly complex models. If you have a model with good CFI and bad TLI, check for the presence of non-significant paths that can be removed from the model. RMSEA: The RMSEA is an absolute fit index and simply verifies that the model fits the data reasonably well. It comes with a 90% confidence interval and includes a penalty function for overly complex models. SRMR: The SRMR represents the average value across all standardized rexiduals. Like the RMSEA, it is an index of absolute fit and small values (below or equal to .06) represent good fit.