About this course: This course aims to help you to draw better statistical inferences from empirical research. First, we will discuss how to correctly interpret p-values, effect sizes, confidence intervals, Bayes Factors, and likelihood ratios, and how these statistics answer different questions you might be interested in. Then, you will learn how to design experiments where the false positive rate is controlled, and how to decide upon the sample size for your study, for example in order to achieve high statistical power. Subsequently, you will learn how to interpret evidence in the scientific literature given widespread publication bias, for example by learning about p-curve analysis. Finally, we will talk about how to do philosophy of science, theory construction, and cumulative science, including how to perform replication studies, why and how to pre-register your experiment, and how to share your results following Open Science principles. In practical, hands on assignments, you will learn how to simulate t-tests to learn which p-values you can expect, calculate likelihood ratio's and get an introduction the binomial Bayesian statistics, and learn about the positive predictive value which expresses the probability published research findings are true. We will experience the problems with optional stopping and learn how to prevent these problems by using sequential analyses. You will calculate effect sizes, see how confidence intervals work through simulations, and practice doing a-priori power analyses. Finally, you will learn how to examine whether the null hypothesis is true using equivalence testing and Bayesian statistics, and how to pre-register a study, and share your data on the Open Science Framework. All videos now have Chinese subtitles. More than 10.000 learners have enrolled so far!
Who is this class for: This course is aimed at anyone who wants to improve their statistical inferences, either because you are preparing to do empirical research for the first time, or because you were never taught these important statistical concepts in a clear and accessible manner in the past. I didn't know most of the things you will learn in this course until well after I got my PhD, and I've tried to create the course I would have liked to have gotten when I started to do research. You should have some basic knowledge about calculating descriptive statistics, and how to perform t-tests, correlations, and ANOVA's (If you don't have this knowledge, try https://www.coursera.org/learn/basic-statistics first). We will use R in many of the assignments, but you don't need any previous knowledge of R - we will mainly use it as a fancy calculator.
Taught by: Daniel Lakens, Associate Professor
Department of Human-Technology Interaction
| Level | Intermediate |
| Commitment | 7 weeks of study, 3 hours a week |
| Language | English, Subtitles: Chinese (Simplified) |
| How To Pass | Pass all graded assignments to complete the course. |
| User Ratings |
- Video: Introduction
- Reading: Structure of the Course
- Reading: Passing the Course
- Reading: Research on Quizzes
- Practice Quiz: Consent Form for Use of Data
- Reading: Week 1: Overview
- Video: Frequentism, Likelihoods, Bayesian statistics
- Video: What is a p-value
- Video: Type 1 and Type 2 errors
- Reading: Assignment 1: Which p-values can you expect?
- Practice Quiz: Answer Form Assignment 1 : Which p-values can you expect?
- Reading: Week 2: Overview
- Reading: Interview with Professor Zoltan Dienes
- Video: Interview: Zoltan Dienes
- Video: Likelihoods
- Reading: Assignment 2.1: Likelihoods
- Practice Quiz: Answer Form Assignment 2.1
- Video: Binomial Bayesian Inference
- Reading: Assignment 2.2: Bayesian Statistics
- Practice Quiz: Answer Form Assignment 2.2: Bayesian Statistics
- Video: Bayesian Thinking
- Reading: Week 3: Overview
- Video: Type 1 error control
- Video: Type 2 error control
- Reading: Assignment 3.1: Positive Predictive Value
- Practice Quiz: Answer Form Assignment 3.1: Positive Predictive Value
- Reading: Assignment 3.2: Optional Stopping
- Practice Quiz: Answer Form Assignment 3.2: Optional Stopping
- Reading: Interview Professor Dan Simons
- Video: Interview Professor Dan Simons
- Video: Pre-registration
- Reading: Week 4: Overview
- Video: Effect Sizes
- Video: Cohen's d
- Video: Correlations
- Reading: Assignment 4: Calculating Effect Sizes
- Practice Quiz: Answer Form Assignment 4: Effect Sizes
- Reading: Week 5: Overview
- Video: Confidence Intervals
- Reading: Assignment 5.1: Confidence Intervals
- Practice Quiz: Answer Form Assignment 5.1: Confidence Intervals and Capture Percentages
- Video: Sample Size Justification
- Reading: Assignment 5.2: Random Variation and Power Analysis
- Practice Quiz: Answer Form Assignment 5.2: Random Variation and Power Analysis
- Video: P-Curve Analysis
- Reading: Week 6: Overview
- Video: Philosophy of Science
- Video: The Null is Always False
- Reading: Assignment 6: Equivalence Testing
- Practice Quiz: Answer Form Assignment 6: Equivalence Testing
- Video: Theory Construction
- Reading: Week 7: Overview
- Video: Replications
- Video: Publication Bias
- Video: Open Science
- Practice Quiz: Practice Exam
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Dr. Lakens is a very good instructor. He speaks cleary and he is extremaly focused in each subject he's teaching, Unfortunatelly, he keeps making some jargons in somehow he understand frequentist statistics. I'll list some of mistakes:
1. The p-value is a probability computed assuming *the null hypothesis is true*, that the test statistic would take a value as extreme or more extreme than that actually observed. When he cite "assuming null effect", he merge "effect size" and "NHSTs". This becomes even worst when we use NHST to analyze variable distributions where, by default, we don't have an "effect", but an "assumption". This is valid for all normality test, such anderson-darling or kolgomorov-smirnoff.
2. Furthermore considering the way he decided to approach to null hypothesis, any statistician knows that a null is always wrong and it is the why we dont accept the null. During all the time, in his videos, he insists to use "accepting the null". When he does that, is like a broken guitar in a symphony. It disturbs the video.
3. The control of type II error always involves some sample-size calculations wether we want to acchieve, at minimium, 80% of power. He simply attached a R script to run and he didnt't mention how we can verify if some study has an effect or not. Point and clicking button, in my opinion, is not adequate when we are in a statistical class where the goal is to improve our inferencial skills.
4. Some of quizzes and evaluations have items where options are not presented in a properly way. The subject of each response vary substantly.
I trully hope this feedback will be read in an academic way, which was the intention.
Amazing course. Definitely worth to accomplish. Highly recommended for every researcher, lecturer, PhD. student or student that is interested in prestent state of art regarding choosen important topics statistics and methodology, especially in Psychology.
A brilliantly informative and engaging exploration of some the issues involved in data analysis and hypothesis testing. Though I'm probably still a while away from using many of the techniques covered myself in formal research, I certainly feel better equipped to interpret existing research and spot potential statistical slip-ups. Much recommended!
Coursera provides universal access to the world’s best education, partnering with top universities and organizations to offer courses online.
GR
a very thoughtful introduction to the different approaches of statistical reasoning