Academia.eduAcademia.edu

Figure 2 – uploaded by Marsha Weinraub

See full PDFdownloadDownload figure
Fig. 2. Plot of interaction between negative life events and attachment security at 15 months for teachers’ report of children’s anxiety at first grade. UBCHMOOG, 10 1OCHULY Ue MIOGCIs, ONS UNStdnGarGiZeG laClor lode Per latent VdalldDIe Wads TACd dt UNLILY, Another advantage of using latent variable SEM is that it provides a goodness-of-fit test as well as regression weights. If a model is a good fit to the data, then the regression weights are interpretable. Both models provided an excellent fit to the data by mos standards. For children’s anxiety, x7 was statistically significant, y* (25, N=1364)= 65.85, p<.001, suggesting the existence of statistically significant discrepancies between the model and the data. Because a large sample size can generate statistical significance even when the absolute size of such discrepancies is relatively small (Raykov, 2000 , we examined alternative fit indices, including the Tucker—Lewis index (TLI) (Tucker & Lewis, 1973), the comparative fit index (CFI) (Bentler, 1990), and the incremental fit index (IFI). These indices ranged in size from .996 to .999. All exceeded Hu and Bentler’s (1990) recommended cutoffs, suggesting that the model explained almost all of t he observed covariances. Furthermore, the root mean square of the residuals (RMSEA)

Figure 2 Plot of interaction between negative life events and attachment security at 15 months for teachers’ report of children’s anxiety at first grade. UBCHMOOG, 10 1OCHULY Ue MIOGCIs, ONS UNStdnGarGiZeG laClor lode Per latent VdalldDIe Wads TACd dt UNLILY, Another advantage of using latent variable SEM is that it provides a goodness-of-fit test as well as regression weights. If a model is a good fit to the data, then the regression weights are interpretable. Both models provided an excellent fit to the data by mos standards. For children’s anxiety, x7 was statistically significant, y* (25, N=1364)= 65.85, p<.001, suggesting the existence of statistically significant discrepancies between the model and the data. Because a large sample size can generate statistical significance even when the absolute size of such discrepancies is relatively small (Raykov, 2000 , we examined alternative fit indices, including the Tucker—Lewis index (TLI) (Tucker & Lewis, 1973), the comparative fit index (CFI) (Bentler, 1990), and the incremental fit index (IFI). These indices ranged in size from .996 to .999. All exceeded Hu and Bentler’s (1990) recommended cutoffs, suggesting that the model explained almost all of t he observed covariances. Furthermore, the root mean square of the residuals (RMSEA)

Related Figures (5)

Hierarchical regression analyses predicting mother’s, father’s, and teacher’s reports of child’s anxiety at first grade
Hierarchical regression analyses predicting mother’s, father’s, and teacher’s reports of child’s anxiety at first grade
Hierarchical regression analyses predicting mother’s, father’s and teacher’s report of child’s aggression at first grade
Hierarchical regression analyses predicting mother’s, father’s and teacher’s report of child’s aggression at first grade
Fig. 1. Plot of interaction between negative life events and attachment security at 15 months for mother’s report of children’s anxiety at first grade.
Fig. 1. Plot of interaction between negative life events and attachment security at 15 months for mother’s report of children’s anxiety at first grade.
Fig. 3. Basic path diagram of model used to test relationship of control, main effect, and interaction variables to child’s anxiety as a latent variable with standardized parameter estimates.
Fig. 3. Basic path diagram of model used to test relationship of control, main effect, and interaction variables to child’s anxiety as a latent variable with standardized parameter estimates.
Fig. 4. Basic path diagram of model used to test relationship of control, main effect, and interaction variables to child’s aggression as a latent variable with standardized parameter estimates.
Fig. 4. Basic path diagram of model used to test relationship of control, main effect, and interaction variables to child’s aggression as a latent variable with standardized parameter estimates.
Related topics:
PsychologyCognitive ScienceDevelopmental PsychopathologyAttachment TheoryYouth developmentApplied Developmental PsychologyStressful Life EventsLIFE EVENT
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved