Advanced

Statistical Research Methods

TU-L0040/JSBJ1311
Fall 2021-Spring 2022
7-10 Credits

Note: All course lectures are openly accessible on the course website and the units are
available as playlists at https://www.youtube.com/mronkko

1 COURSE STAFF AND CONTACT INFORMATION .................................................................................... 2

2 OVERVIEW OF THE COURSE ....................................................................................................................... 2
3 PARTICIPATION AND SIGNING UP ............................................................................................................. 3
4 LEARNING OUTCOMES .................................................................................................................................. 3
5 WORKLOAD ....................................................................................................................................................... 3
6 COURSE CONTENT .......................................................................................................................................... 4
6.1 PRE-EXAM (MANDATORY) ...................................................................................................5
6.2 READINGS AND WRITTEN ASSIGNMENTS (2 MANDATORY, 6 OPTIONAL) ..............................6
6.3 DATA-ANALYSIS ASSIGNMENTS (8 MANDATORY) ................................................................6
6.4 MONTE CARLO ASSIGNMENT (MANDATORY).......................................................................7
6.5 PRESENTATION OF A METHODOLOGICAL PAPER (MANDATORY) ...........................................7
6.6 VIDEO LECTURES (MANDATORY AND OPTIONAL) ................................................................7
6.7 ONLINE INTERACTIONS (MANDATORY)................................................................................8
6.8 SEMINAR SESSIONS (MANDATORY) ......................................................................................8
6.9 FINAL EXAM (MANDATORY) ................................................................................................8
7 UNITS AND SCHEDULE ................................................................................................................................... 8
7.1 UNIT 1: COURSE INTRODUCTION .......................................................................................10
7.2 UNIT 2: CAUSALITY, ENDOGENEITY, AND NATURAL EXPERIMENTS ...................................10
7.3 UNIT 3: STRUCTURAL EQUATION MODELING, MEDIATION, AND INSTRUMENTAL VARIABLES
11
7.4 UNIT 4: MODERATION, TRANSFORMATIONS, AND GENERALIZED LINEAR MODELS.............13
7.5 UNIT 5: STRUCTURAL EQUATION MODELING WITH LATENT VARIABLES ............................13
7.6 UNIT 6: MEASUREMENT AND MEASUREMENT VALIDATION ...............................................14
7.7 UNIT 7: MULTILEVEL MODELS ..........................................................................................15
7.8 UNIT 8: LONGITUDINAL ANALYSIS AND MULTILEVEL SEMS .............................................16
7.9 UNIT 9: SAMPLING, SAMPLE SELECTION, AND MISSING DATA ............................................17
7.10 UNIT 10: STUDENT PRESENTATIONS AND COURSE CONCLUSION.....................................19
8 GRADING .......................................................................................................................................................... 19
9 COURSE MATERIAL ...................................................................................................................................... 19
9.1 BOOKS...............................................................................................................................19
9.2 ARTICLES ..........................................................................................................................19
9.3 EMPIRICAL ARTICLES USED AS EXAMPLES .........................................................................20
10 ABOUT THE INSTRUCTOR ...................................................................................................................... 20
1 COURSE STAFF AND CONTACT INFORMATION
Dr. Mikko Rönkkö Course instructor [email protected]
[email protected]
• All course assignments are available and returned through Aalto MyCourses.
• All articles and other reading materials are available through Zotero and/or the library.
• MyCourses forums are the primary communications channel of the course.
• Zoom and WhatsApp/Signal are used for instructing computer assignments
• Email the course instructor only in personal matters (e.g. if you miss a seminar.)

2 OVERVIEW OF THE COURSE

This is a blended learning course that contains both online and in-person elements. The course is
organized by Aalto University and University of Jyväskylä and participants can obtain credits
from either of these universities with a course code of their choice (TU-L0040/JSBJ1311).
This is an advanced level course that is designed to be completed after TU-L0022/JSBJ1310
Statistical Research Methods. Ideally, participants should already some experience in using
quantitative research designs and data analysis techniques in their own research.
The goal of the course is to develop a more thorough understanding of how and why certain
techniques are used and what principles these techniques are based on. The course focuses on
longitudinal and multilevel designs and analyses. The techniques covered include all advanced
econometrics and latent variable techniques used in Academy of Management Journal, Journal
of Applied Psychology, Journal of Management, Journal of Operations Management, Journal of
Organizational Behavior, The Leadership Quarterly, Organization Science, Personnel
Psychology, and Strategic Management Journal as reported in a recent review1. The focus of the
course will be on how these techniques can be used to empirically support causal claims taking
particularly the issues of endogeneity and measurement validity into account. Compared to the
basic Statistical Research Methods course, this course will focus much more on data analysis.
The course consists of ten units, that each take three to four weeks and contain video lectures,
online and in-person discussions, and assignments. The number of credits varies between 7-10
depending on which assignments students choose to complete. The content of each course
component is explained later in the syllabus. All data analysis assignments can be completed
with Stata or R. Mplus can be used for some of the assignment or their parts.
Credits Content
7 • Pre-exam
• Video lectures and online participation
• Readings and written assignments 1 and 2
• Data-analysis assignment for units 1-8
• Monte Carlo study
• Paper presentation
• Final exam
+0.5 each Written assignments 3-8

Max 10 credits. The number of credits is rounded down.

1 John Antonakis, Nicolas Bastardoz, and Mikko Rönkkö, “On Ignoring the Random-Effects Assumption in Multilevel Models:
Review, Critique, and Recommendations,” Organizational Research Methods forthcoming (2019),
https://doi.org/10.1177/1094428119877457.
3 PARTICIPATION AND SIGNING UP
This course is targeted to students who have completed TU-L0022/JSBJ1310 Statistical
Research Methods and want to deepen their understanding of quantitative research methods.
Faculty or students from other universities are admitted if space permits.
Aalto students can sign up for the course using Oodi. Student without Aalto user account can
sign up through MyCourses using the following URL and the enrolment key ASRM2021 (in
capital letters):
https://mycourses.aalto.fi/enrol/index.php?id=33652

4 LEARNING OUTCOMES
The main goal of the course is to provide an overview of most commonly used data analysis
techniques and research designs that go beyond cross-sectional designs and simple linear models.
Instead of just explaining how the methods are used, we focus on why certain methods are used
and how and why these methods work. We will also learn to interpret methodological evidence
and go over basics of doing simulations to test or validate methods.
Completing the 6-credit base module will introduce you to the logic of structural equation
models, generalized linear models, longitudinal data analysis, missing data, advanced
measurement concepts, and endogeneity and causality.
The optional written assignments are more challenging and recommended only for those who
plan to use the methods and designs covered in these assignments in their own research.

