PSYC316: Statistical Analysis II
Section: 52 (BL)
Instructor: David Grenet Ph.D
Assistant Professor
Department of Psychology
Faculty of Arts and Science
Office: PY101.02 (or by Zoom)
Office hours: by appointment
Contact: david.grenet@concordia.ca (put PSYC316 in the subject heading)
(514) 898 2424 ext. 5435 (email is preferred)
For questions about Lab assignments, contact your Teaching Assistant.
Class: Initially remote on Zoom, then room CC 321
Wednesday 6pm – 8pm, on the following dates: 12/01, 26/01, 16/02, 23/02, 16/03, 30/03, 13/04
Teaching Assistants:
5255
5257
5256
Christine Gerson
Christine Gerson
Conall Mac Cionnaith
chrissy.gerson@gmail.com
chrissy.gerson@gmail.com
conallmaccionnaith@gmail.com
Description
PSYC 316 Statistical Analysis II (3 credits).
Prerequisite: PSYC 310, 315.
This course is an extension of PSYC 315. It is designed to advance students' understanding of hypothesis
testing and statistical inferences. The course will begin with a quick recap of what you should have
learnt in PSYC 315. Note that some new concepts will be introduced (e.g., data integrity and outlier
removal) as these are required to check assumptions for using most statistical analysis. The course then
presents the general linear model, which subsumes linear regression, multiple regression, analysis of
variance (ANOVA), and linear mixed effects models. As well, the course deals in detail with the limits of
null-hypothesis significance testing (NHST) and reviews alternatives to NHST including confidence
intervals, measures of effect size, meta-analysis, and Bayesian Analysis. Due to the changing standards
in the field of Psychology, students will learn how to use state-of-the-art statistical analysis programs,
specifically JASP (https://jasp-stats.org/) and R (https://www.r-project.org/). The advantage of these
programs is that they are open source and free, and there is a growing userbase in Psychology for each.
Their use is a sought-after skill by supervisors here at Concordia and beyond, and they are becoming the
standard for the field of Psychology.
Lecture content is delivered by remote video lectures, supplemented with live classes. Live classes will
be initially on Zoom, and in person when (if) permitted by university health guidelines.
Course Materials
Due to the continuing pandemic, this course will initially be taught completely online, with live classes
commencing later in the semester dependant on Provincial and University health guidelines. Course
1
content will be delivered by video lectures that you will be able to watch from moodle. Each video is 1015 minutes and will cover a subpart of a larger topic (normally a specific type of statistical analysis). \
The scheduled lecture time will be used for a Q&A session, where students can ask specific questions
about the videos and I will emphasise important parts of the topics covered. Supporting lecture notes
will be available on the course moodle page.
Content belonging to instructors shared in online and blended courses, including, but not limited to,
online lectures, course notes, and video recordings of classes remain the intellectual property of the
faculty member. It may not be distributed, published or broadcast, in whole or in part, without the
express permission of the faculty member. Students are also forbidden to use their own means of
recording any elements of an online class or lecture without express permission of the instructor. Any
unauthorized sharing of course content may constitute a breach of the Academic Code of Conduct
and/or the Code of Rights and Responsibilities. As specified in the Policy on Intellectual Property, the
University does not claim any ownership of or interest in any student IP. All university members retain
copyright over their work.
Tips for a successful outcome to the course: Make sure to watch every video. Statistics is about building
on concepts – if you fall behind in any one concept this will make it difficult to keep up with the course.
As you watch the videos, try being an active student. Take notes, try problems, write down questions,
and ask them in the Q&A classes when you don’t quite get it. Your goal during class should be to think
actively and make connections so that the concepts make sense to you. My goal is to help you make
these connections. I teach in a format that places a strong emphasis on students demonstrating they
comprehend the theoretical and practical aspects of modern statistical analysis. I won’t be asking you to
calculate any of the statistics by hand or memorize formulae – that is what Google is for! But students
need to demonstrate their conceptual understanding of how statistics work, and most importantly, to
interpret the outcome measures of statistical tests appropriately.
Laboratory classes
Lab exercises will be posted to guide you through how to implement the analysis methods from the
course in R and JASP. These skills will be necessary to complete the four assignments. When permitted
by health guidelines, labs will resume in-person, and you will be expected to attend your scheduled
laboratory classes on campus. The Teaching Assistants will be available to answer questions, initially via
email or scheduled Zoom meeting, and in class when in-person classes resume.
Textbook and Course Materials
This course will be using open source materials for calculating statistics (JASP, R), and for teaching (open
source textbook). This is done so that all students can have access to the book without having to pay for
it. Note that if you have a textbook from PSYC315 (e.g., Rick Gurnsey’s book), then this is
complementary to the online free books, but not required. The other advantage is that both books
below are identical in their theory but show how to calculate the statistics using the two software
packages we will be using.
Learning Statistics in JASP: https://tomfaulkenberry.github.io/JASPbook/lsj.pdf
Learning Statistics in R: https://learningstatisticswithr.com/book/
Additional materials (lecture notes, guides, R code, datasets, readings, assignments) will be posted on
the class moodle site. Note that if a reading is discussed in class, you will be expected to read the article,
as this will be in the exams.
2
Assignments
The assignments will serve a critical purpose - to assess your application of the techniques necessary to
demonstrate that you can conduct appropriate statistical analysis. The course includes four homework
assignments, which aim to help you build your practical skills by transferring knowledge to real data
sets. Assignments must be the work of the individual student and fall under the normal academic
conduct rules (see below).
Exams
The midterm and final exam will be run via Moodle quizzes. These will not use the University COLE
system, and under the current situation will be open book. Each student will be presented with the
same format of exam question, but with randomized datasets – meaning each student will have a
different set of answers from each other student. This means that even if you discuss your answer with
other students (which is a violation of the academic code), it won’t help you as they will have a different
answer than yours. Students will be expected to demonstrate the theory behind statistics covered in the
course, as well be being able to read data from statistical output tables presented in the exam.
Evaluation Summary
Test
Lab assignment 1-4
Midterm
Final
Total
Value
10% per assignment (40% total)
30%
30%
100%
Accessibility and Inclusion
The University’s commitment to providing equal educational opportunities to all students includes
students with disabilities. To demonstrate full respect for the academic capacities and potential of
students with disabilities, the University seeks to remove academic, attitudinal, and physical barriers
that may hinder or prevent students with disabilities from participating fully in University life. All
students are welcome to meet with me during the first week of classes to discuss the barriers they face
and how we can work together to reduce them. In my role as professor, I strive to make the learning
experience in my class as accessible and inclusive as possible. However, if you require that an
accommodation plan be established to help reduce the barriers you face as a result of a disability
condition (including mental health conditions as well as chronic and temporary medical conditions) then
you are requested to contact the Access Centre for Students with Disabilities in a timely fashion. Please
inform me about specific accommodation needs at the start of the course.
Email: acsdinfo@concordia.ca Phone: 514-848-2424 ext. 3525.
For more information, contact: http://www.concordia.ca/students/accessibility.htm
Participant Pool Credits
One of the best ways to learn about statistics and research methods is to participate. In particular, there
are special benefits for quantification students because participation will give you a chance to see how
the concepts of this course are applied in actual research projects that are being carried out at
Concordia University. The department has a participant pool that offers credit for participation in
research being conducted in the department. You can find details about the participant pool through the
3
department’s website: https://www.concordia.ca/artsci/psychology/facilities-services/participantpool.html
Each participation credit is worth 0.5% towards your final grade. In this course you will be allowed to
earn up to 3 participation credits. This means that you can earn up to 1.5% bonus marks through
participation. Please note that participation is completely voluntary and your final grade will not be
affected if you do not participate. It is your responsibility to ensure that you correctly assign your
Participant Pool credits to the correct Course and Section. Please note that the participant pool marks
will only be available in Moodle after they are finalised for the semester (usually shortly after the final
day of classes).
Grading Scheme
A+ 94 - 100
B+ 82 – 85.9
C+ 70 – 73.9
D+ 58 - 61.9
F < 50
A 90 – 93.9
B 78 – 81.9
C 66 – 69.9
D 54 - 57.9
A- 86 – 89.9
B- 74 – 77.9
C- 62 – 65.9
D- 50 – 53.9
NOTE: THIS GRADE-SCHEME IS DIFFERENT THAN SOME COURSES, AS GRADES WILL NOT BE CURVED.
This scheme may seem odd to some but is actually a fair grading scheme. Each letter grade has an
approximately equal value.
Students cannot re-distribute the grading weight across assignments. If you are unable to complete the
course as requirements as described above, you should drop the course.
Plagiarism and Academic Conduct
Plagiarism: The most common offense under the Academic Code of Conduct is plagiarism, which the
Code defines as “the presentation of the work of another person as one’s own or without proper
acknowledgement.” This includes material copied word for word from books, journals, Internet sites,
professor’s course notes, etc. It refers to material that is paraphrased but closely resembles the original
source. It also includes for example the work of a fellow student, an answer on a quiz, data for a lab
report, a paper or assignment completed by another student. It might be a paper purchased from any
source. Plagiarism does not refer to words alone –it can refer to copying images, graphs, tables and
ideas. “Presentation” is not limited to written work. It includes oral presentations, computer
assignments and artistic works. Finally, if you translate the work of another person into any other
language and do not cite the source, this is also plagiarism.
In Simple Words: Do not copy, paraphrase or translate anything from anywhere without saying where
you obtained it.
By remaining within the course, it will be assumed that all students will have read and understood the
policies, and agree to abide by them. Any violation of the code will result in a charge being submitted to
the faculty against the student, which can result in a warning, a zero grade for the assessment or course.
Note that all submitted assignments and exams may be subject to a check for plagiarism should the
instructor deem it necessary due to suspected plagiarism or code of conduct violation.
Behaviour
All individuals participating in courses are expected to be professional and constructive throughout the
course, including in their communications.
4
Concordia students are subject to the Code of Rights and Responsibilities which applies both when
students are physically and virtually engaged in any University activity, including classes, seminars,
meetings, etc. Students engaged in University activities must respect this Code when engaging with any
members of the Concordia community, including faculty, staff, and students, whether such interactions
are verbal or in writing, face to face or online/virtual. Failing to comply with the Code may result in
charges and sanctions, as outlined in the Code.
In case of Illness or Missed Exam
Please familiarize yourself with all policies pertaining to cases of illness, missed exams, incomplete work,
etc. in the Undergraduate Calendar. Please note that there is a new form available for short-term
absences of no more than two days. This form can be used to register a short absence without providing
documentary evidence (such as a doctor’s note) under certain circumstances. However, this form
cannot be used if you are going to miss an assessment of value 30% or more of the course total (such as
the midterm exam).
There will be no makeup for a missed midterm exam, except in emergencies (documentation from the
Office of Student Affairs is required). Cases where the student missed the exam will be assessed at the
instructor’s discretion on a case-by-case basis. If permitted, the makeup exams will be given in an oral
exam format with the instructor. Missed exams, quizzes, or exams where the student fails to put their
name on the exam script will result in a zero grade. Conflicts with the scheduled final exam must be
handled through the Examinations Office.
Extraordinary Circumstances
In the event of extraordinary circumstances and pursuant to the Academic Regulations, the University
may modify the delivery, content, structure, forum, location and/or evaluation scheme. In the event of
such extraordinary circumstances, students will be informed of the changes.
Important dates
DNE deadline (withdrawal with tuition refund)
DISC deadline (withdrawal without tuition refund)
Monday, 19 January 2022
Monday, 18 April 2022
Make sure that you confirm these dates on the Concordia website:
https://concordia.ca/events/academic-dates.html
5
List of topics
•
•
Introduction to JASP and R
Recap of 315
o Data visualization
o Measures of central tendency and variance
o Distributions
o Estimating differences between means
o Limitations of estimates of the mean
o More robust methods of estimating and comparing means
o Rationale behind dependant and independent populations
o Correlations and regressions
o Inferential stats using correlations and regressions
o Significance testing (and problems with it)
o Alternatives to significance testing
o Power analysis
•
•
•
•
•
•
•
Data Screening
Multiple regression
Comparing multiple samples: the Analysis of Variance (ANOVA)
ANCOVA
Linear mixed-effects models
Bootstrap & Robust Statistics
Bayes Factor
6