Victoria Savalei

Professor
phone 604 822 2296
location_on Kenny Room 3410--2136 West Mall

Research Area

Education

PhD, UCLA, 2007

Research

At present, I am continuing work on the new estimation method for incomplete data, called the two-stage (TS) method. I have recently shown that the TS method performs as well as or better than other approaches when data are incomplete (Savalei & Bentler, 2009) and incomplete as well as nonnormal (Savalei & Falk, 2014). I am now extending the TS method to the common situation when data are missing at the item level but the analysis is at the level of the sum scores (e.g., as would be the case when the model is a regression or a path analysis model with sum scores, or an SEM model with parcels), and the results are very promising. This work is funded by NSERC.

Additionally, extending my earlier work on the RMSEA (Savalei, 2012), I am currently investigating some properties of the CFI fit index, popular in SEM.

Finally, I have also developed a new research interest in the area of statistical cognition (how people reason about and use statistics), particularly as it pertains to the crisis of replicability in psychology. I am beginning a research project investigating how researchers use Bayes Factors.


Publications

Zhang, X., & Savalei, V. (2016). Bootstrapping confidence intervals for fit indices in structural equation modeling. Structural Equation Modeling, 23, 392-408.

Zhang, X., & Savalei, V. (2016). Improving the factor structure of psychological scales: The Expanded format as an alternative to the Likert scale format. Educational and Psychological Measurement, 76, 357-386.

Rhemtulla, M., Savalei, V., & Little, T. (2016). On the asymptotic relative efficiency of planned missingness designs. Psychometrika, 81,0-89. doi: 10.1007/s11336-014-9422-0

Chuang, J., Savalei, V., & Falk, C. (2015). Investigation of Type I error rate of three versions of robust chi-square difference tests. Structural Equation Modeling, 22, 517-530. 10.1080/10705511.2014.938713

Savalei, V., & Dunn, E. (2015). Is the call to abandon p-values the red herring of the replicability crisis? Frontiers in Psychology, 6, 2015. doi: 10.3389/fpsyg.2015.00245

Savalei, V., & Falk, C. (2014). Recovering substantive factor loadings in the presence of acquiescence bias: A comparison of three approaches. Multivariate Behavioral Research, 49, 407-424.

Brosseau-Liard, P. E., & Savalei, V. (2014). Adjusting relative fit indices for nonnormality. Multivariate Behavioral Research, 49, 460-470.

Savalei, V. (2014). Understanding robust corrections in structural equation modeling. Structural Equation Modeling, 21, 149-160.

Savalei, V., & Falk, C. (2014). Robust two-stage approach outperforms robust FIML with incomplete nonnormal data. Structural Equation Modeling, 21, 280-302.

Savalei, V., & Rhemtulla, M. (2013). The performance of robust test statistics with categorical data. British Journal of Mathematical and Statistical Psychology, 66, 201-223.

Brosseau-Liard, P., Savalei, V., and Li, L. (2012). An investigation of the sample performance of two non-normality corrections for RMSEA. Multivariate Behavioral Research, 47, 904-930.

Savalei, V. (2012). The relationship between RMSEA and model misspecification in CFA models. Educational and Psychological Measurement, 72, 910-932.

Rhemtulla, M., Brosseau-Liard, P., & Savalei, V. (2012). How many categories is enough to treat data as continuous? A comparison of robust continuous and categorical SEM estimation methods under a range of non-ideal situations. Psychological Methods, 17, 354-373. doi: 10.1037/a0029315

Savalei, V., & Rhemtulla, M. (2012). On obtaining estimates of the fraction of missing information from full information maximum likelihood. Structural Equation Modeling, 19, 477-494.

For a current list of publications, visit the lab website.


Victoria Savalei

Professor
phone 604 822 2296
location_on Kenny Room 3410--2136 West Mall

PhD, UCLA, 2007

At present, I am continuing work on the new estimation method for incomplete data, called the two-stage (TS) method. I have recently shown that the TS method performs as well as or better than other approaches when data are incomplete (Savalei & Bentler, 2009) and incomplete as well as nonnormal (Savalei & Falk, 2014). I am now extending the TS method to the common situation when data are missing at the item level but the analysis is at the level of the sum scores (e.g., as would be the case when the model is a regression or a path analysis model with sum scores, or an SEM model with parcels), and the results are very promising. This work is funded by NSERC.

Additionally, extending my earlier work on the RMSEA (Savalei, 2012), I am currently investigating some properties of the CFI fit index, popular in SEM.

Finally, I have also developed a new research interest in the area of statistical cognition (how people reason about and use statistics), particularly as it pertains to the crisis of replicability in psychology. I am beginning a research project investigating how researchers use Bayes Factors.

Zhang, X., & Savalei, V. (2016). Bootstrapping confidence intervals for fit indices in structural equation modeling. Structural Equation Modeling, 23, 392-408.

Zhang, X., & Savalei, V. (2016). Improving the factor structure of psychological scales: The Expanded format as an alternative to the Likert scale format. Educational and Psychological Measurement, 76, 357-386.

Rhemtulla, M., Savalei, V., & Little, T. (2016). On the asymptotic relative efficiency of planned missingness designs. Psychometrika, 81,0-89. doi: 10.1007/s11336-014-9422-0

Chuang, J., Savalei, V., & Falk, C. (2015). Investigation of Type I error rate of three versions of robust chi-square difference tests. Structural Equation Modeling, 22, 517-530. 10.1080/10705511.2014.938713

Savalei, V., & Dunn, E. (2015). Is the call to abandon p-values the red herring of the replicability crisis? Frontiers in Psychology, 6, 2015. doi: 10.3389/fpsyg.2015.00245

Savalei, V., & Falk, C. (2014). Recovering substantive factor loadings in the presence of acquiescence bias: A comparison of three approaches. Multivariate Behavioral Research, 49, 407-424.