5 WORKLOAD
TO BE ADDED2. If you want to complete all mandatory and optional assignments on the course,
you should book at least a day per week for the duration of the course.

2 Asko Karjalainen, Katariina Alha, and Suvi Jutila, Anna Aikaa Ajatella: Suomalaisten Yliopisto-Opintojen Mitoitusjärjestelmä
(Oulun yliopisto, opetuksen kehittämisyksikkö, 2007).
 Principles Study the topic Watch videos and read a book. Can be done Test in TEL environment. Immediate feedback
(factual knowledge) alone. anytime, but preferably well before the next step. (correct answers and points).
Practice Group meets to Assignments in TEL environment: conceptual TEL environment offers immediate feedback
(conceptual knowledge) practice using questions, simulations, numerical exercises, (correct answers and points; group members
the principles short problems, and reflective assignments that present in the meeting share the same points).
and concepts. support collaborative inquiry-based learning.
6 COURSE CONTENT Group can meet anytime and anywhere.
The teacher is not present.
The course consistsApply
Problems of athepre-exam, readings
concepts Solve andalone
physics problems written assignments,
or collaboratively. data TEL
After deadline, analysis
environmentassignments,
reveals correct
(procedural knowledge) in full-scale Reinforce explicit problem-solving skills. solutions. Students grade and correct their
video lectures, online interactions,Teacher
problem-solving. seminar
support sessions,
available when computer
needed. classes, a Monte
solutions based on givenCarlo project,
criteria. Teacher
and final exam. All assignments are distributed and returned
Solutions (e.g., scanned papers) are submitted
to TEL environment by a deadline.
through Aalto MyCourses
verifies corrections and gives feedback.
where
online
Primetimeinteractions also
Students take place.
and the Group meets teacher privately to discuss Teacher gives oral feedback for the group and
(metacognitive knowledge) group receive remaining problems and to reflect upon each student personally.
https://mycourses.aalto.fi/course/view.php?id=33652
personal support learning difficulties.
from the teacher.
The course is structured as ten units that are completed sequentially. Unit 1 is a preparatory unit
Units 2-8 are the main units, and Unit 10 is the course conclusion with student presentations and
have better chances to address individual needs. Although Step 3. Problems: Full-scale problem-solving
final exam.
the teacher is absent, TEL environments can adopt some After the principles are known and rehearsed under the
of the teacher’s routine work (Bell et al. 2010; Maloney guidance of TEL environment, students proceed to solve
The main units follow primetime learning model3, modified to fit the course. In the primetime
2011; Wagh et al. 2017). Precious contact time with full-scale problems, as familiar from traditional course
learning model,
teachers, as each
discussed unit
later, willhas fourindifferent
increase later stepssteps: principles,
of designs. practice,
The emphasis problems
is on proceduraland primetime
understanding,
astheshown in Figure 1. The learning model is explained
study process. duringrealistic,
on analyzing the first seminar but
context-rich participants
problems, and on
Principles and practices can also repeat twice before
are encouraged to read the article by Koskinen and coauthors to familiarize themselves withmay
applying the concepts in realistic settings. Problems the
proceeding to the following steps. Such an arrangement be adopted from textbooks, but they should explicitly
model.
helps to balance study load and to lessen the amount of teach problem-solving skills and go beyond mere symbol
material
Figure per session. learning (Koskinen et al, 2018)
1 Primetime manipulation. The problems can also be based on the

Fig. 2 Primetime learning model with the four-step study process: principles, practice, problems, and primetime. Formative assessment underlies the
entire process and motivates students to perform activities that also directly affect the grade. This drawing is a succinct summary of the primetime
model (drawing courtesy of Linda Saukko-Rauta)

Principles is the first step of a unit. During this step, the students receive a set of readings and
video materials that they study independently. Written assignments are also completed and
returned individually during this step.
After the students have studied the principles individually, we discuss them as a whole class.
These discussions start on the course forum where possible questions and thoughts that the
material raises are discussed. Thereafter, we will meet for a seminar for further discussions.
For the practice and problems steps the students are assigned into groups. Each group can decide
on their own work practices and schedules, but share the same deadline for submitting the data
analysis assignment.
Practice is when work on the data analysis assignment starts. The students should work on the
assignment alone and complete those parts that they can. The assignments are challenging and it

3 Pekka Koskinen et al., “Primetime Learning: Collaborative and Technology-Enhanced Studying with Genuine Teacher
Presence,” International Journal of STEM Education 5, no. 1 (December 2018), https://doi.org/10.1186/s40594-018-0113-8.
is not expected that students can complete them alone within a reasonable time. The purpose of
this step is to gain experience on the use of statistical software and looking for information and
solutions to problems online – both essential skills for an advanced quantitative researcher. The
course forum can be used for general questions (e.g. which multilevel package for R is the best)
but troubleshooting of problems should be done in the next step.
Problems step follows the practice step. In this step, the students meet with their groups,
compare their answers to the data analysis assignment and try to solve problems that they had
together. There is no traditional computer class but the teacher is available through
WhatsApp/Signal hotline and guidance can be arranged over Zoom as needed. After working on
the assignment together, the students prepare one submission and everyone in the group receives
the same grade. The purpose of this part is to provide peer support and learn how to solve data
analysis problems as a research team. More advanced students should also gain experience in
instructing others, which is a useful skill to have when you move to a position where you need to
instruct and supervise junior researchers such as doctoral students.
Primetime takes place after the group has submitted all the work. After viewing the model
answers, each group schedules a Zoom meeting with the teacher to discuss their work and the
challenges that they faced during the unit.
Detailed descriptions of the elements of the course are listed below:

