In this page you will find educational resources related to Biostistics. That includes announcements about events, material for online workshops, material related to workshops that we held in person, and other resources.
Workshops - We are delivering a series of workshops targeted to researchers who would like to learn R and/or SPSS. We try to keep these workshops at the basic level so that no pre-requisites are required and we can attend all interested researchers, regardless of their background in statistics. The workshops are focused on types of analyses that in our experience are most used at CAMH. We will include optional assignment lists and office hours for those who want to go deeper on the subject matter presented in the workshops, and those who have questions.
SPSS and RStudio Access - As a CAMH researcher, you should have access to both SPSS and R/RStudio. You can request CAMH help desk for access to SPSS. R/RStudio are free wnad you can download and install from the internet.
How it wil work - The workshops will be delivered via Webex, and relevant links, datasets and other materials will be emailed to you a day or two before the workshop for which you are registered. We will record the sessions and make them available here. There will be optional assignments for thowse who want to go a little further into their learning. We will also set up virtual office hours to go over solving the assignments and any question related to the workshops.
Registration & Questions - To register for the workshops, please, complete this form. If you have any question, please, don't hesitate contacting Marcos (marcos.sanches@camh.ca).
Tuesday, Apr 19 from 12 to 1pm Introduction to SPSS Part I | Dataset and Data Dictionary Entering data manually Importing data from Excel Sorting and quick data inspection |
Tuesday, Apr 26 from 12 to 1pm Introduction to SPSS Part II | Recode Compute If conditional Split File and Select Cases |
Tuesday, May 03 from 12 to 1pm Introduction to SPSS Part III | Crosstab Means Graphs Explore |
Tuesday, May 10 from 12 to 1pm Introduction to SPSS Syntax | We will show you how the SPSS syntax works. This is about reproducibility, not coding/programing. The idea is that you have enough understanding of SPSS syntax so that you can use it if you want, but most importantly, keep a record of what you did. |
Tuesday, May 17 from 12 to 1pm SPSS Means and Proportions I | We will show how to compare means and proportions in SPSS. With this workshop we will enter Statistical Inference territory, and part of the workshop will be an overview of the scientific method, how statistics fits into it, and what p-values means. We plan to cover: t-tests for independent samples Chi-square tests for contingence tables |
Tuesday, May 24 from 12 to 1pm SPSS Means and Proportions II | In this workshop we plan to finish covering location tests. We hope to cover: Paired Sample t-test Simple ANOVA (Analysis of Variance) Non-parametric Mann-Whitney U test Non-parametric Kruskal-Wallis H Testl Non-parametric Wilcoxon Test Non-parametric Friedman Test |
Tuesday, May 31 from 12 to 1pm SPSS Linear Regression I | We will cover linear regression in general, including: Categorical and Continuous Variables Variable Selection Confounders Predictive and Exploratory models Coefficients and Interpretation |
Tuesday, Jun 07 from 12 to 1pm SPSS Logistic Regression | We will cover Logistic Regression, including: Definition of binary outcomes, Probability, Odds and Risk Logistic Regression basics and interpretation. |
Tuesday, Jun 14 from 12 to 1pm SPSS Mixed Models I | The workshop will cover: Longitudinal Data; Basics of fixed and random effects; Restructuring Data in SPSS; Within and Between Subject Variables; Within subjet correlation; Interpretation of Results. |
Tuesday, Jun 21 from 12 to 1pm SPSS Linear Regression II | We will expand on what we learned in the first workshop, including: Interactions Model Diagnostics (Influence, outliers) Estimated Marginal Means |
Tuesday, Jun 28 from 12 to 1pm SPSS Mixed Models II | In this workshop we will dive a little deeper into Mixed Models and get some ideas of the different ways we can specify random effect and covariance structure for residuals. |
Wednesday, Apr 20 from 12 to 1pm R and RStudio - Overview | Software installation What is R and RStudio RStudio tour Introduction to Script and Markcown |
Wednesday, Apr 27 from 12 to 1pm Introduction to R part I | Reaing data into R Dataframes, lists, variables How to work with dataframes in general Missing values in R |
Wednesday, May 04 from 12 to 1pm Introduction to R part II | Some basic functions in R Describing the data Means, Standard Deviations Tables R Help |
