|Instructor:||Professor Lesa Hoffman (she, her, hers)|
Educational Measurement and Statistics Program
|Department:||Psychological and Quantitative Foundations
Office: 361 Lindquist Center (South); DEO: Dr. Megan Foley Nicpon
|Instructor Office:||356 Lindquist Center (South)||Instructor Email:||Lesa-Hoffman@UIowa.edu|
|Course Room:||North 166 Lindquist Center||Course Time:
|Tuesdays and Thursdays 2:00–3:15 PM
Tuesdays and Thursdays 3:15-4:15 PM in the course room
|Course Textbook:||Multilevel Analysis: An Introduction to Basic and Advanced Multilevel Modeling||SAS Resources:||Lesa's SAS guide from PilesOfVariance.com
SAS MIXED Online Manual
|Online Homework:||Homework Portal (coming soon)||Stata Resources:||Lesa's Stata guide from PilesOfVariance.com
Stata MIXED Online Manual
Topics and Course Materials
|1||8/26||NO HOMEWORK (HW) OR FORMATIVE ASSESSMENTS (FA) DUE|
Lecture 1: Introduction to Multilevel Models (MLMs)
|S & B ch. 1-2|
|8/29||Lecture 2a: Review of Single-Level General Linear Models
Example 2a: Review of General Linear Models in SAS and STATA
Data, Syntax, and Output for Example 2a, 2b, and 2c
|Hoffman (2015) ch. 2 sec. 1|
|2||9/2||FA1 DUE VIA ICON BY 11:59 PM|
|9/3||Lecture 2a and Example 2a continued
Lecture 2b: Interactions among Continuous Predictors
Example 2b: Interactions among Continuous Predictors in SAS and STATA
|Hoffman (2015) ch. 2 sec. 2|
|9/5||HW0 DUE ONLINE BY 11:59 PM FOR 3 POINTS EXTRA CREDIT
Lecture 2b and Example 2b continued
|Hoffman (2015) ch. 2 sec. 3+|
|3||9/9||FA2 DUE VIA ICON BY 11:59 PM|
|9/10||Lecture 2c: Interactions among Categorical Predictors
Example 2c: Interactions among Categorical Predictors in SAS and STATA
|9/12||NO CLASS OR OFFICE HOURS|
|4||9/16||HW1 DUE ONLINE BY 11:59 PM|
|9/17||Topic 3: General MLMs for Two-Level Nested Data||S & B ch. 3-7|
|9/19||Topic 3 continued||Rights & Sterba (2019)|
|5||9/23||FA3 DUE VIA ICON BY 11:59 PM|
|9/24||Topic 3 continued||Raudenbush & Bryk (2002) ch. 5|
|9/26||Topic 3 continued||Enders (2010) ch. 3-5|
|6||9/30||HW2 DUE ONLINE BY 11:59 PM|
|10/1||Topic 4: General MLMs for Two-Level Crossed Data||S & B ch. 13|
|10/3||Topic 4 continued||Raudenbush & Bryk (2002) ch. 12
Hoffman (2015) ch. 12
|7||10/7||NO HW OR FA DUE|
|10/8||Topic 5: Review of Single-Level Generalized Linear Models||DeMaris (2003)|
|10/10||NO CLASS OR OFFICE HOURS|
|8||10/14||FA4 DUE VIA ICON BY 11:59 PM|
|10/15||Topic 5 continued|
|10/17||Topic 6: Generalized MLMs for Two-Level Nested Data||S & B ch. 10, 17
|9||10/21||HW3 DUE ONLINE BY 11:59 PM|
|10/22||Topic 6 continued||Nakagawa & Schielzeth (2010)|
|10/24||Topic 6 continued||Hox (2010) ch. 6-7|
|10||10/28||FA5 DUE VIA ICON BY 11:59 PM|
|10/29||Topic 7: Generalized MLMs for Two-Level Crossed Data||Rijmen et al. (2003)|
|10/31||Topic 7 continued|
|11||11/4||HW4 DUE ONLINE BY 11:59 PM|
|11/5||Topic 8: MLMs for Two-Level Multivariate and Path Analysis||Ludtke et al. (2008)|
|11/7||Topic 8 continued||Preacher et al. (2010, 2011)|
|12||11/11||FA6 DUE VIA ICON BY 11:59 PM|
|11/12||Topic 8 continued||Hoffman (2019)|
|11/14||Topic 8 continued|
|13||11/18||HW5 DUE ONLINE BY 11:59 PM|
|11/19||Topic 9: MLMs for Three-Level Data||Hoffman (2015) ch. 11|
|11/21||Topic 9 continued|
|14||11/25||NO HW OR FA DUE|
|11/26||NO CLASS OR OFFICE HOURS|
|11/27||NO CLASS OR OFFICE HOURS|
|15||12/2||NO HW OR FA DUE|
|12/3||Topic 9 continued|
|12/5||Topic 9 continued|
|16||12/9||FA7 DUE VIA ICON BY 11:59 PM|
|12/10||Topic 10: TBD||TBD|
|12/12||Topic 10 continued|
|17||12/20||HW6 DUE BY 11:59 PM ONLINE
ALL OUTSTANDING WORK MUST BE SUBMITTED BY 11:59 PM FOR COURSE CREDIT
The planned schedule of topics and events may need to be adjusted throughout the course. The online syllabus above will always have the most current schedule and course materials.
