Zahide Alaca

I am a Senior Research Analyst at the Population Analytics and Insights Unit of the Ontario Ministry of Children, Community and Social Services.

I completed a PhD in Educational Leadership and Policy at the University of Toronto, where I studied educational inequality. My ongoing research program improves the quantitative methods that are used to infer the effects of contexts, programs, and policies on population outcomes. My research has been funded by the Social Sciences and Humanities Research Council of Canada and published in the Journal of the Royal Statistical Society: Series A (Statistics in Society).

Previously, I completed a Master and Bachelor of Social Work at Carleton University.

Contact Me

  • zahide.alaca@ontario.ca
  • zahide.alaca@mail.utoronto.ca

CV

Download my CV here.

Research

Working Papers


Using multilevel piecewise growth models to test theories of educational inequality: Caveats.*
Within-student stability in learning trajectories: Revisiting the narrative on summer learning.*
Treatment sequence as dosage: The case of multiyear summer learning programs.*
The random forest estimator: A tutorial and empirical example of Catholic school effects.

*Based on my PhD dissertation.

Articles in Peer-Reviewed Journals


Wodtke, G. T., Alaca, Z., & Zhou, X. (2020). Regression-with-residuals estimation of marginal effects: A method of adjusting for treatment-induced confounders that are also moderators. Journal of the Royal Statistical Society: Series A (Statistics in Society), 183(1), 311–332. https://doi.org/10.1111/rssa.12497
Authors' copy

Teaching

Quantitative Methods


Multilevel and Longitudinal Modelling

Teaching Assistant · Winter 2019
Graduate Course, Department of Leadership, Higher and Adult Education, University of Toronto

This course provides a comprehensive introduction to multilevel modelling, also known as hierarchical linear modelling or mixed effects modelling. I facilitated weekly lab activities, held weekly office hours, graded assignments, and supervised students in the development, analyses, and writing of their final projects with data from the Programme for International Student Assessment (PISA) and the Early Childhood Longitudinal Study, Kindergarten Class of 1998–99 (ECLS-K).

[]
LHA6005: Multilevel and Longitudinal Modelling in Educational Research

This is an advanced applied statistics course designed for doctoral or advanced master’s students and serving as a comprehensive introduction to multilevel modelling, also known as “hierarchical linear modelling (HLM)” or “mixed effects modelling.” These powerful models have become very common in educational research, both for the analysis of data with a multilevel structure (e.g., students nested in schools, school boards, provinces or countries) and for the study of educational change (e.g., student learning/growth, school improvement or organizational change). The course covers two-level and three-level cross-sectional and growth curve models, as well as model selection, assumptions and diagnostics. Examples and assignments will draw on data from large-scale national and international datasets; the course will also serve as an introduction to the HLM7 software package. The objective of the course is to equip students with the skills to use, interpret and write about multilevel models in their own research.

Prerequisite: An intermediate statistics course, such as Intermediate Statistics in Educational Research: Multiple Regression Analysis (JOI3048H), Intermediate Statistics and Research Design (JOI1288H) or equivalent
[Student evaluations]


Multiple Regression Analysis

Teaching Assistant · Winter 2017, Winter 2018
Graduate Course, Department of Leadership, Higher and Adult Education, University of Toronto

This course equips students with the skills to use, interpret, and write about regression models. The course uses the software Stata and large-scale assessment data from the Programme for International Student Assessment (PISA) and the Progress in International Reading Literacy Study (PIRLS). I designed and facilitated weekly lab activities, held weekly office hours, graded assignments, and supervised students in the development, analyses, and writing of their final projects.

[]
JOI3048H: Intermediate Statistics in Educational Research: Multiple Regression Analysis

This is an intermediate applied statistics course designed for students who have already taken one course in elementary concepts (e.g., sampling and statistical inference). The course covers the use, interpretation, and presentation of bivariate and multivariate linear regression models, curvilinear regression functions, dummy and categorical variables, and interactions; as well as model selection, assumptions, and diagnostics. Examples and assignments will draw from commonly-used large-scale educational datasets. Students are encouraged to use Stata; the course will also serve as an introduction to this software package (students may instead choose to use SPSS or other software they are familiar with). The objective of the course is to equip students with the skills to use, interpret and write about regression models in their own research.

