Syllabus - Updated 08/25/2021

COURSE NUMBER, TITLE:

NRSG 736, Quantitative Analysis of Clinical Research Data

Prerequisites:

BIOS 500 and 501 (or permission of instructor)

Credits:

2 credit hours (lecture 1 hr/week; computer lab 2 hr/week)

Course Time & Locations:

DAY TIME LOCATION
Mondays 11:00 – 11:50 am Nursing classroom 114, via ZOOM only if needed https://zoom.us/j/94229624789?pwd=cmh4eit4dWZmTU9tVEgrZ1pkejVidz09
Wednesdays 1:00-2:50 pm Nursing classroom 114, via ZOOM only if needed https://zoom.us/j/95680217485?pwd=T29QdUk1YWFvUzFURURMc3FzanBXdz09

Dates:

  • Classes begin August 25 – end December 3, 2021
  • Exam Period December 6 - 10, 2021 (Grades due by Dec 15)

Course Objective:

To build and expand upon the statistical theory and methods learned in BIOS 500 and 501 and improve the student’s statistical software experience and programming skills with SAS, SPSS or R to improve research scholarship and dissemination.

Course Description:

This course builds on the required statistical sequence and focuses on practical application of statistics including understanding clinical research questions. Analyzing data is the major emphasis of the course including examining if assumptions of the statistical analysis are being met and interpreting the findings. Course assignments focus on using statistical software and computing resources to analyze data sets from actual clinical research studies and interpretation of output and literature.

General Outline:

  1. Computing Environment (SAS, SPSS, R, Other Supporting Software)
  2. Getting data into and out of statistical software (import, export features)
  3. Reproducible Research Principles (documentation, reporting, version control)
  4. Initial data assessments: univariate and bivariate methods, parametric and non-parametric
  5. Regression methods: linear, logistic and introduction to “generalized”
  6. Analysis of (co)Variance: univariate and multivariate, ANOVA, ANCOVA, MANOVA, MANCOVA
  7. Longitudinal analysis: repeated measures with introduction to multi-level models (MLM)
  8. Assessment and testing of data & model assumptions (including missing data)
  9. Introduction to Factor Analysis, Reliability and Discriminant Analysis, and SEM (structural equation modeling) as time allows

Primary text (Recommended, but not required):

  • Andy Field (Author); Discovering Statistics using IBM SPSS Statistics [Paperback: 952 pages], Publisher: SAGE Publications Ltd; Fourth Edition edition (January 24, 2013), Language: English, ISBN-10: 1446249182, ISBN-13: 978-1446249185
  • Andy Field (Author); Discovering Statistics using R; First Edition [Paperback: 992 pages], Publisher: SAGE Publications Ltd; First Edition edition (April 5, 2012), Language: English, ISBN-10: 1446200469, ISBN-13: 978-1446200469
  • Andy Field (Author); Discovering Statistics using SAS; First Edition [Paperback: 752 pages], Publisher: SAGE Publications Ltd; First Edition edition (February 10, 2010), Language: English, ISBN-10: 1849200920, ISBN-13: 978-1849200929

Other texts that may be referenced during the semester:

  • Jacob Cohen, Patricia Cohen, Stephen G. West, Leona S. Aiken. “Applied Multiple Regression/Correlation Analysis for the Behavioral Sciences, 3rd Edition [Hardcover]”, Publisher: Routledge; Third edition (August 1, 2002), Language: English, ISBN-10: 0805822232 , ISBN-13: 978-0805822236
  • Barbara G. Tabachnick and Linda S. Fidell , “Using Multivariate Statistics (6th Edition) [Hardcover]”, Publisher: Pearson; 6th edition (June 25, 2012), Language: English, ISBN-10: 0205849571, ISBN-13: 978-0205849574 {although the instructor may also draw from the 5th edition as well}
  • Publication Manual of the American Psychological Association, 6th Edition [Paperback], Publisher: American Psychological Association (APA); 6th edition (July 15, 2009), Language: English, ISBN-10: 1433805618, ISBN-13: 978-1433805615
  • Muenchen, Robert A. (2011). R for SPSS and SAS Users. Springer Science: New York. Book website at http://r4stats.com/books/r4sas-spss/

Canvas:

  • Notes, Assignments and associated datasets and instructions will be posted on Emory Canvas (https://classes.emory.edu/) Grades will also be posted on Canvas
  • In addition to Canvas, this website built for N736 is https://melindahiggins2000.github.io/N736/index.html When applicable, helpful videos, handouts and materials for each class lecture will be posted at this website
  • I will also occasionally post data, code, files and other materials using Github repositories – these can be access at my Github account https://github.com/melindahiggins2000
  • When applicable, videos will be done of the class lectures which will be posted on EchoALP linked to the Canvas website for your referral after class or if you miss a class.

Other Helpful Resources:

Evaluations:

  • 7 Homework assignments 70% (10% each)
  • FINAL Project 30% (3 milestones: 5%, 5%, 20%)

Homework:

Homework will be assigned every 1 to 2 weeks (total of 7 assignments). Detailed instructions will be provided with each homework. However, the goal of each assignment is two-fold: (1) to demonstrate that you know how to use your statistical software to execute the appropriate analyses requested in each assignment and (2) present your results in a professional manner equivalent to what is required for peer-reviewed research journal submissions.

FINAL Data Analysis Project (more details to come later in semester) [100 points]:

  1. Datasets will be provided to choose from or you can bring in an appropriate one of your choice, but the dataset must be approved by the instructor prior to executing your final analysis.
  2. [10 points] Develop a short proposal including a description of the dataset, how it was acquired, sampling design, hypotheses, and analysis plan(s)
  3. Analyze the data using your statistical software
  4. Write up “journal-ready” (APA formatting guidelines) sections for each of the following:
    1. [5 points] (brief) Background of data and purpose of the planned analyses (i.e. your hypotheses)
    2. [20 points] Methods section
    3. [15 points] Results
    4. [15 points] Tables and Figures as needed
    5. [15 points] Discussion of results and conclusions drawn
  5. [20 points] Provide a copy of your dataset (with appropriate details on your labels and “codebook/formats”) and complete analysis syntax/code used to complete your analyses

Grading:

I will strive to post grades for each assignment within a week of turning in your homework and project milestones. You are welcome to inquire about your grades at any time during the semester. The instructor will strive to provide continuous feedback throughout the semester relative to your projected final grade for the course.

Instructor provided help as needed/as requested:

Additional help outside of class time will be provided as requested (please send email to mailto:melinda.higgins@emory.edu.

Class Calendar – Fall 2021

class schedule

Copyright © Melinda Higgins, Ph.D.. All contents under (CC) BY-NC-SA license,CC-BY-NC-SA unless otherwise noted.

Feedback, Comments (email me)?