This course will illustrate the uses of multilevel models (i.e., general linear mixed-effect models, hierarchical linear models) for the analysis of clustered data (persons nested in groups). The course is organized to take participants through each of the cumulative steps in a multilevel analysis: deciding which type of model is appropriate, organizing the data and creating predictor variables, testing fixed and random effects, predicting multiple sources of variation, and interpreting and presenting empirical findings. Class time will be devoted primarily to lectures and examples. Lecture materials will be available for download at the website above the day prior to class, or else paper copies can be requested. Video recordings of the class lectures will also be available online but are not intended to take the place of class attendance. Book chapters and journal articles will be assigned for each specific topic as needed; the initial list of readings below may be updated later. There will be no exams nor any required attendance outside the regular class time. However, because the course will have an applied focus requiring the use of statistical software, instructor office hours will also be held in a group-based format, in which multiple participants will have opportunities to work on course assignments simultaneously and receive immediate assistance. Participants should be comfortable with estimating and interpreting general linear models (i.e., analysis of variance, regression) prior to enrolling in this course.
Participants will have the opportunity to earn up to 100 total points in this course. Up to 86 points can be earned from homework assignments (approximately 6 in total)—these will be graded for accuracy. Up to 14 points may be earned from submitting outside-of-class formative assessments (approximately 7 in total); these will be graded on effort only—incorrect answers will not be penalized. Please note there will also be an opportunity to earn up to 3 points of extra credit (labeled as homework 0; see the above syllabus). There may be other opportunities to earn extra credit at the instructor's discretion.
In order to be able to provide the entire class with prompt feedback, homework assignments submitted any time after the deadline will incur a 3-point penalty. However, extensions will be granted as needed for extenuating circumstances (e.g., conferences, comprehensive exams, family obligations) if requested at least two weeks in advance of the due date. Late or incomplete outside-of-class formative assessments will incur a 1-point penalty when submitted. A final grade of “incomplete” will only be given in dire circumstances and entirely at the instructor's discretion.
>96 = A+, 93–96 = A, 90–92 = A−, 87–89 = B+, 83–86 = B, 80–82 = B−, 77–79 = C+, 73–76 = C, 70–72 = C−, 67–69 = D+, 63–66 = D, 60–62 = D−, <60 = F
As a reminder, the University of Iowa College of Education has a formal policy on academic misconduct, which all students in this course are expected to follow. Please consult the instructor if you have questions.
Students with disabilities or who have other special needs are encouraged to contact the instructor for a confidential discussion of their individual needs for academic accommodation.
It is my intent that students from ALL backgrounds and perspectives feel welcome and encouraged to participate in this course. There is no such thing as a “stupid” question. All course participants—enrolled students and auditors—should always feel welcome to ask whatever questions will be helpful in helping them understand and follow the course content. You may do so during class, in office hours, over email, or in individual appointments with the instructor (available by request).
The instructor realizes that this course is not your only obligation in your work or your life. If work or life events (expected or unexpected) may compromise your ability to succeed in this course, PLEASE contact the instructor for a confidential discussion (in person or over email, as you prefer) so that we can work together to make a plan for your success. Please do not wait to do so until you are too far behind to catch up!
Participants will also need to have access to software that can estimate the models presented. Although the course will feature SAS and Stata primarily, other software packages (e.g., SPSS, R) can also be used to complete homework assignments. These packages are freely available to University of Iowa members through the UIowa Virtual Desktop. Please note that Stata is only available when using the Virtual Desktop on campus, whereas SAS is available remotely as well.
S & B: Snijders, T. A. B., & Bosker, R. J. (2012). Multilevel analysis: An introduction to basic and advanced multilevel modeling. Thousand Oaks, CA: Sage.
Bauer, D. (2009). A note on comparing the estimates of models for cluster-correlated or longitudinal data with binary or ordinal outcomes. Psychometrika, 74 (1), 97-105.
DeMaris, A. (2003). Logistic regression. In I. B. Weiner, D. K. Freedheim, J. A. Shinka, & W. F. Velicer (Eds.) Handbook of Psychology, Research Methods in Psychology (pp. 509-532). Hoboken, NJ: Wiley.
Enders, C. K. (2010). Applied missing data analysis. New York, NY: Guilford.
Hoffman, L. (2015). Longitudinal analysis: Modeling within-person fluctuation and change. New York, NY: Routledge Academic.
Hoffman, L. (2019). On the interpretation of parameters in multivariate multilevel models across different combinations of model specification and estimation. Forthcoming in Advances in Methods and Practices in Psychological Science.
Hox, J. (2010). Multilevel analysis: Techniques and applications (2nd ed). New York, NY: Routledge Academic.
Lüdtke, O., Marsh, H. W., Robitzsch, A., Trautwein, U., Asparouhov, T., & Muthén, B. (2008). The multilevel latent covariate model: A new, more reliable approach to group-level effects in contextual studies. Psychological Methods, 13(3), 203-229.
Nakagawa, S., & Schielzeth, H. (2010). Repeatability for Gaussian and non-Gaussian data: A practical guide for biologists. Biological Reviews, 85, 935-956.
Preacher, K. J., Zhang, Z., & Zyphur, M. J. (2011). Alternative methods for assessing mediation in multilevel data: The advantages of multilevel SEM. Structural Equation Modeling, 18, 161-182.
Preacher, K. J., Zyphur, M. J., & Zhang, Z. (2010). A general multilevel SEM framework for assessing multilevel mediation. Psychological Methods, 15(3), 209-233.
Raudenbush, S. W., & Bryk, A. S. (2002). Hierarchical linear models: Applications and data analysis methods (2nd ed.). Thousand Oaks, CA: Sage.
Rights, J. D., & Sterba, S. K. (2019). Quantifying explained variance in multilevel models: An integrative framework for defining R-squared measures. Psychological Methods, 24(3), 309-338.
Rijmen, F., Tuerlinckx, F., De Boeck, P., & Kuppens, P. (2003). A nonlinear mixed model framework for item response theory. Psychological Methods, 8(2), 185-205.