Prerequisite: An introductory statistics course, such as Introduction to Applied Statistics (JOI1287H) or equivalent
[Student evaluations]


Quantitative Research Practicum

Teaching Assistant · Winter 2018
Graduate Course, Department of Leadership, Higher and Adult Education, University of Toronto

In this course, students conduct large-scale data analysis for their theses or dissertations, write a quantitative journal article, or conduct a quantitative research project for a policy audience. I supervised all the course projects, which included local studies with student-level data from school boards, province-wide studies with school-level data from the Ontario Ministry of Education, international studies with data from international assessments, and experimental studies in psychology. I guided students in cleaning and preparing their data, conducting their analyses, and interpreting their results. I also held weekly office hours and facilitated one-hour lab sessions on Stata, causal inference, categorical data analysis, and missing-data imputation.

[]
LHA6003: Quantitative Research Practicum

This course has several goals. The foremost is to prepare students wishing to conduct large scale data analysis for their theses or dissertations, to write a quantitative journal article, or to conduct a quantitative research project for a policy audience. Students will receive thorough guidance in the management and analysis of large-scale data sets, including administrative and survey data. Through the DEPE lab, students are provided access to several kinds of data sets (students can also use their own data in the course). Students will write their term papers in a journal article format and will tackle some form of quantitative data analysis. A secondary goal of the course is to provide some supplementary instruction in statistical techniques. As students are expected to begin the course with knowledge of basic statistics, inference and multiple regression, the instructor will provide instruction in the broad topic of causal inference, and offer classes on categorical analysis and propensity score matching. Finally, this course exposes students to issues in research design and novel forms of data collection.

Prerequisite: An intermediate statistics course, such as Intermediate Statistics in Educational Research: Multiple Regression Analysis (JOI3048H), Intermediate Statistics and Research Design (JOI1288H) or equivalent



Exploratory Data Analysis with R

Instructor · Winter 2018, Winter 2019, Fall 2019
Undergraduate Workshop, Program for Accessing Research Training, University of Toronto Mississauga

The Program for Accessing Research Training (PART) prepares undergaduate students at the University of Toronto Mississauga for research opportunities and graduate studies. It is attended by students in all disciplines. I co-instructed a four-hour training module on exploratory data analysis with R, with a focus on importing, cleaning, and visualizing data with the ggplot2 package. Most students did not have prior experience with R.



Substantive Topics


Introduction to Social Work and Social Welfare

Teaching Assistant · Fall 2013, Fall 2014
Undergraduate Course, School of Social Work, Carleton University


Introduction to Economics

Teaching Assistant · 2011–2012, 2012–2013
Undergraduate Course, Department of Economics, Carleton University


Childhood in the Canadian Context

Teaching Assistant · Fall 2012
Undergraduate Course, Institute of Interdisciplinary Studies, Carleton University


Invited Lectures


Using Piecewise Growth Models to Test Seasonal Theories of Educational Inequality · Winter 2019 · For Multilevel and Longitudinal Modelling, Graduate Course, Department of Leadership, Higher and Adult Education, University of Toronto

Regression Diagnostics and a Review of Interactions · Winter 2018 · For Multiple Regression Analysis, Graduate Course, Department of Leadership, Higher and Adult Education, University of Toronto

Developing a Research Program · Fall 2017, Winter 2018 · For People and Power in Organizations, Graduate Course, Department of Leadership, Higher and Adult Education, University of Toronto

Participatory Action Research and the First Nations Principles of OCAP® (Ownership, Control, Access, and Possession) · Winter 2015 · For Research Methods in Social Work, Undergraduate Course, School of Social Work, Carleton University

Child Abuse in Canada · Fall 2012 · For Introduction to Child Studies, Undergraduate Course, Institute of Interdisciplinary Studies, Carleton University

News