Admission requirements
N/A
Description
This is a class in applied single equation ordinary least squares (OLS) regression analysis and the binary outcome logistic regression model. It will be assumed that students have mastered the topics of basic statistics, though a brief review of relevant concepts will be provided before presenting the three main topics. The first topic is a review of the single equation OLS regression model in bivariate and multivariate applications. Students will develop an understanding of the logic of OLS regression, the parameter estimates generated, and assessments of model quality. The second topic will be a thorough review of the assumptions underlying the OLS regression model. The third topic will be an introduction to the logic and use of logistic regression. In all three topics, the class emphasizes the substantive interpretation of regression results as reported in statistical software and social science research reports.
Course objectives
Students will have acquired knowledge of the logic of OLS and logistic regression and the assumptions underlying these two models.
Students will be able to interpret and report the results of OLS and logistic regression.
Students will be able to apply OLS and logistic regression to public administration research problems in tutorial assignments and a final group paper.
Students will be able to communicate the results of OLS and logistic regression in written form using the conventions used by practitioners and social scientists for reporting these results.
Timetable
On the Public Administration front page of the E-guide you will find links to the website and timetables, uSis and Brightspace.
Mode of instruction
Lectures
Workgroups (mandatory attendance)
The following rules will apply regarding mandatory workgroup attendance and assignments:
Students must attend all workgroup sessions. If one workgroup session is missed, the student must do an extra assignment. If more than one session is missed, the student will not receive a grade for the course. It is the responsibility of each student to register their attendance with the workgroup instructor.
Students must submit all workgroup assignments and the tutorial assignments on time. If one such assignment is submitted late or not submitted at all, the student must do an extra assignment. If more than one workgroup assignment is submitted late, the student will not receive a grade for the course.
If a student misses one or more workgroups and turns in one or more workgroup assignments late (or not at all), the student will not receive a grade for the course.
Lectures (14 hours)
Workgroups (10 hours)
Final exam (5 hours)
Other assessments (25 hours)
Self-study (86 hours)
Assessment method
The following assessments will be used:
Take-home midterm exam (20%); Enrolment on the course Brightspace site is required to receive this examination.
Final group paper (30%)
Multiple-choice final exam (50%)
Students must receive a sufficient grade (5.5 or higher) on the group paper and the multiple-choice final exam to pass the course. Students must also receive a weighted average of all three course components that is 5.5 or higher.
The following resit provisions apply:
One additional take-home midterm exam will be provided in January for students who do not pass the initial take-home midterm exam. Students receive a maximum grade of 7 on this resit.
If the group assignment receives an insufficient grade, the group may resubmit this assignment once. If the group does not submit the initial group assignment before the deadline, they may submit it after the deadline but will not have the opportunity to retake this assignment if they receive an insufficient grade.
A resit for the final exam will be given in January.
Partial grades are only valid in the current academic year; partial grades will not remain valid after the exam and the resit of the course.
You can find more information about assessments and the timetable exams on the website.
Details for submitting papers (deadlines) are posted on Brightspace. On the Public Administration front page of the E-guide you will find links to the website, uSis and Brightspace.
More information about participation in exams can be found in the Rules & Regulations.
Reading list
‘Multiple Regression: A Primer’ by Paul D. Allison, SAGE Publications. 'Logistic Regression: A Primer' by Fred C. Pampel, SAGE Publications (e-book available free digitally via Leiden library).
Registration
Register for every course and workgroup via My Studymap or uSis. Course registration via My Studymap is possible from 12 July 13.00h. Registration for the workgroups starts on 1 August 13:00h. Some courses and workgroups have a limited number of participants, so register on time (before the course starts). In uSis you can access your personal schedule and view your results.
Leiden University uses Brightspace as its online learning management system. After enrolment for the course in uSis you will be automatically enrolled in the Brightspace environment of this course.
Contact
Dr. Brendan J. Carroll (Wijnhaven, 4.92), office hours by appointment, e-mail: b.j.carroll@fgga.leidenuniv.nl