6.1 Pre-exam (mandatory)

The pre-exam is a written exam that you must pass to be able to participate and get credits. The
exam materials are
Singleton, R., & Straits, B. C. (2018). Approaches to social research (Sixth edition). New York:
Oxford University Press.
Wooldridge, J. M. (2013). Introductory econometrics: A modern approach (5th ed). Mason, OH:
South-Western Cengage Learning. Chapters 1-9.
Jaccard, J., & Jacoby, J. (2020). Theory construction and model-building skills: A practical
guide for social scientists (Second edition). The Guilford Press. (Ebooks at Aalto and JYU)
and either of these books depending on whether you want to use Stata or R as your main
statistical analysis software for the course:
StataCorp. (2021). Stata user’s guide. College Station, TX: Stata Press. (PDF on Stata’s website)
Wickham, H., & Grolemund, G. (2016). R for Data Science: Import, Tidy, Transform, Visualize,
and Model Data. O’Reilly Media, Inc. (Available online)
all reading materials of TU-L0021 Statistical Research Methods.
The exam consists of four questions. The first question is term definitions, in which you need to
define 8 terms from the course material. The three remaining questions are essays. The exam
questions are chosen randomly from a question pool that can be found on the course website.
Tips for studying for the exam: Wooldridge (2013) and Singleton and Straits (2018) should be
already familiar to the students from the statistical research methods course and it should be
sufficient to skim through these books to remember what they were about. Jaccard and Jacoby
(2020) is new should be read in more detail focusing on Chapters 1-7, 13-17. The selected book
about statistical software should be read cover to cover. After you have familiarized yourself
with the materials, you should open the question pool on the course website and start going
through the term definitions. When you see a term that you do not know how to define, you
should seek the definition from the books. After this, you should do the same for the essay
questions. If you have a clear idea on how you would answer a question, you can skip it and
move on. If not, you should consult the books and perhaps write down a few bullet points of how
you would answer the question.

6.2 Readings and written assignments (2 mandatory, 6 optional)

The written assignments consist of reading methodological literature and empirical papers and
then doing an assignment where you apply the methodological ideas that you just studied to
analyze the empirical papers. You will be provided individual feedback on the written
assignments and these are discussed in both the online and in-person interactions.
Two written assignments 2 are. All returned written assignment should follow the American
Psychological Association (APA) Publication Manual style for article manuscripts. All work will
be checked for plagiarism using the TurnItIn service and will be returned to the students for
revising if plagiarism problems are found.

6.3 Data-analysis assignments (8 mandatory)

Because the course is focused on doing quantitative analysis effectively, all data analysis
assignments are mandatory. Each assignment contains three parts, tools, analyses, and challenge.
The work on the assignment follows the primetime learning model, where students first work on
the assignments individually and then go through their work and submit it as a group.
The tools part introduces you to general concepts such as reproducibility, programming your
statistical software, data management, and visualization. Reproducibility refers to the being able
to reproduce the exact analysis results presented in an article from the original raw data.
Reproducibility can be compromised by poor data-analysis practices as well as by manual
transferring of results from the statistical software to the research article.
Data management is an important skill of a quantitative researcher for two reasons. First, the raw
data are typically in a different format than what the final analysis requires and thus some
preparations are required before the actual analysis can even start. Second, the data preparation
step is error prone and therefore it is important to know how to do data preparation in a
transparent and reproducible way so that possible data preparation errors can be identified.
Reproducibility can be increased by structuring all analyses as well-documented analysis files
and by using the statistical software to produce the final tables shown in articles.
Data visualization is another important skill of a quantitative researcher. While good statistical
software provides you with useful visualization tools (e.g. margins and marginsplot in Stata),
there are scenarios where these tools are not applicable. For example, if you want to do a
marginal effect or marginal prediction plot based on a latent variable model or a multilevel
model, the built-in commands are often inadequate. Moreover, sometimes the impact of the
different options and what they mean for the graphics may be difficult to evaluate.
The analyses part contains a series of short data-analysis tasks where the students apply the
techniques discussed in the unit to either real or simulated dataset and interpret the results.
The challenge part contains one or two more challenging questions from the question pool of
the final exam and can be useful for evaluating one’s level of skill at various stages of the course.
Assignments can be done with either Stata or R. Some assignments can be also be completed
partly with Mplus. Each assignment requires the submission of one or more files. The first file is
commented analysis file (R file or Stata do file) that implements the analyses and a report that is
produced using the reproducibility techniques taught on the course and also shows the analysis
results and the required interpretations. In addition to the main analysis files, some assignments
might require the submission of additional files such as Word and Excel documents.
All submissions receive verbal feedback during the primetime session.
6.4 Monte Carlo assignment (mandatory)
A Monte Carlo study is a study where repeated samples are generated from a known population
which are then each analyzed with a technique being studied. This kind of studies are the most
common form of evidence presented to support new data analysis techniques, but they are also
useful for applied researchers, because a simple Monte Carlo can sometimes be enough to
convince your readers and reviewers of the soundness of your empirics (e.g. a power analysis in
the case of small-sample research). Simulations can also be useful when trying to learn a new
analysis technique.
In the Monte Carlo assignment, the task is to pick a rule of thumb or a guideline and present
evidence either supporting or refuting the rule. Examples of rules that you might study are:
• Variance inflation factor (VIF) should be less than ten to ensure that the estimates are
interpretable.
• Control variables that are uncorrelated with the dependent variable should be left out
from a regression model4.
• Approximate fit indices indicating RMSEA < .06 and CFI > .95 indicate a good fitting
model that can be causally interpreted.
• Regression analysis requires the error term to be normally distributed.
• Common method variance will always inflate regression estimates.
• Measurement error will always attenuate regression estimates.
The Monte Carlo studies are reported as short presentations (15 minutes) that are given in the
last seminar session by the students. The grading is based on presentation and the submitted
analysis file that implements the simulation.
The purpose of this assignment is to familiarize the students with the programming features of
their statistical software and to learn how methodological evidence is generated and interpreted.

6.5 Presentation of a methodological paper (mandatory)

In this assignment, the students pick an article published in Organizational Research Methods
during the last three years. The article should be chosen based on how useful or thought
provoking you found the article to be. The articles that are discussed in detail on the course
cannot be picked. Read through the article and prepare a 15-minute presentation of the article
that you will give to the other students during the last seminar.
The purpose of this assignment is to familiarize you with the kind of research that
Organizational Research Methods publishes and how articles presented in this journal should be
read and interpreted. This is useful if you want to keep yourself up to date with the latest
developments in research methods that are applied in management research.

6.6 Video lectures (mandatory and optional)

The course follows a flipped classroom design and the lectures are delivered as videos that
students watch on their own before online and in-person meetings with the instructor.
Each of the videos is assigned to a unit and the completion of watching the videos is tracked so
that a student can complete a unit only if they have watched all mandatory videos for that unit.
Some videos may contain interactive content (e.g. quizzes) that must be completed successfully
to complete the video.

4 e.g., Herman Aguinis and Robert J. Vandenberg, “An Ounce of Prevention Is Worth a Pound of Cure: Improving Research
Quality Before Data Collection,” Annual Review of Organizational Psychology and Organizational Behavior 1, no. 1 (2014):
574, https://doi.org/10.1146/annurev-orgpsych-031413-091231.
6.7 Online interactions (mandatory)
Each unit contains mandatory online participation in the form of course forum discussion. At the
beginning of each unit, the students are assigned the materials for that unit including readings,
assignments, and video content. After a few days of familiarizing with the content, students are
expected to post a question or a comment about the materials on the course forum. These
questions and comments are then discussed online with the course instructor. To pass an online
interaction session, a student must either start at least one discussion thread by posting a question
or comment or reply to at least one thread started by someone else. Participation is graded.
Detailed instructions for how to participate online are delivered by email when the course forums
open.

