Correlation, linear and logistic regression with R

Description:

This course runs over three afternoons.

Introduction/Overview

This live online course will show you how do to correlation, linear and logistic regression. The course will also explore the statistical concepts behind these methods in a fun and easy way. An added benefit is that you learn R as well. In addition to workshops in small groups, the instructor will be demonstrating R commands and putting them into “chat” so that you can copy these and follow along; actually doing what the instructor is doing.

Course requirements

For this course you need some understanding of conducting statistical tests. Before the course, it would be helpful for you to look at (or remind yourself of) the following concepts. Links to various websites are provided as an aid.

• Two-sample t-test (https://www.jmp.com/en_gb/statistics-knowledge-portal/t-test/two-sample-t-test.html)
  • The null hypothesis (mean 1 = mean 2) and the 3 alternative hypotheses for t-test (one-tailed: mean 1 > 2, one-tailed: mean 1 < mean 2, two-tailed: mean 1 not equal to mean 2 (Should you use a one-tailed test or a two-tailed test for your data analysis? - Statistics Solutions )
  • Reject the null hypothesis (i.e., declare a result significant) when the p value is less than 0.05 (where 0.05 is a typical value for alpha) (P-Value vs. Alpha: What's the Difference? (statology.org) ). Or compare the test statistic to the appropriate number from a t-distribution table (https://www.jmp.com/en_gb/statistics-knowledge-portal/t-test/two-sample-t-test.html)
  • Linear regression is very similar with 3 hypotheses for the b value, the slope is positive, the slope is negative, the slope can be either positive or negative. Significance is declared in the same way.
• Dependent and independent variables (https://nces.ed.gov/nceskids/help/user_guide/graph/variables.asp#:~:text=(Time%20Spent%20Studying)%20causes%20a,sense%20the%20other%20way%20around)
• Four levels of measurement (https://www.scribbr.co.uk/stats/measurement-levels/)
• Sample standard deviation and variance (https://www.scribbr.co.uk/faqs/standard-deviation-variance/#:~:text=Variance%20is%20the%20average%20squared,e.g.%2C%20minutes%20or%20meters)
• Standard error(https://careerfoundry.com/en/blog/data-analytics/standard-error-vs-standard-deviation/#:~:text=Standard%20deviation%20describes%20variability%20within,that%20can%20only%20be%20estimated)

There is a revision at the beginning of the course, but the more comfortable you are with all of these concepts, the more comfortable you will be with building from these to regression.

No previous knowledge of the R software is required.

Learning objectives

By the end of the workshop, participants will:

• Be able to execute a correlation, bivariate regression, multiple regression and logistic regression and various statistical diagnostics in R.
• Have a good awareness of the statistical concepts behind correlation and regression.
• Have knowledge of the issues which arise with these analysis methods and how to solve these issues.

Topics

This course covers the following topics:

• Scatterplots, covariance and correlation
• Bivariate regression
• Multiple regression
• Logistic regression
• Assumptions behind the models
• Creating and using dummy variables
• Building interaction terms
• This course is also an introduction to the R software for these topics

Who will benefit

People with an understanding of basic statistics, who want to expand their knowledge to regression and the R software for regression. The course is also for people who want knowledge of these topics for critiquing the work of others.

Software

You need both R and RStudio. Prior to the course you will be emailed a link which will contain the course material, but also a document which provides important tips for downloading and installing R and RStudio.

Course tutor

Dr Pamela Campanelli is a Survey Methods Consultant and runs The Survey Coach business. She is also a Chartered Statistician, Chartered Scientist and Fellow of the Academy of Social Sciences. She has worked at the University of Michigan, the U.S. Bureau of the Census, ISER at the University of Essex, and NatCen Social Research. She has both led and been a team member on ESRC grants (one on survey nonresponse and one on measurement error in mixed mode surveys).

She regularly teaches short courses in the UK and abroad for government departments, survey research companies, universities, as well as for various other institutions and businesses. She has been teaching courses in regression for the past 25 years. She believes in delivering courses that are lively and engaging, foster an informal and interactive atmosphere, communicate concepts in a straightforward and accessible way, illustrate the material through the use of ‘real life’ examples, and provide workshops to put theory into practice.

Cost:

£360 for SRA members, £470 for non-members

Website and registration:

Register for this course

Region:

International

Keywords:

Frameworks for Research and Research Designs, Data Collection, Data Quality and Data Management , Qualitative Data Handling and Data Analysis, Quantitative Data Handling and Data Analysis, Mixed Methods Data Handling and Data Analysis, ICT and Software, Research Management and Impact, Research Skills, Communication and Dissemination

Related publications and presentations from our eprints archive:

Frameworks for Research and Research Designs
Data Collection
Data Quality and Data Management
Qualitative Data Handling and Data Analysis
Quantitative Data Handling and Data Analysis
Mixed Methods Data Handling and Data Analysis
ICT and Software
Research Management and Impact
Research Skills, Communication and Dissemination

Back to the training database