Graduate Studies Reports Access
Graduate Course Proposal Form Submission Detail - EDF7474
Tracking Number - 2123
Edit function not enabled for this course.
Current Status:
Approved, Permanent Archive - 2011-07-17
Campus:
Submission Type: New
Course Change Information (for course changes only):
Comments: to GC for revew; section 3A justification incomplete. Completed. Back to GC 3/11/11. Needs 4E,F,G,h,I,J completed. Emailed 3/17/11, 6/23/11. Updated 6/29/11. GC approved 7/5/11. To USF Syst 7/5/11; to SCNS 7/13/11. approved effective 8/1/11. posted in ba
Detail Information
- Date & Time Submitted: 2008-07-29
- Department: Measurement and Research
- College: ED
- Budget Account Number: 171100000
- Contact Person: Robert F. Dedrick
- Phone: 45722
- Email: dedrick@tempest.coedu.usf.edu
- Prefix: EDF
- Number: 7474
- Full Title: Applied Multilevel Modeling in Education
- Credit Hours: 3
- Section Type: C -
Class Lecture (Primarily)
- Is the course title variable?: N
- Is a permit required for registration?: Y
- Are the credit hours variable?: N
- Is this course repeatable?:
- If repeatable, how many times?: 0
- Abbreviated Title (30 characters maximum): Applied Multilevel Model in Ed
- Course Online?: -
- Percentage Online:
- Grading Option:
R - Regular
- Prerequisites: Multiple Regression
- Corequisites:
- Course Description: Helps students develop skills in defining, estimating, testing, and reporting the results of multilevel models. Design issues, model specification, estimation, statistical software, and model evaluation will be discussed.
- Please briefly explain why it is necessary and/or desirable to add this course: There has been an increase in the number and complexity of multilevel models used in education and other fields. This course provides students the skills to evaluate current applications and contribute to the evolving field of multilevel modeling.
- What is the need or demand for this course? (Indicate if this course is part of a required sequence in the major.) What other programs would this course service? This course will be an elective for students in Measurement and Evaluation. Given the widespread application of multilevel modeling in education and related fields, it is anticipated that the majority of students in the program will choose this elective. As with other courses in the Measurement and Research program that attract students from Psychology, Public Health, Business, etc. it is anticipated that these students will also take advantage of this course offering.
- Has this course been offered as Selected Topics/Experimental Topics course? If yes, how many times? The course has been offered 3 times (Summer semester in 2005, 2006, 2008). Enrollment has averaged approximately 30 students.
- What qualifications for training and/or experience are necessary to teach this course? (List minimum qualifications for the instructor.) Doctoral degree in Educational, Measurement, and Research and courses and experiences meeting Department criteria for teaching doctoral level courses in the area.
- Objectives: Course Goals and Objectives: For 2- and 3-level models with continuous or dichotomous outcomes (e.g., individuals nested in contexts, growth curves, observations nested within individuals within contexts), this course is designed to enable students to:
a. Recognize research scenarios that are amenable to multilevel modeling
b. Translate research questions into multilevel models
c. Specify the multilevel model using hierarchical modeling notation
d. Specify the multilevel model using the mixed modeling notation
e. Screen data for the purpose of assessing the tenability of assumptions
f. Make decisions regarding estimation of the model
g. Prepare data for the multilevel modeling analysis
h. Center variables appropriately
i. Write the computer code necessary to run a multilevel modeling analysis
j. Recognize and make decisions when estimation difficulties are encountered
k. If appropriate, compare the fit of competing models
l. If appropriate, use results to build the multilevel model
m. Summarize the results of the analyses
n. Critically read and critique applications using multilevel modeling
- Learning Outcomes: 1. Assignment 1 Analysis of 2-level organizational model (preliminary data analysis, evaluate model assumptions and fit, estimate and report model parameter estimates) 20%
2. Assignment 2 Analysis of 2-level growth curve model (preliminary data analysis, evaluate model assumptions and fit, estimate and report model parameter estimates) 20%
3. Assignment 3 Critique of HLM application article using checklist 20%
4. Project 40%
Students will complete multilevel analyses based on data and models of their own choosing. The student will identify and/or gather the data, develop the model(s), specify the model(s), estimate the model(s) using appropriate software, and write a report on the study in APA format, where the results section should be of a quality suitable for publication.
____ Rationale for questions/models included
____ Appropriate level of detail regarding sample
____ Appropriate level of detail regarding variables
____ Analyses clearly described, including any modifications
____ Model(s) specified consistently with theory/rationale
____ Program syntax is accurate
____ Data screening conducted and reported
____ Appropriate choice of estimation method
____ Variance components included
____ Accurate description/discussion of variance components
____ Fixed effect estimates included
____ Accurate description/discussion of fixed effects
____ Limitations noted
____ Conclusions consistent with results
____ Publishable writing of results section
- Major Topics: Orientation to course, introduction to multilevel modeling, and multilevel analysis software, Intraclass Correlation Coefficient (ICC)
Model specification and centering in 2-level organizational models
Building and evaluating 2-level organizational models
Data screening, estimation, and inference in 2-level organizational models
Model specification for growth curve models
Assessing the adequacy of growth curve models
Three-level models
Meta-analysis
Dichotomous outcome variables in multilevel models
Cross-classified random effects models
Power and sample size
- Textbooks: Luke, D. A. (2004). Multilevel modeling. Newbury Park: Sage Publications.
Raudenbush, S. W., & Bryk, A. S. (2002). Hierarchical linear models: Applications and data analysis methods. Newbury Park: Sage Publications.
Additional readings provided in Blackboard.
Raudenbush, S. W., & Bryk, A. S. (2002). Hierarchical linear models: Applications and data analysis methods. Newbury Park: Sage Publications.
Current methodological articles such as:
Paccagnella, O. (2006). Centering or not centering in multilevel models? The role of the group mean and the assessment of group effec
- Course Readings, Online Resources, and Other Purchases: Optional
Hox, J. J. (2010). Multilevel analysis: Techniques and applications. New York, NY: Routledge.
Singer, J. D. (1998). Using SAS PROC MIXED to fit multilevel models, hierarchical models, and individual growth models. Journal of Educational and Behavioral Statistics, 24, 323-355.
Statistical Software:
HLM 6 (Free student version is available at http://www.ssicentral.com/hlm/student.html)
SAS PROC MIXED is available for purchase at the USF bookstore; available for use at USF open use labs, and EDU 248
- Student Expectations/Requirements and Grading Policy: Each students final course grade is computed as a weighted combination of the following components:
ELEMENTS WEIGHT
1. Assignment 1 Analysis of 2-level organizational model 10%
2. Assignment 2 Analysis of 2-level growth curve model 10%
3. Assignment 3 Critique of HLM application article 10%
4. Project See below for description 35%
5. Final Exam 35%
Project Description:
All projects should be discussed with the instructors early in the semester to get direction and approval. Projects may be done individually or in collaborative teams of no more than three.
Students will complete multilevel analyses based on data and models of their own choosing. The student will identify and/or gather the data, develop the model(s), specify the model(s), estimate the model(s) using appropriate software, and write a report on the study in APA format, where the results section should be of a quality suitable for publication.
____ Rationale for questions/models included
____ Appropriate level of detail regarding sample
____ Appropriate level of detail regarding variables
____ Analyses clearly described, including any modifications
____ Model(s) specified consistently with theory/rationale
____ Program syntax is accurate
____ Data screening conducted and reported
____ Appropriate choice of estimation method
____ Variance components included
____ Accurate description/discussion of variance components
____ Fixed effect estimates included
____ Accurate description/discussion of fixed effects
____ Limitations noted
____ Conclusions consistent with results
____ Publishable writing of results section
Grading Criteria:
Course Grading Standards:
90 - 100% = A
80 - 89% = B
70 79% = C
60 69% = D
< 60% = F
The grading system used in the course will be letter grades assigned on the following basis
A - Superior Performance (overall score= 90-100)
B - Average Performance (overall score= 80-89)
C - Below Average Performance (overall score =70-79)
D, F- Failure (overall score 69)
Please note the following USF Graduate School Policy on grades :
No grade below C will be accepted toward a graduate degree. This includes C - grade.
G. Assignments, Exams and Tests
1. Assignment 1 Analysis of 2-level organizational model (HS& B dataset)
2. Assignment 2 Analysis of 2-level growth curve model (ECLS dataset)
3. Assignment 3 Critique of HLM application article (using HLM Checklist)
4. Project
5. Final Exam (based on objectives listed in Blackboard)
- Assignments, Exams and Tests:
- Attendance Policy: Although attendance is critical to success in the class, there is no penalty for missing class. Please alert the instructor if you know in advance if you will be missing class. Class sessions may be taped and tapes and notes may be shared with classmates, but these materials may not be sold.
- Policy on Make-up Work: Late work will be accepted but there will be a penalty of 1 point for each day turned in late. The penalty may be waived if there are extenuating circumstances (e.g., illness).
- Program This Course Supports: Measurement and Research Dept
- Course Concurrence Information:
- if you have questions about any of these fields, please contact chinescobb@grad.usf.edu or joe@grad.usf.edu.