6.8 Seminar sessions (mandatory)

Each unit except the first one has a Zoom seminar. These seminars follow a flipped classroom
design. Each seminar starts with an overview of the lecture materials that the students have
viewed as videos in advance, but the focus is more on discussion and classroom assignments.
The final seminar session includes student presentations of their Monte Carlo projects and
chosen articles.

6.9 Final exam (mandatory)

The course concludes with a final exam. The exam is done using either Stata and R and the
answers are submitted as a report similar to the assignment reports. The exam will require the
students to carry out and interpret analyses on datasets given by the instructor, troubleshooting
problematic analyses, finding problems in analyses and research designs reported by others, and
so on. The exam is an open book exam and the students can use their notes, written material, and
internet, but they may not communicate with each other or anyone else over the internet.
The exam time is 4 hours.

7 UNITS AND SCHEDULE

The course consists of ten units. Each unit starts with a self-study of the materials, followed by
online interactions where the materials are discussed on the course forum, a seminar, and group
work on the assignment concluding with the primetime session.
Because of the pandemic, the course will be implemented fully online. If the pandemic situation
allows, the course has also an alternative schedule prepared for in-person seminars.
Date Time Location Topic
Unit 1: Course introduction and pre-exam
Weeks 36-38
6.9. 8:00 Online Course forum for unit 1 opens. The task is to write a forum
post where you introduce yourself to others on the course.
6.9.- Exam Course pre-exam
5.10 system
Unit 2: Causality, endogeneity, and natural experiments
Weeks 39-41
27.9. 8:00 Online Course forum for unit 2 opens.
4.10. 24:00 Online Deadline for written assignment 1 (mandatory)
6.10. 9:15-12 Online Unit 2 seminar
17.10. 24:00 Online Deadline for data-analysis assignment 1
Unit 3: Structural equation modeling, mediation, and instrumental variables
Weeks 42-44
18.10. 8:00 Online Course forum for unit 3 opens.
25.10. 24:00 Online Deadline for written assignment 2 (mandatory)
27.10. 9:15-12 Online Unit 3 seminar
7.11. 24:00 Online Deadline for data-analysis assignment 2
Unit 4: Moderation, transformations, and generalized linear models
Weeks 45-47
8.11. 8:00 Online Course forum for unit 4 opens.
15.11. 24:00 Online Deadline for written assignment 3 (optional)
17.11. 9:15-12 Online Unit 4 seminar
28.11. 24:00 Online Deadline for data-analysis assignment 3
Unit 5: Structural equation modeling with latent variables
Week 48-50
29.11. 8:00 Online Course forum for unit 5 opens.
6.12. 24:00 Online Deadline for written assignment 4 (optional)
8.12. 9:15-12 Online Unit 5 seminar
19.12. 24:00 Online Deadline for data-analysis assignment 4
Unit 6: Measurement and measurement validation
Week 2-4
10.1. 8:00 Online Course forum for unit 6 opens.
17.1 24:00 Online Deadline for written assignment 5 (optional)
19.1. 9:15-12 Online Unit 6 seminar
30.1. 24:00 Online Deadline for data-analysis assignment 5
Unit 7: Multilevel models
Weeks 6-8
7.2. 8:00 Online Course forum for unit 7 opens.
14.2. 24:00 Online Deadline for written assignment 6 (optional)
16.2. 9:15-12 Online Unit 7 seminar
27.2. 24:00 Online Deadline for data-analysis assignment 6
Unit 8: Longitudinal analysis and multilevel SEM
Weeks 10-12
7.3. 8:00 Online Course forum for unit 8 opens.
14.3. 24:00 Online Deadline for written assignment 7 (optional)
16.3. 9:15-12 Online Unit 8 seminar
27.3. 24:00 Online Deadline for data-analysis assignment 7
 Unit 9: Sampling, sample selection, and missing data
Weeks 14-16
4.4. 8:00 Online Course forum for unit 9 opens.
11.4. 24:00 Online Deadline for written assignment 8 (optional)
13.4. 9:15-12 Online Unit 9 seminar
24.4. 24:00 Online Deadline for data-analysis assignment 8
Unit 10: Student presentations and course conclusion
Weeks 17-19
2.5. 24:00 Online Deadline for Monte Carlo assignment
4.5. 9:15-17 Online Unit 10 seminar with student presentations
Final exam
Week 22
TBA TBA Aalto Final exam
TBA TBA JYU
The detailed description of the ten units follows.

7.1 Unit 1: Course introduction

The purpose of this unit is to introduce the students to the work practices on the course. The
students may not be familiar with working on a blended learning / online course or the primetime
learning model, and this first unit will introduce the course tools (MyCourses/Moodle, Zotero,
TurnItIn, Zoom) and work practices.
The unit concludes with the course pre-exam.

7.2 Unit 2: Causality, endogeneity, and natural experiments

Research designs and techniques:
The unit discusses assumptions and principles behind making causal claims. We briefly cover
different philosophical approaches for causation after which we focus on the counterfactual
model. The average causal (treatment) effect is contrasted with other possible ways to define
causal effects.
We also cover natural experimental designs for making causal claims. Difference-in-differences,
propensity score matching, and regression discontinuity models are introduced as statistical tools
for causal analysis.
The concept of endogeneity and why it presents a dilemma is discussed. We discuss the use of
instrumental variables to address endogeneity and the instrument relevance and exclusion
criterions.
Computer tools:
Besides the analysis techniques presented during this unit, the computer assignment addresses
random number generation and reproducibility. Generating random numbers is a useful skill
because it allows one to generate datasets from known populations and then test if a particular
analysis technique can recover the correct population values. This is useful for example when
you are learning new analysis techniques or are troubleshooting existing analyses (e.g. checking
for model identification).
This unit introduces Markdown and StatTag5 to automate linking analysis results to research
reports as well as how to export results in CSV or Excel format so that they can be copy-pasted
to research reports as full tables.
Readings:
Hitchcock, C. (2010). Causation. In S. Psillos & M. Curd (Eds.), The Routledge companion to
philosophy of science (1. publ. in paperback, pp. 317–326). London: Routledge.
Morgan, S. L., & Winship, C. (2007). Counterfactuals and causal inference methods and
principles for social research. Leiden: Cambridge University Press. (Chapters 1-2)
Wooldridge, J. M. (2013). Introductory econometrics: a modern approach (5th ed.). Mason, OH:
South Western, Cengage Learning. (Chapter, 15)
Athey, S., & Imbens, G. W. (2017). The state of applied econometrics: Causality and policy
evaluation. Journal of Economic Perspectives, 31(2), 3–32.
Ketokivi, M., & McIntosh, C. N. (2017). Addressing the endogeneity dilemma in operations
management research: Theoretical, empirical, and pragmatic considerations. Journal of
Operations Management, 52, 1–14. https://doi.org/10.1016/j.jom.2017.05.001
Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A
review and recommendations. The Leadership Quarterly, 21(6), 1086-1120.
doi:10.1016/j.leaqua.2010.10.010
Lonati, S., Quiroga, B. F., Zehnder, C., & Antonakis, J. (2018). On doing relevant and rigorous
experiments: Review and recommendations. Journal of Operations Management, 64, 19–
40. https://doi.org/10.1016/j.jom.2018.10.003
Empirical examples:
Mochon, D., Johnson, K., Schwartz, J., & Ariely, D. (2017). What Are Likes Worth? A
Facebook Page Field Experiment. Journal of Marketing Research (JMR), 54(2), 306–317.
Cuddy, A. J. C., Wilmuth, C. A., Yap, A. J., & Carney, D. R. (2015). Preparatory power posing
affects nonverbal presence and job interview performance. Journal of Applied Psychology,
100(4), 1286–1295. https://doi.org/10.1037/a0038543
Optional readings:
Deaton, A., & Cartwright, N. (2018). Understanding and misunderstanding randomized
controlled trials. Social Science & Medicine, 210, 2–
21. https://doi.org/10.1016/j.socscimed.2017.12.005
Sieweke, J., & Santoni, S. (2019). Natural experiments in leadership research: An introduction,
review, and guidelines. The Leadership Quarterly, 101338.
https://doi.org/10.1016/j.leaqua.2019.101338
Singleton, R., & Straits, B. C. (2018). Approaches to social research (Sixth edition). Oxford
University Press. Chapter 8

7.3 Unit 3: Structural equation modeling, mediation, and instrumental variables

Research designs and techniques:
This unit explains the basic principles of structural equation modeling with observed variables
for independent observations (e.g. a cross-sectional study). We discuss identification, estimation,
interpretation, and diagnostics. The focus will be on maximum likelihood (ML) estimation.

5 Leah J Welty et al., StatTag (Chicago, IL: Galter Health Science Library, 2016), https://doi.org/10.18131/G36K76.
Mediation is introduced in more detail including estimation of models with endogenous
mediators.
We discuss further instrumental variable techniques including estimation of instrumental
variable models with ML SEM, generalized method of moments (GMM), and two-stage least
squares. Tests for endogeneity, weak instruments, and instrument exclusion are introduced as is
the concept of plausible exogeneity.
Computer tools:
This unit introduces two new tools: matrix algebra and numerical optimization. Understanding
the basics of matrix algebra is useful for two reasons. First, many texts on quantitative methods
that go beyond introductory level use matrix notation if not in full then at least in part. If you
understand how to read matrix equations and what these equations mean, this will make it easier
to study these sources. Second, if you are generating datasets yourself, doing that with matrix
equations instead of writing a separate (scalar) equation for each variable is much more
straightforward. The introduction covers the topics of matrix sums, matrix multiplication,
inverse, and determinant.
Every statistical model addressed on the course is estimated by minimizing and objective
function. While some techniques, such as least-squares regression, has a closed from solution
which can be simply calculated by applying algebra to the data, most other techniques do not. In
these cases, the estimates are obtained by numerically minimizing or maximizing the objective
function. This unit covers the basics of numerical optimization and how gradient vector and
Hessian matrix are used in this process and can be used for troubleshooting non-convergent
models.
Readings:
Kline, R. B. (2011). Principles and practice of structural equation modeling (3rd ed.). New York,
NY: Guilford Press. (Chapters 1, 5-8, 153 pages)
Lu, G., Ding, X. (David), Peng, D. X., & Hao-Chun Chuang, H. (2018). Addressing endogeneity
in operations management research: Recent developments, common problems, and directions for
future research. Journal of Operations Management. https://doi.org/10.1016/j.jom.2018.10.001
Empirical examples:
Bergh, D. D., Aguinis, H., Heavey, C., Ketchen, D. J., Boyd, B. K., Su, P., … Joo, H. (2016).
Using meta-analytic structural equation modeling to advance strategic management research:
Guidelines and an empirical illustration via the strategic leadership-performance
relationship. Strategic Management Journal, 37(3), 477–497. https://doi.org/10.1002/smj.2338
Hekman, D. R., Aquino, K., Owens, B. P., Mitchell, T. R., Schilpzand, P., & Leavitt, K. (2010).
An Examination of Whether and How Racial and Gender Biases Influence Customer
Satisfaction. Academy of Management Journal, 53(2), 238–
264. https://doi.org/10.5465/AMJ.2010.49388763
Eshima, Y., & Anderson, B. S. (2017). Firm growth, adaptive capability, and entrepreneurial
orientation. Strategic Management Journal, 38(3), 770–779. https://doi.org/10.1002/smj.2532
Optional readings:
Cortina, J. M., Green, J. P., Keeler, K. R., & Vandenberg, R. J. (2017). Degrees of Freedom in
SEM: Are We Testing the Models That We Claim to Test? Organizational Research
Methods, 20(3), 350–378. https://doi.org/10.1177/1094428116676345
Kline, R. B. (2015). The mediation myth. Basic and Applied Social Psychology, 37(4), 202–
213. https://doi.org/10.1080/01973533.2015.1049349
Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A
review and recommendations. The Leadership Quarterly, 21(6), 1086-1120.
doi:10.1016/j.leaqua.2010.10.010
Ketokivi, M., & McIntosh, C. N. (2017). Addressing the endogeneity dilemma in operations
management research: Theoretical, empirical, and pragmatic considerations. Journal of
Operations Management, 52, 1–14. https://doi.org/10.1016/j.jom.2017.05.001

