Browsing by Author "Hsu, Hsien-Yuan"

Now showing 1 - 4 of 4

Detecting Misspecified Multilevel Structural Equation Models with Common Fit Indices: AMonte Carlo Study
(2015-03-04)
Hsu, Hsien-Yuan
;
Kwok, Oi-man
;
Lin, Jr Huang
;
Acosta, Sandra
;
教育研究所
This study investigated the sensitivity of common fit indices (i.e., RMSEA, CFI, TLI, SRMR-W, and SRMR-B) for detecting misspecified multilevel SEMs. The design factors for the Monte Carlo study were numbers of groups in between-group models (100, 150, and 300), group size (10, 20, 30, and 60), intra-class correlation (low, medium, and high), and the types of model misspecification (Simple and Complex). The simulation results showed that CFI, TLI, and RMSEA could only identify the misspecification in the within-group model. Additionally, CFI, TLI, and RMSEA were more sensitive to misspecification in pattern coefficients while SRMR-W was more sensitive to misspecification in factor covariance. Moreover, TLI outperformed both CFI and RMSEA in terms of the hit rates of detecting the within-group misspecification in factor covariance. On the other hand, SRMR-B was the only fit index sensitive to misspecification in the between-group model and more sensitive to misspecification in factor covariance than misspecification in pattern coefficients. Finally, we found that the influence of ICC on the performance of targeted fit indices was trivial.
The Impact of Intraclass Correlation on the Effectiveness of Level-Specific Fit Indices in Multilevel Structural Equation Modeling: A Monte Carlo Study
(2017-01)
Hsu, Hsien-Yuan
;
Lin, Jr-Hung
;
Kwok, Oi-Man
;
Acosta, Sandra
;
Willson, Victor
Several researchers have recommended that level-specific fit indices should be applied to detect the lack of model fit at any level in multilevel structural equation models. Although we concur with their view, we note that these studies did not sufficiently consider the impact of intraclass correlation (ICC) on the performance of level-specific fit indices. Our study proposed to fill this gap in the methodological literature. A Monte Carlo study was conducted to investigate the performance of (a) level-specific fit indices derived by a partially saturated model method (e. g., CFIPS B and CFIPS W) and (b) SRMRW and SRMRB in terms of their performance in multilevel structural equation models across varying ICCs. The design factors included intraclass correlation (ICC: ICC1 = 0.091 to ICC6 = 0.500), numbers of groups in between-level models (NG: 50, 100, 200, and 1,000), group size (GS: 30, 50, and 100), and type of misspecification (no misspecification, between-level misspecification, and within-level misspecification). Our simulation findings raise a concern regarding the performance of between-level-specific partial saturated fit indices in low ICC conditions: the performances of both TLIPS B and RMSEAPS B were more influenced by ICC compared with CFIPS B and SRMRB. However, when traditional cutoff values (RMSEA <= 0.06; CFI, TLI <= 0.95; SRMR <= 0.08) were applied, CFIPS B and TLIPS B were still able to detect misspecified between-level models even when ICC was as low as 0.091 (ICC1). On the other hand, both RMSEAPS B and SRMRB were not recommended under low ICC conditions.
The Impact of Intraclass Correlation on the Effectiveness of Level-Specific Fit Indices in Multilevel Structural Equation Modeling: A Monte Carlo Study
(2017-01)
Hsu, Hsien-Yuan
;
Lin, Jr-Hung
;
Kwok, Oi-Man
;
Acosta, Sandra
;
Willson, Victor
Several researchers have recommended that level-specific fit indices should be applied to detect the lack of model fit at any level in multilevel structural equation models. Although we concur with their view, we note that these studies did not sufficiently consider the impact of intraclass correlation (ICC) on the performance of level-specific fit indices. Our study proposed to fill this gap in the methodological literature. A Monte Carlo study was conducted to investigate the performance of (a) level-specific fit indices derived by a partially saturated model method (e. g., CFIPS B and CFIPS W) and (b) SRMRW and SRMRB in terms of their performance in multilevel structural equation models across varying ICCs. The design factors included intraclass correlation (ICC: ICC1 = 0.091 to ICC6 = 0.500), numbers of groups in between-level models (NG: 50, 100, 200, and 1,000), group size (GS: 30, 50, and 100), and type of misspecification (no misspecification, between-level misspecification, and within-level misspecification). Our simulation findings raise a concern regarding the performance of between-level-specific partial saturated fit indices in low ICC conditions: the performances of both TLIPS B and RMSEAPS B were more influenced by ICC compared with CFIPS B and SRMRB. However, when traditional cutoff values (RMSEA <= 0.06; CFI, TLI <= 0.95; SRMR <= 0.08) were applied, CFIPS B and TLIPS B were still able to detect misspecified between-level models even when ICC was as low as 0.091 (ICC1). On the other hand, both RMSEAPS B and SRMRB were not recommended under low ICC conditions.
The Role of Group Interaction in Collective Efficacy and CSCL Performance
(2014-10-01)
Wang, Shu-Ling
;
Hsu, Hsien-Yuan
;
Lin, Sunny S. J.
;
Hwang, Gwo-Jen
;
教育研究所
Although research has identified the importance of interaction behaviors in computer-supported collaborative learning (CSCL), very few attempts have been made to carry out in-depth analysis of interaction behaviors. This study thus applies both qualitative (e. g., content analyses, interviews) and quantitative methods in an attempt to investigate the role of interaction behaviors (i. e., cooperative processes, cognitive involvement) in group motivation (i. e., collective efficacy) and group performance in CSCL. A total of 35 college students generated 387 cooperative processes and 421 cognitive ideas during the collaborative process over six weeks. The results indicated that the quality of interaction behaviors was positively related to CSCL performance. High performance groups were more involved in complex cooperative processes, and expressed more cognitive ideas at both high and low cognitive levels than low performance groups. For the role of interaction in collective efficacy, the quantity rather than quality of interaction behaviors played a more critical role in constructing collective efficacy. High efficacy groups had more cooperative processes and cognitive ideas than low collective efficacy groups. The interviews also revealed that group interaction played a mediating role in constructing collective efficacy. For the role of collective efficacy in group performance, the results also show that the high efficacy groups performed better than the low efficacy groups. Implications and suggestions for future research are also provided.