Statistical Inference for Biology

The Jackson Laboratory

Mar 10, 17 & 24, 2020

9:00 am - 12:30 pm

Instructors: Robyn Ball, Ann Wells, Andrew Deighan, Sue McClatchy

Helpers: Isabela Gerdes Gyuricza

General Information

Statistical Inference for Biology will follow Irizarry & Love's Data Analysis for the Life Sciences. It will introduce the statistical concepts essential to understanding p-values and confidence intervals. Lecture and demonstration in concepts will precede guided hands-on practice and coaching for skills development so that participants can perform statistical analysis with good understanding. At the end of the series, participants will be able to:

  1. Define a population, sample, estimate, and parameter
  2. Describe null and normal distributions
  3. Explain why confidence intervals, not p-values, better reflect statistical significance
  4. Calculate power
  5. Perform permutation and association tests
The course will meet weekly on Tuesdays from 9:00 am - 12:30 pm on March 10th, 17th and 24th in Bar Harbor. Participants must attend in person. Remote attendance from desks, home, or away will not be supported. This course is open to Jackson Laboratory Employees as well as those from neighboring institutions.

Prerequisite: Competence with the R programming language.

Who: The course is aimed at graduate students and other researchers who would like to learn more about statistics.

Where: Breezeway Bioinformatics Training Room, bldg 1, unit 5, 600 Main Street, Bar Harbor, Maine. Get directions with OpenStreetMap or Google Maps.

When: Mar 10, 17 & 24, 2020. Add to your Google Calendar.

Requirements: Participants must bring a laptop with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.). They should have a few specific software packages installed (listed below).

Accessibility: We are committed to making this workshop accessible to everybody. The workshop organizers have checked that:

Materials will be provided in advance of the workshop and large-print handouts are available if needed by notifying the organizers in advance. If we can help making learning easier for you (e.g. sign-language interpreters, lactation facilities) please get in touch (using contact details below) and we will attempt to provide them.

Contact: Please email susan.mcclatchy@jax.org for more information.


Code of Conduct

Everyone who participates in Carpentries activities is required to conform to the Code of Conduct.


Collaborative Notes

We will use this collaborative document for chatting, taking notes, and sharing URLs and bits of code.


Surveys

Please be sure to complete this survey after the workshop.

Post-workshop Survey


Schedule

Tuesday, Mar 10

09:00 Overview and introductions
09:15 Inference: introduction
09:20 Random variables
09:30 The null hypothesis
09:40 Distributions
09:50 Probability distribution
10:00 Normal distribution
10:10 Practice exercises
10:30 Review practice exercises & discuss
10:45 Morning break
11:00 Populations, samples & estimates
11:10 Practice exercises
11:30 Review practice exercises & discuss
11:40 Central Limit Theorem and t-distribution
11:50 Practice exercises
12:10 Review practice exercises & discuss
12:30 END

Tuesday, Mar 17

09:00 Central Limit Theorem in practice
09:15 Practice exercises
09:30 Review practice exercises & discuss
09:45 T-tests in practice
09:55 The t-distribution in practice
10:05 Confidence intervals
10:15 Power calculations
10:25 Practice exercises
10:45 Morning break
11:00 Review practice exercises & discuss
11:15 Monte Carlo simulation
11:25 Parametric simulations for the observations
11:35 Practice exercises
11:55 Review practice exercises & discuss
12:05 Permutation tests
12:15 Practice exercises
12:30 END

Tuesday, Mar 24

09:00 Review previous exercises & discuss
09:15 Association tests
09:25 Practice exercises
09:45 Review practice exercises & discuss
09:55 Exploratory Data Analysis
10:00 Quantile Quantile Plots
10:10 Boxplots
10:20 Practice exercises 1 and 2 only
10:35 Review practice exercises & discuss
10:45 Morning break
11:00 Scatterplots and correlation
11:10 Stratification
11:20 Practice exercises 3-8 only
11:40 Review practice exercises & discuss
11:50 Plots to avoid
11:55 Practice exercises 9 & 10 only
12:00 Review practice exercises & discuss
12:05 Misunderstanding correlation (advanced)
12:10 Robust summaries
12:15 Wilcoxon rank sum test
12:20 Practice exercises
12:25 Post-workshop Survey
12:30 END

Syllabus

Inference

  • Random variables
  • Distributions
  • Central Limit Theorem
  • P-values
  • Confidence intervals
  • Reference...

Exploratory Data Analysis

  • Q-Q plots, boxplots and scatterplots
  • Correlation
  • Stratification
  • Bi-variate normal distribution
  • Plots to avoid
  • Reference...

Setup

To participate in a workshop, you will need access to the software described below. In addition, you will need an up-to-date web browser.

We maintain a list of common issues that occur during installation as a reference for instructors that may be useful on the Configuration Problems and Solutions wiki page.

R

R is a programming language that is especially powerful for data exploration, visualization, and statistical analysis. To interact with R, we use RStudio.

Video Tutorial

Install R by downloading and running this .exe file from CRAN. Also, please install the RStudio IDE. Note that if you have separate user and admin accounts, you should run the installers as administrator (right-click on .exe file and select "Run as administrator" instead of double-clicking). Otherwise problems may occur later, for example when installing R packages.

You can download the binary files for your distribution from CRAN. Or you can use your package manager (e.g. for Debian/Ubuntu run sudo apt-get install r-base and for Fedora run sudo dnf install R). Also, please install the RStudio IDE.