Wednesday, May 11 from 12 to 1pm Introduction to package dplyr | dplyr is a R package quite useful for ‘data wrangling’. We will cover the primary functions: mutate (creating new variables) select (select columns) filter (select rows) arrange (sort) summarise (summary stats) “%>%” (forward pipe operator, from magrittr pacakge) |
Wednesday, May 18 from 12 to 1pm Introduction to package ggplot2 | ggplot2 is a package for data visualization. We will go over some basic graphs using ggplot2. Scatterplot + smoothing line Boxplot Barchart Line plot |
Wednesday, May 25 from 12 to 1pm Statistical Inference and Basic Stats I | Statistical Inference - Scientific Method, Sampling, Hypothesis Testing, p-values and Confidence Intervals. Test of Means |
Wednesday, Jun 01 from 12 to 1pm R Basic Stats II | Non-parametric tests Chi-square and Fisher's tests Correlation tests |
Wednesday, Jun 08 from 12 to 1pm Linear Regression I | Simple and Multiple Linear Regression Residuals adn Predicted Values Influential Points and Outliers Normality and Linearity Interactions Estimated Marginal Means |
Wednesday, Jun 15 from 12 to 1pm Linear Regression II | Same as above. The content will be convered in two workshops. |
Wednesday, Jun 22 from 12 to 1pm Logistic and Poisson Regression | Binary and Count data Crosstable, Odds Ratio and Relative Risk Probability and Odds Scale Logistic Model Poissson Model Overdispersion Estimated Marginal Means |
Wednesday, Jun 29 from 12 to 1pm Mixed Models | Longitudianl and Clustered data Random Effects Models for Covariance of Residuals Non-normal data longitudinal data, Mixed Lotisitc Regerssion and GEE |
11 workshops held on Webex You can access the recordings and do the assignments!
Video 1 - Introducting myself and some quick stats background (7m19s)
Video 2 - Introduction to R and RStudio. Split in three parts: Part 1, Part 2 and Part 3, each with around 25 minutes.
CSV Dataset - This is the dataset we used in the workshop.
RMarkdown - This is the markdown file with instructions and script that we used.
HTML Output - This is the output from the RMarkdown file in HTML format, which you can read in your web browse.
In this section you will find material that helps you to learn software and statistics related to the work you do in your research at CAMH.
Since 2016 we have had frequent series of SPSS workshops. These workshops are delivered in person, in the CAMH computer lab. They expanded from the initial introductory courses to the current series that inovlves more than 10 different topics of interest to CAMH researchers.
To the extent of possible, we will try to make available here the material of those workshops, or online versions of them.
SPSS is probably the most popular software for Statistical Analysis at CAMH, and one that is accessible to researchers. The material available here will allow you to have a first and basic experience with SPSS, from opening the software, to importing data, doing some simple data cleaning and data analysis tasks. The material is currently in PDF format but it is in our priority list to have it also in video format.
Video 1 - You will learn:
Vido 2 - You will learn:
Video 3 - You will learn:
Download this CSV Dataset, this SPSS Dataset and this Excel Dataset, and then follow the video!
Video 4 - You will learn:
The activities in this video uses this SPSS Dataset.
Video 5 - You will learn:
The activities in this video uses this SPSS Dataset.
In order for your data analysis to be reproducible, you need to keep a record of all you did. Ideally, that means everything from reading the initial dataset to your published results. Doing data cleaning and data analysis using script is the perfect way to make your research reproducible.
SPSS Syntax here does not mean SPSS programming. We just want you to know that is easy to do anything in SPSS using Syntax, and get you comfortable with it. As such, this course is very introductory, we don't expect you to have a high level of SPSS or programing knowledge in order to understand it. We do expect that you know SPSS at the introductory level, that you already know how to do some basica analysis using the point & click menu.
Here you will find a collection of videos and auxiliary material to help you get started with R.
There are not pre
Video 1 - You will learn:
Video 2 - You will learn:
Video 3- You will learn:
Video 4 - You will learn:
Video 5- You will learn:
Dataset Format CSV and Dataset Format SPSS - Please, download these datasets so that you can follow the activities in the video.
Video 6 - You will learn:
Video 1- You will learn: