Instructor: Kristin D. Mickelson, Ph.D.
Office: Kent Hall Addition 332
Office Phone: 672-2253
Office Hours: Mondays
& Wednesdays 1:30-4:00pm and by appointment
Email: kmickels@kent.edu
Required Texts:
Kline – Principles and Practices of Structural
Equation Modeling, 2nd edition (2005).
Singer & Willett, Applied Longitudinal Data
Analysis: Modeling Change and Event Occurrence (2003).
Additional articles will be assigned as
supplemental reading for various techniques (available at the UPS Store).
Course goals: This seminar is intended
to cover two major multivariate statistical techniques currently utilized in
psychology: structural equation modeling (SEM) and hierarchical linear modeling
(HLM) – some areas of psychology will make more use of these techniques, but
all areas require a basic understanding of them. The goal for students is to
achieve a conceptual understanding of
each statistical technique, be able to apply the correct analysis to any data
set, properly conduct and interpret the output of statistical computer
packages, and understand and critique scientific papers that utilize such
techniques.
The
term conceptual understanding means
that the student gains knowledge of the functional nature of each technique –
in other words, what it is used for, how it is used, the assumptions behind it,
and the information it provides about the data.
The course will not cover the derivations of the formulas, but rather
will use the formulas to assist in understanding the way each technique works.
It
is important that you read the chapters/articles before and after each
class period – this sounds redundant, but reading before the class period will
provide a base of knowledge about the terms while re-reading after the class
period will help to reiterate the details.
Statistical Computer
Packages: Several computer packages will be used in
this course, including EQS, HLM and SPSS.
Each package will be available for student use on the computers in the
grad student lab throughout the semester.
In addition, several class periods will be held in the computer lab to
help students learn to use the programs – students will be notified the prior
class period.
Grading: As the goal of the course is to provide an
understanding that students can transfer to their own research and reading, no
in-class exams will be given. Instead,
grading will reflect your understanding and application of the techniques. First, each student will pose a multivariate
research question, conduct the analyses on an existing data set, and interpret
the results. This project will be
written up as a 10-page paper (40%). In
addition, there will be one take-home exam (50%) at the end of the semester;
this exam will be more conceptual in nature focusing on the functional nature
of the techniques as defined above.
Finally, several small homework assignments will be given - usually in
the context of the computer lab sessions.
These will be graded pass/fail and worth 10% of the course grade.
Analysis Project (40% of
final grade):
With
assistance from the instructor, choose a multivariate research question and
analyze using an existing data set (either your own or one that I have access
to). For the 10-page paper, briefly
state the question and hypothesis (the Introduction should be no more than 2
pages and should conclude with a statement of your hypothesis). Next, your Methods section should be the same
as you would write for a manuscript – detail the sample, procedures, measures
(including how they were scored and alphas), and overview of analysis. The Results section will be a more detailed
version of what you would include in a manuscript; walk through the steps taken
to conduct the most appropriate analysis to answer the question and test the
hypothesis – this includes what you did with missing data and outliers, how you
tested the relevant assumptions and corrected any violations, as well as presenting
the results of the proposed analyses.
Interpret the analyses and results briefly in the Discussion section (no
more than one page). Also, in the
Discussion state what can be concluded from the analyses you conducted and what
cannot be concluded based on your specific dataset (i.e., the pros/cons of your
analysis). Finally, briefly discuss the
pros/cons of one alternative analysis that you could have conducted to
answer the hypothesis.
Paper
should be typed, double-spaced, APA format, 12-point font, and 1"
margins. Tables and/or figures should be
included in the paper, but are not counted toward the page limit. In addition, attach a copy of the syntax and
output from the computer program used for the project as an appendix.
Final Exam (50% of final
grade):
The
exam will be a take-home cumulative exam that covers the conceptual nature of
the techniques discussed in class. The
exam will be an essay format, open-note, open-book. Students are not allowed to work on
the exams together and must sign-out the exam and return it 36-hours
later. The final answers should be
typed, not hand-written.
Homework Assignments (10% of final grade):
Throughout
the semester, I will give several short homework assignments, usually in
conjunction with the computer lab sessions.
These assignments will help in making sure that you understand the
concepts and computer programs. Grading
will be pass/fail.
This
syllabus schedule is tentative.
Background
and Review
Chapter:
Licht, M. H. (1995). Multiple regression and correlation. In L. G. Grimm & P. R. Yarnold
(Eds.),
Wright, R. E. (1995). Logistic regression. In L. G. Grimm & P. R. Yarnold
(Eds.),
Articles:
Coulton, C., & Chow, J. (1992). Interaction effects in multiple
regression. Journal of Social
Service Research, 16, 179-199.
Frazier,
P. A., Tix, A. P., & Barron, K. E. (2004). Testing moderator and mediator effects
in counseling psychology research. Journal of Counseling Psychology, 51, 115-134.
Venter,
A., & Maxwell, S. E. (2000). Issues in the use and application of
multiple regression analysis. In H. E. A. Tinsley & S. D. Brown (Eds.), Handbook of
applied multivariate statistics and mathematical modeling (pp. 151-182).
Kline – Chapter 1
(pp. 9-16 – Section 1.5 Family Values)
Kline – Chapter 2 (pp. 20-44)
Hoyle, R.
H., & Smith, G. T. (1994). Formulating clinical research
hypotheses as structural equation models: A conceptual overview. Journal of Consulting and Clinical
Psychology, 62, 429-440.
Musil, C. M., Jones, S. J., & Warner, C. D. (1998). Structural equation modeling and its
relationship to multiple regression and factor analysis. Research in Nursing and Health, 21, 271-281.
Dilalla, L. F. (2000). Structural equation modeling: Uses and
issues. In H. E. A. Tinsley & S. D.
Brown (Eds.), Handbook of Applied Multivariate Statistics and Mathematical
Modeling (pp. 439-463).
MacCallum, R. C., & Austin, J. T.
(2000).
Applications of structural equation modeling in psychological
research. Annual Review of
Psychology, 51, 201-226.
Russell, D. W., Kahn, J. H.,
Spoth, R., & Altmaier,
E. M. (1998). Analyzing
data from experimental studies: A latent variable structural equation modeling
approach. Journal of Counseling Psychology, 45,
18-29.
Kline – Chapters 3 & 4 (pp. 45-90)
Jackson, D. L. (2003). Revisiting sample size and number of
parameter estimates: Some support for the n:q
hypothesis. Structural Equation
Modeling, 10, 128-141.
Kline – Chapters 5 & 6 (pp. 93-164)
Klem, L. (1995). Path analysis. In L. G. Grimm & P. R. Yarnold (Eds.),
MacKinon, D. P., Krull,
J. L., & Lockwood, C. M. (2000). Equivalence of the
mediation, confounding and suppression effect.
Prevention Science, 1, 173-181.
Shrout, P. E., & Bolger, N. (2002). Mediation in experimental and nonexperimental studies: New procedures and
recommendations. Psychological
Methods, 7, 422-445.
Kline – Chapter 7 (pp. 165-208)
Kenny, D. A., & McCoach, B. (2003). Effect of the number of variables on measures of fit in structural
equation modeling. Structural
Equation Modeling, 10, 333-351.
Kline – Chapter 8 (pp. 209-234)
MacCallum, R. C. (1995). Model specification: Procedures, strategies,
and related issues. In R. H. Hoyle
(Ed.), Structural Equation Modeling: Concepts, Issues, and Applications
(pp. 16-36).
Tomarken, A. J., & Waller, N. G. (2003). Potential problems with “well fitting”
models. Journal of Abnormal Psychology, 112, 578-598.
Kline – Chapters 9 & 11 (pp. 237-262;
289-312)
Benbenishty, R., Astor, R. A., Zeira, A., & Vinokur, A.
D. (2002). Perceptions of violence and fear of
school attendance among junior high school students in
Farrell, A. D. (1994). Structural equation modeling with
longitudinal data: Strategies for examining group differences and reciprocal
relationships. Journal of Consulting
and Clinical Psychology, 62, 477-487.
Fincham, F. D., Beach, S. R. H., Harold, G. T.,
& Osborne, L. N. (1997). Marital satisfaction and depression:
Different causal relationships for men and women? Psychological Science, 8, 351-357.
Vinokur, A. D., & Schul, Y. (2002). The web of coping
resources and pathways to reemployment following a job loss. Journal of Occupational Health Psychology,
7, 68-83.
Kline – Chapter 12
(pp. 313-324)
Hoyle, R.
H., & Panter, A. T. (1995). Writing about structural equation
models. In R. H. Hoyle (Ed.), Structural
Equation Modeling: Concepts, Issues, and Applications (pp. 158-176).
McDonald,
R. P., & Ho, M. R. (2002). Principles and practice in reporting
structural equation analyses. Psychological
Methods, 7, 64-82.
Raykov, T., Tomer, A.,
& Nesselroade, J. R. (1991). Reporting structural equation modeling
results in Psychology and Aging: Some proposed guidelines. Psychology and Aging, 6, 499-503.
Thompson, B. (2000). Ten commandments of structural
equation modeling. In L. G. Grimm &
P. R. Yarnold (Eds.), Reading and Understanding
More Multivariate Statistics (pp. 261-284).
Washington, D. C.: APA.
Singer & Willet – Chapters 1 & 2 (pp. 3-44)
Weinfurt, K. P. (2000). Repeated measures analyses: ANOVA,
MANOVA, and HLM. In L. G. Grimm & P.
R. Yarnold (Eds.), Reading and Understanding More
Multivariate Statistics (pp. 317-362).
Washington, D. C.: APA.
Wendorf, C. A. (2002). Comparisons of structural equation modeling
and hierarchical linear modeling approaches to couples’ data. Structural Equation
Modeling, 9, 126-140.
Singer & Willett – Chapter 3 (pp. 45-74)
Bryk, A. S., & Raudenbush,
S. W. (1987). Application of hierarchical linear
models to assessing change. Psychological
Bulletin, 101, 147-158.
Nezlek, J. B. (2003). Using multilevel random
coefficient modeling to analyze social interaction diary data. Journal of Social and Personal
Relationships, 20, 437-469.
Nezlek, J. B., & Zyznuewski,
L. E. (1998). Using hierarchical linear modeling to
analyze grouped data. Group Dynamics,
2, 313-320.
Singer & Willett – Chapters 4 & 5
(pp. 75-188)
DeLongis, A., Capreol, M., Holtzman,
S., O’Brien, T., & Campbell, J. (2004). Social support and social strain among
husbands and wives: A multilevel analysis.
Journal of Family Psychology, 18, 470-479.
Helson, R., Jones, C., & Kwan, V. S. Y. (2002). Personality change over 40 years of
adulthood: Hierarchical linear modeling analyses of two longitudinal
samples. Journal of Personality and Social
Psychology, 83, 752-766.
Raudenbush, S. W., Brennan, R. T.,
& Barnett, R. C. (1995). A multivariate hierarchical model for
studying psychological change within married couples. Journal
of Family Psychology, 9, 161-174.