Brosseau-Liard, P. E., & Savalei, V. (2014). Adjusting relative fit indices for nonnormality. Multivariate Behavioral Research, 49, 460-470.

Savalei, V. (2014). Understanding robust corrections in structural equation modeling. Structural Equation Modeling, 21, 149-160.

Savalei, V., & Falk, C. (2014). Robust two-stage approach outperforms robust FIML with incomplete nonnormal data. Structural Equation Modeling, 21, 280-302.

Savalei, V., & Rhemtulla, M. (2013). The performance of robust test statistics with categorical data. British Journal of Mathematical and Statistical Psychology, 66, 201-223.

Brosseau-Liard, P., Savalei, V., and Li, L. (2012). An investigation of the sample performance of two non-normality corrections for RMSEA. Multivariate Behavioral Research, 47, 904-930.

Savalei, V. (2012). The relationship between RMSEA and model misspecification in CFA models. Educational and Psychological Measurement, 72, 910-932.

Rhemtulla, M., Brosseau-Liard, P., & Savalei, V. (2012). How many categories is enough to treat data as continuous? A comparison of robust continuous and categorical SEM estimation methods under a range of non-ideal situations. Psychological Methods, 17, 354-373. doi: 10.1037/a0029315

Savalei, V., & Rhemtulla, M. (2012). On obtaining estimates of the fraction of missing information from full information maximum likelihood. Structural Equation Modeling, 19, 477-494.

For a current list of publications, visit the lab website.

Victoria Savalei

Professor
phone 604 822 2296
location_on Kenny Room 3410--2136 West Mall

PhD, UCLA, 2007

At present, I am continuing work on the new estimation method for incomplete data, called the two-stage (TS) method. I have recently shown that the TS method performs as well as or better than other approaches when data are incomplete (Savalei & Bentler, 2009) and incomplete as well as nonnormal (Savalei & Falk, 2014). I am now extending the TS method to the common situation when data are missing at the item level but the analysis is at the level of the sum scores (e.g., as would be the case when the model is a regression or a path analysis model with sum scores, or an SEM model with parcels), and the results are very promising. This work is funded by NSERC.

Additionally, extending my earlier work on the RMSEA (Savalei, 2012), I am currently investigating some properties of the CFI fit index, popular in SEM.

Finally, I have also developed a new research interest in the area of statistical cognition (how people reason about and use statistics), particularly as it pertains to the crisis of replicability in psychology. I am beginning a research project investigating how researchers use Bayes Factors.

Zhang, X., & Savalei, V. (2016). Bootstrapping confidence intervals for fit indices in structural equation modeling. Structural Equation Modeling, 23, 392-408.

Zhang, X., & Savalei, V. (2016). Improving the factor structure of psychological scales: The Expanded format as an alternative to the Likert scale format. Educational and Psychological Measurement, 76, 357-386.

Rhemtulla, M., Savalei, V., & Little, T. (2016). On the asymptotic relative efficiency of planned missingness designs. Psychometrika, 81,0-89. doi: 10.1007/s11336-014-9422-0

Chuang, J., Savalei, V., & Falk, C. (2015). Investigation of Type I error rate of three versions of robust chi-square difference tests. Structural Equation Modeling, 22, 517-530. 10.1080/10705511.2014.938713

Savalei, V., & Dunn, E. (2015). Is the call to abandon p-values the red herring of the replicability crisis? Frontiers in Psychology, 6, 2015. doi: 10.3389/fpsyg.2015.00245

Savalei, V., & Falk, C. (2014). Recovering substantive factor loadings in the presence of acquiescence bias: A comparison of three approaches. Multivariate Behavioral Research, 49, 407-424.

Brosseau-Liard, P. E., & Savalei, V. (2014). Adjusting relative fit indices for nonnormality. Multivariate Behavioral Research, 49, 460-470.

Savalei, V. (2014). Understanding robust corrections in structural equation modeling. Structural Equation Modeling, 21, 149-160.

Savalei, V., & Falk, C. (2014). Robust two-stage approach outperforms robust FIML with incomplete nonnormal data. Structural Equation Modeling, 21, 280-302.

Savalei, V., & Rhemtulla, M. (2013). The performance of robust test statistics with categorical data. British Journal of Mathematical and Statistical Psychology, 66, 201-223.

Brosseau-Liard, P., Savalei, V., and Li, L. (2012). An investigation of the sample performance of two non-normality corrections for RMSEA. Multivariate Behavioral Research, 47, 904-930.

Savalei, V. (2012). The relationship between RMSEA and model misspecification in CFA models. Educational and Psychological Measurement, 72, 910-932.

Rhemtulla, M., Brosseau-Liard, P., & Savalei, V. (2012). How many categories is enough to treat data as continuous? A comparison of robust continuous and categorical SEM estimation methods under a range of non-ideal situations. Psychological Methods, 17, 354-373. doi: 10.1037/a0029315

Savalei, V., & Rhemtulla, M. (2012). On obtaining estimates of the fraction of missing information from full information maximum likelihood. Structural Equation Modeling, 19, 477-494.

For a current list of publications, visit the lab website.