7.4 Unit 4: Moderation, transformations, and generalized linear models

Research designs and techniques:
We discuss the use of linear regression to estimate moderation models and how transformations
can be used for modeling non-linear effects.
The unit introduced the generalized linear model, which is an extension to linear regression
covering most commonly used single dependent variable models as special cases (e.g. logistic
regression, Poisson regression, tobit regression, etc.). Maximum likelihood estimation of these
models is introduced.
We will focus on the choice of non-linear model as well as their graphical interpretation and
common non-graphical interpretations including their misuses.
Computer tools:
The computer tools covered in this unit are about visualization. We will focus particularly on
two-way plots and their application for calculating marginal prediction and marginal effects
plots. These plots are produced by both the built-in plots (e.g. margins in Stata) as well as
without these tools by using generic graphing functions.
Readings:
Wooldridge, J. M. (2013). Introductory econometrics: a modern approach (5th ed.). Mason, OH:
South Western, Cengage Learning. (Chapters 6-8, 17)
Dawson, J. F. (2014). Moderation in management research: What, why, when, and how. Journal
of Business and Psychology, 29(1), 1–19. https://doi.org/10.1007/s10869-013-9308-7
Rönkkö, M., Aalto, E., Tenhunen, H., & Aguirre-Urreta, M. I. (2021). Eight simple guidelines
for improved understanding of transformations and nonlinear effects. Organizational Research
Methods, 1094428121991907. https://doi.org/10.1177/1094428121991907
Empirical examples:
Hekman, D. R., Aquino, K., Owens, B. P., Mitchell, T. R., Schilpzand, P., & Leavitt, K. (2010).
An Examination of Whether and How Racial and Gender Biases Influence Customer
Satisfaction. Academy of Management Journal, 53(2), 238-264.
doi:10.5465/AMJ.2010.49388763
Antonakis, J., Bastardoz, N., Liu, Y., & Schriesheim, C. A. (2014). What makes articles highly
cited? The Leadership Quarterly, 25(1), 152–179. https://doi.org/10.1016/j.leaqua.2013.10.014

7.5 Unit 5: Structural equation modeling with latent variables

Research designs and techniques:
The unit introduces students to structural equation models with both latent and observed
variables for cross-sectional designs. Structural equation models are a basic tool in the course
and many of the techniques covered can be considered as special cases of this general modeling
framework.
Different techniques for analyzing latent interactions are presented. Estimation techniques other
than ML are introduced (MIIV, WLS).
Various diagnostics and model fit indices are discussed.
Computer tools:
This unit introduces loops, which allow automating repetitive tasks in statistical software. Loops
are used for example to construct and export tables of model fit indices. Such tables are not
available for export directly from the software that we use, but must be constructed manually.
We also continue practicing matrix calculations and troubleshoot problematic models by
inspecting the output of numerical optimization routines of statistical software.
Readings:
Kline, R. B. (2011). Principles and practice of structural equation modeling (3rd ed.). New
York, NY: Guilford Press. (Chapter 5-9, 10, 12)
Ropovik, I. (2015). A cautionary note on testing latent variable models. Frontiers in Psychology,
6. https://doi.org/10.3389/fpsyg.2015.01715
Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A
review and recommendations. The Leadership Quarterly, 21(6), 1086–1120.
doi:10.1016/j.leaqua.2010.10.010
Empirical examples:
Mesquita, L. F., & Lazzarini, S. G. (2008). Horizontal and Vertical Relationships in Developing
Economies: Implications for Smes’ Access to Global Markets. Academy of Management
Journal, 51(2), 359–380.
Yli-Renko, H., Autio, E., & Sapienza, H. J. (2001). Social capital, knowledge acquisition, and
knowledge exploitation in young technology-based firms. Strategic Management Journal, 22(6-
7), 587–613. doi:10.1002/smj.183

7.6 Unit 6: Measurement and measurement validation

Research designs and techniques:
Measurement related problems, particularly in studies where data are collected with surveys, are
some of the most common reasons for rejecting manuscripts from publication. In this unit we
will address issues related to reliability, validity, and measurement modeling.
A fairly typical way of addressing reliability in empirical research is to first calculate
“Cronbach’s alphas” that are then compared against fixed 0.70 cutoff. If all alphas exceed 0.70,
reliability is declared acceptable and then ignored for the remainder of the article. This practice
is problematic for two main reasons: alpha is rarely the best reliability index and reliability
assessment is not a yes or no decision. We will discuss different reliability indices and their
assumptions and how reliability statistics and the effect of unreliability can be interpreted and
quantified beyond using fixed benchmarks. The concept of bi-factor model is introduced to
support the discussion.
The concept of validity is more challenging. We will discuss a couple of different measurement
theories and how these relate to current (psychometric) modeling practices. The problematic
concepts of formative measurement and multidimensional constructs are discussed.
Common method variance is another issue that is often raised during the review process of
survey-based research. We will discuss the different potential causes of this phenomenon, what
different statistical approaches are available to detect and possibly control for method variance,
and why most of these techniques are actually inadequate for the task.
Finally, we will also discuss what to do when a structural equation model does not fit or fails to
converge. Exploratory structural equation models and Bayesian structural equation models are
introduced as possible solutions for relaxing the strict covariance implications of traditional
linear structural equation models.
Computer tools:
This unit discusses programming and data management. We discuss how data can be merged and
reshaped and how repetitive tasks can be automated with programs (Stata) and functions (R).
Readings:
DeVellis, R. F. (2017). Scale development theory and applications (4th ed.). Thousand Oaks:
Sage. (Chapters 1-4, 6-7)
Borsboom, D., Mellenbergh, G. J., & van Heerden, J. (2004). The concept of
validity. Psychological Review, 111(4), 1061.
Kline, R. B. (2011). Principles and practice of structural equation modeling (3rd ed.). New
York, NY: Guilford Press. (Chapter 8)
McNeish, D. (2017). Thanks Coefficient Alpha, We’ll Take It From Here. Psychological
Methods. https://doi.org/10.1037/met0000144
Rönkkö, M., & Cho, E. (2019). Discriminant validity: A synthesis of definitions and a test of
techniques. Organizational Research Methods.
Podsakoff, P. M., MacKenzie, S. B., & Podsakoff, N. P. (2012). Sources of Method Bias in
Social Science Research and Recommendations on How to Control It. Annual Review of
Psychology, 63(1), 539–569. https://doi.org/10.1146/annurev-psych-120710-100452
Empirical examples:
Kohtamäki, M., Kraus, S., Mäkelä, M., & Rönkkö, M. (2012). The role of personnel
commitment to strategy implementation and organisational learning within the relationship
between strategic planning and company performance. International Journal of Entrepreneurial
Behavior & Research, 18(2), 159–178. https://doi.org/10.1108/13552551211204201

