Welcome to Simon Fraser University
You have reached this page because we have detected you have a browser that is not supported by our web site and its stylesheets. We are happy to bring you here a text version of the SFU site. It offers you all the site's links and info, but without the graphics.
You may be able to update your browser and take advantage of the full graphical website. This could be done FREE at one of the following links, depending on your computer and operating system.
Or you may simply continue with the text version.

FireFox (Recommended) http://www.mozilla.com/en-US/firefox/
Opera http://www.opera.com/

*Macintosh OSX:*
FireFox (Recommended) http://www.mozilla.com/en-US/firefox/
Opera http://www.opera.com/

*Macintosh OS 8.5-9.22:*
The only currently supported browser that we know of is iCAB. This is a free browser to download and try, but there is a cost to purchase it.
Close x
Searching... Please wait...

Measurement and Modelling Lab

Current Projects in the MML
* see below for select Research Tools developed in our lab. 

Advancing Questionnaire Design/Use

Our current focus is studying response processes on questionnaires of health/well-being/depressive symptomology using a combination of quantitative and qualititative research methodologies. Of particular interest is the language background of the respondent as well as linguistic features of the items on the questionnaire, and their role in the response generation process by the respondent. We are using questionnaire surveys as well as interviews with our study participants to gain understanding of commonalities and very individualized processes/responses.

The main project of understanding respondents perceptions of questionnaires for the Advancing Questionnaire Design/Use team of the Fouladi MML Lab includes volunteer and worstudy students currently guided by the team coordinator, Jamie Hystad. (See the People tab for a listing of students across the university variously contibuting to the work of the MML lab).

Advancing Statistical Practice

A key aim in our lab is to advance statistical practice. A current focus is on disseminating underutilized statistical procedures, including but not limited to procedures that Fouladi and colleagues have studied and/or developed, e.g., analysis of correlation pattern models. Because easy user-interface is important to helping the adoption of statistical procedures, the MML lab is working to provide web-based Shiny implementations of some of these procedures. 

The research tools below are being developed in the Fouladi MML lab by volunteer and workstudy students working in the Advancing Statistical Practice team guided by the team coordinator, Paul Serafini.  (See the People tab for a listing of students across the university variously contibuting to the work of the MML lab).

MMLR2 (2017): https://shiny.rcg.sfu.ca/u/pserafin/rsquared

R2 was developed by Steiger and Fouladi (1992) to advance the practice of multiple regression analysis planning and results reporting. The original R2 program is an MSDOS program which implements procedures not generally available in commonly used statistical software, and provides an early illustration of the application of the use of principles of non-centrality interval estimation discussed in the chapter by Steger and Fouladi (1997) in the widely cited book What if there were no significance tests (Harlow, Mulaik, & Steiger, eds., 1997). R2 provides exact confidence intervals for the squared multiple correlation coefficent based on a random regressor model, varied power calculations, distributional probability calculations, and non-standard hypothesis tests of the squared multiple correlation. 

MMLR2 implements some of the key features of R2 but also uses the more commonly used fixed regressor model framework  (e.g., GPower) for some the procedures.

MMLR2 provides a web-based interface permitting users to perform:

  • Calculation of confidence intervals and lower confidence bounds for the squared multiple correlation, using either a fixed regressor method or the random regressor method, similar to those implemented in GPower and R2, which can then in turn be used for CI on differences between independent squared multiple correlation values as described by Zou (2007) .
  • Power calculation for tests of significance of the squared multiple correlation based on a fixed regressor model.
  • Calculation of the sample size necessary to achieve a desired level of power for testing a hypothesis of zero multiple correlation using a fixed regressor model.
  • Calculation of the sample size necessary to achieve a desired level of power for testing a hypothesis of a multiple correlation value other than zero, using a fixed regressor model.

Additionally, MMLR2 permits calculation of squared multiple correlations and standardized regression coeffients using inputted correlation matrices. For the input matrix, users can flexibily identify any variable as the criterion variable and any of the remaining variables as the regressor set. Inputted correlation matrices must be in csv file format -- use MML CSV generator (see below)  for assistance on setting up an appropriately formatted *.csv correlation matrix file). Within this

MMLWBCORR (2017): https://shiny.rcg.sfu.ca/u/pserafin/wbcorr/

WBCORR (Within-Between CORRelational tests) is correlation pattern hypotheis test program developed for Mathematica by Steiger (2004). WBCORR can handle raw or correlation data, in one or more samples, with or without equal sample sizes, and with or without the assumption of multivariate normaltiy. The program implements GLS, TSGLS, ADF, and TSADF chi-square statistics. See Steiger (2004) for a discussion of the methods employed by WBCORR.

MMLWBCORR provides a web-based interface permitting users to perform analyses similar to those analyzable using Steiger's WBCORR, using the GLS, TSGLS, ADF, and TSADF chi-square statistics. However, MLWBCORR differs from the Steiger's Mathematica WBCORR (2004) in its implementation of tests of correlation patterns for common specified values, and its treatment of missing data. In particular, MLWBCORR draws on work presented in Yuan, Lambert, Fouladi (2004) for tests of multivariate normality under conditions of missing data conditions.

Please be sure to read the ReadMe section MMLWBCORR, and associated documents.

MML CSV Generator (2017): https://shiny.rcg.sfu.ca/u/pserafin/csvgenerator/

MML CSV Generator was created to facilitate the construction of appropriately formatted csv correlation matrix and hypothesis matrix files for MMLWBCORR. The Correlation Matrix tab of MML CSV Generator can also be used to create appropriately formatted csv files to make use of MMLR2's flexible capabability to calculate squared multiple correlations and standardized regression coefficients based on input correlation matrices.