7.7 Unit 7: Multilevel models

Research designs and techniques:
Independence of observations is one of the key assumptions of linear regression. However, this
assumption is violated when working with longitudinal or clustered data (i.e. members in teams)
because of unobserved heterogeneity. We start by introducing the concepts of nested and crossed
clustering, the between, within, and contextual effects, and the concepts of random and fixed
effects.
The data-analysis techniques covered include GLS random and fixed effects estimators and the
Mundlak/correlated random effect/hybrid approach from the econometrics tradition for analyzing
these types of data and mixed/random/multilevel models from the modeling tradition.
Generalized estimation equations and cluster robust standard errors are presented as an
alternative to these techniques. Additionally, we discuss the use of cluster means or cluster mean
centering for estimating effects on different levels. Different empirical approaches for model
choice (Hausman test and different nested model tests) are presented. The data analysis
techniques conclude with models for cross-level interactions and generalized mixed models.
Finally, we will also discuss what to do when a multilevel model fails to converge.
Computer tools:
This unit will teach the students how to run Monte Carlo simulations how to summarize the
Monte Carlo results as tables and figures.
Readings:
Luke, D. A. (2004). Multilevel Modeling. Sage. (Chapters 1, 2)
Wooldridge, J. M. (2013). Introductory econometrics: A modern approach (5th ed). South-
Western Cengage Learning. (Chapters 9.2, 13, 14)
McNeish, D., Stapleton, L. M., & Silverman, R. D. (2017). On the unnecessary ubiquity of
hierarchical linear modeling. Psychological Methods, 22(1), 114–
140. https://doi.org/10.1037/met0000078
Antonakis, J., Bastardoz, N., & Rönkkö, M. (2019). On ignoring the random effects assumption
in multilevel models: Review, critique, and recommendations. Organizational Research
Methods, 1094428119877457. https://doi.org/10.1177/1094428119877457
Empirical examples:
Holcomb, T. R., Combs, J. G., Sirmon, D. G., & Sexton, J. (2010). Modeling Levels and Time in
Entrepreneurship Research An Illustration With Growth Strategies and Post-IPO
Performance. Organizational Research Methods,13(2), 348–389.
doi:10.1177/1094428109338401
Hausknecht, J. P., Hiller, N. J., & Vance, R. J. (2008). Work-Unit Absenteeism: Effects of
Satisfaction, Commitment, Labor Market Conditions, and Time. Academy of Management
Journal, 51(6), 1223–1245. doi:10.5465/AMJ.2008.35733022
Deephouse, D. L. (1999). To be different, or to be the same? It’s a question (and theory) of
strategic balance. Strategic Management Journal, 20(2), 147–166.
Mochon, D., Johnson, K., Schwartz, J., & Ariely, D. (2017). What Are Likes Worth? A
Facebook Page Field Experiment. Journal of Marketing Research (JMR), 54(2), 306–317.
Optional readings:
McNeish, D., Stapleton, L. M., & Silverman, R. D. (2016). On the Unnecessary Ubiquity of
Hierarchical Linear Modeling. Psychological Methods. http://dx.doi.org/10.1037/met0000078
Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A
review and recommendations. The Leadership Quarterly, 21(6), 1086–1120.
doi:10.1016/j.leaqua.2010.10.010
Ketokivi (2019) Avoiding Bias and Fallacy in Survey Research: A Behavioral Multilevel
Approach. Journal of Operations Management
Bou, J. C., & Satorra, A. (2017). Univariate Versus Multivariate Modeling of Panel Data: Model
Specification and Goodness-of-Fit Testing. Organizational Research Methods,
109442811771550. https://doi.org/10.1177/1094428117715509
Bliese, P. D., & Ployhart, R. E. (2002). Growth Modeling Using Random Coefficient Models:
Model Building, Testing, and Illustrations. Organizational Research Methods, 5(4), 362–387.
https://doi.org/10.1177/109442802237116
Aguinis, H., Gottfredson, R. K., & Culpepper, S. A. (2013). Best-Practice Recommendations for
Estimating Cross-Level Interaction Effects Using Multilevel Modeling. Journal of Management,
39(6), 1490–1528. https://doi.org/10.1177/0149206313478188

7.8 Unit 8: Longitudinal analysis and multilevel SEMs

Research designs and techniques:
Longitudinal analysis can refer to either studying the effects of time on the dependent variable or
studying the effect of the dependent variable itself on its future values. This unit introduces the
concepts of lagged dependent variables, and the choice of lags more generally, autocorrelation,
dynamic panel models, and endogeneity in panel models.
The econometrics techniques cover the use of instrumental variables to address the endogeneity
issue in dynamic panels, particularly by using the Arellano-Bond approach. Longitudinal
analysis with structural equation models are covered using the latent growth model, cross-lagged
model and its variants, and latent change score models.
Stata’s generalized structural equation modeling and other approaches to multilevel structural
equation modeling, including the MUML and WLSMV estimators as implemented in Mplus and
Lavaan are presented. Longitudinal latent class analysis is introduced briefly.
Computer tools:
Besides the analysis techniques discussed in this unit, there will be no new computer tools. The
students will have an opportunity to ask questions and get guidance on their Monte Carlo
projects.
Readings:
Bliese, P. D., & Ployhart, R. E. (2002). Growth Modeling Using Random Coefficient Models:
Model Building, Testing, and Illustrations. Organizational Research Methods, 5(4), 362–387.
https://doi.org/10.1177/109442802237116
Ketokivi (2019) Avoiding Bias and Fallacy in Survey Research: A Behavioral Multilevel
Approach. Journal of Operations Management
Antonakis, J., Bastardoz, N., & Rönkkö, M. (2019). On ignoring the random-effects assumption
in multilevel models: Review, critique, and recommendations. Organizational Research
Methods, forthcoming.
Bou, J. C., & Satorra, A. (2017). Univariate Versus Multivariate Modeling of Panel Data: Model
Specification and Goodness-of-Fit Testing. Organizational Research Methods,
109442811771550. https://doi.org/10.1177/1094428117715509
Aguinis, H., Gottfredson, R. K., & Culpepper, S. A. (2013). Best-Practice Recommendations for
Estimating Cross-Level Interaction Effects Using Multilevel Modeling. Journal of Management,
39(6), 1490–1528. https://doi.org/10.1177/0149206313478188
Little, T. D. (Ed.). (2013). The Oxford handbook of quantitative methods (Vol. 2). New York:
Oxford University Press. (Chapter 18)
Hamaker, E. L., Kuiper, R. M., & Grasman, R. P. (2015). A critique of the cross-lagged panel
model. Psychological Methods, 20(1), 102–116.’
Kline, R. B. (2011). Principles and practice of structural equation modeling (3rd ed.). New
York, NY: Guilford Press. (Chapter 11)
Ployhart, R. E., & Vandenberg, R. J. (2010). Longitudinal Research: The Theory, Design, and
Analysis of Change. Journal of Management, 36(1), 94–120.
https://doi.org/10.1177/0149206309352110’
Wooldridge, J. M. (2013). Introductory econometrics: a modern approach (5th ed.). Mason, OH:
South Western, Cengage Learning. (Chapters 13.2)
Wu, W., Selig, J. P., & Little, T. D. (2013). Longitudinal data analysis. In T. D. Little (Ed.), The
Oxford handbook of quantitative methods (Vol. 2, pp. 387–410). Oxford University Press.
Empirical example:
Meier, L. L., & Spector, P. E. (2013). Reciprocal effects of work stressors and counterproductive
work behavior: A five-wave longitudinal study. Journal of Applied Psychology, 98(3), 529-539.

7.9 Unit 9: Sampling, sample selection, and missing data

Research designs and techniques:
Missing data refers to a phenomenon where part of the data that would be ideally be available for
an analysis is in fact not available. Sample selection is a special case of missing data where the
missingness depends systematically on the studied phenomenon. A classic example is a study of
how strongly women’s income depend on their level of education. Studying this effect is
challenging because some women choose to not work and stay at home with the children and this
decision depends on the income that they would receive from the job markets.
This unit starts by introducing the three different missing data mechanisms, missing completely
at random (MCAR), missing at random (MAR), and missing not at random (MNAR) and
different missing data patterns. After this, we will discuss when and why missing data could
become a problem and how a potential missing data or sample selection issue can be diagnosed.
Multiple imputation and maximum likelihood estimation with missing data (FIML) are presented
as solutions to the MCAR and MAR scenarios. Selection models, including the widely used
Heckman model, are presented as a potential solution to MCAR scenarios, focusing particularly
on the assumptions that these techniques make and the fact that sometimes these assumptions
may be more untenable than the MAR assumption.
Finally, we will discuss endogenous selection where data are not missing, but where a selection
into a group depends on the dependent variable. For example, companies do not makes a
decision randomly but based on the company’s expected returns from that decision.
Computer tools:
Besides the analysis techniques discussed in this unit, there will be no new computer tools. The
students will have an opportunity to ask questions and get guidance on their Monte Carlo
projects.
Readings:
Wooldridge, J. M. (2013). Introductory econometrics: a modern approach (5th ed.). Mason, OH:
South Western, Cengage Learning. (Chapters 9.5, 17.1, 17.4, 17.5)
Baraldi, A. N., & Enders, C. K. (2013). Missing data methods. In T. D. Little (Ed.), The Oxford
handbook of quantitative methods (Vol. 2, pp. 635–664). Oxford University Press.
Enders, C. K. (2010). Applied missing data analysis. New York: Guilford Publications.
(Chapters 1-4, 10)
Clougherty, J. A., Duso, T., & Muck, J. (2016). Correcting for self-selection based endogeneity
in management research: Review, recommendations and simulations. Organizational Research
Methods, 19(2), 286–347. https://doi.org/10.1177/1094428115619013
Rogelberg, S. G., & Stanton, J. M. (2007). Introduction Understanding and Dealing With
Organizational Survey Nonresponse. Organizational Research Methods, 10(2), 195–
209. https://doi.org/10.1177/1094428106294693
Newman, D. A. (2014). Missing Data Five Practical Guidelines. Organizational Research
Methods, 17(4), 372–411. https://doi.org/10.1177/1094428114548590
Certo, S. T., Busenbark, J. R., Woo, H., & Semadeni, M. (2016). Sample selection bias and
Heckman models in strategic management research. Strategic Management Journal, 37(13),
2639–2657. https://doi.org/10.1002/smj.2475
Empirical examples:
Egan, M., Daly, M., Delaney, L., Boyce, C. J., & Wood, A. M. (2017). Adolescent
conscientiousness predicts lower lifetime unemployment. Journal of Applied
Psychology, 102(4), 700–709. https://doi.org/10.1037/apl0000167
Gooderham, P., Fenton-O’Creevy, M., Croucher, R., & Brookes, M. (2018). A Multilevel
Analysis of the Use of Individual Pay-for-Performance Systems. Journal of Management, 44(4),
1479–1504. https://doi.org/10.1177/0149206315610634
Mansour, S., & Tremblay, D.-G. (2019). How can we decrease burnout and safety workaround
behaviors in health care organizations? The role of psychosocial safety climate. Personnel
Review, 48(2), 528–550. https://doi.org/10.1108/PR-07-2017-0224

7.10 Unit 10: Student presentations and course conclusion

The seminar has two sets of student presentations. Each student is required to read one recent
article from Organizational Research Methods and present that in the class. Additionally, the
students present their Monte Carlo simulations. We will also have time for general discussion on
research methods and doing research.

8 GRADING
All submitted work will be graded between 1-5 and your grade will be a weighted average of the
parts of the course that you completed.
Course part Weight Notes
Pre-exam 5
Seminar and 1 each By default, you will receive 2 for posting something on the
forum (total 9) course forum or being present at a seminar and your grade
participation will increase based on your participation
Final exam 16
Assignments 1 each 8 data analysis assignments, 8 written assignments, 1
(total 17) methodological article presentation.
Project 3 1 Monte Carlo project presentation
Total 50

9 COURSE MATERIAL
The reading materials for the course are distributed through the Zotero reference management
system. To get access to the materials:
1. Create a user account at Zotero.org
2. Email your username to the course instructor
3. The course instructor will send you an invitation to a group library, which you need to
accept.
After you have accepted the invitation, you can access the material either online with a web
browser or by installing the Zotero software on your computer. See the MyCourses page for
information.

9.1 Books
To be added.
XX pages total.

9.2 Articles
To be added.
XX pages total.
9.3 Empirical articles used as examples
To be added.
XX pages total.

10 ABOUT THE INSTRUCTOR

The course is taught by Dr. Mikko Rönkkö. He is Associate Professor of Entrepreneurship at
Jyväskylä University School of Business and Economics and Docent in Management at Aalto
University. His work focuses on the use of quantitative research methods in management and
and on growth entrepreneurship. He has published articles about quantitative research methods in
multiple journals including leading applied research methods journals, (e.g. Organizational
Research Methods, Psychological Methods), and leading field journals (e.g. Journal of
Operations Management and MIS Quarterly), and has taught quantitative research methods at
multiple universities in and outside Finland. He has served as a department editor at Journal of
Operations Management and on the editorial boards of Organizational Research Methods and
Entrepreneurship Theory and Practice.