Introduction (L1)

NoteLearning objectives

After this unit, students will be able to:

  1. Describe how the lectures, course book, practicals, homework, weekly quizzes and final exam of BIO144 fit together. (not examined)
  2. Identify the prior knowledge and skills assumed at the start of the course, and where to revise them. (not examined)
  3. Describe the steps of a data analysis workflow, from formulating a question to communicating the answer, and explain why the presentation and analysis should be planned before the data are collected.
  4. Describe the four principles for high-quality data analysis: a focused question with planned sampling and analysis; a model that accounts for the distribution and dependence of the data; emphasis on effect sizes and biological relevance; and reporting that makes the research reproducible.
  5. Explain the advantages of doing a data analysis with a script in R, such as being repeatable, readable and sharable.
  6. Distinguish appropriate from inappropriate uses of AI assistants in learning data analysis and in BIO144 assessments.
  7. Recognise and use the course notation for samples, populations and linear models (e.g. the sample mean, sample and population standard deviation, parameter estimates and residuals).

These learning objectives, together with the content of this chapter, define what you need to know for the exam.

The learning objectives for all chapters, and for the course as a whole, are also given on the Learning Objectives page of the course information website.

NoteCode walkthrough for this chapter

Script: walkthrough_ch01_intro.R

This R script contains the code of this chapter, with comments that explain each step. This is the code from the analysis of the class reaction time data in the first lecture. Download it, save it in your BIO144 RStudio project folder, open it in RStudio, and run it line by line while you read the chapter or watch the video. The script reads the datasets directly from the internet. Its last section (“Practical toolbox”) shows code that the Unit 1 practical uses but this chapter does not.

To download the script straight into your project folder (for example on RStudio Server), run this line in the Console:

download.file("https://opetchey.github.io/BIO144_Course_Book/walkthroughs/walkthrough_ch01_intro.R", destfile = "walkthrough_ch01_intro.R")

Video walkthrough: coming soon.

About this chapter

The first week of BIO144 is different from all the others. It is the only lecture that uses slides, and much of it is about how the course works rather than about statistical methods. This chapter is the written version of that lecture. It covers:

  • the goals of the course, and why data analysis matters;
  • what makes a data analysis high quality;
  • how the course is organised, and how the final examination works;
  • how we will work together, including how to use AI assistants;
  • RStudio Server;
  • a complete data analysis, from question to answer, using data that you collect in the lecture;
  • the knowledge it is useful to have already, and the notation used throughout the course.

Goals of the course

The overarching goals of BIO144 are to:

  • provide a solid foundation for answering biological questions with quantitative data;
  • grow your confidence in your ability to understand and perform data analysis;
  • help you plan research projects so that they are easy to analyse;
  • excite you about the wonders of data analysis;
  • prepare you for the final exam;
  • have fun!

Why data analysis matters

Why should you care about data analysis? Only you can answer that question. A strong sense of purpose usually comes from doing something that is meaningful to you and useful to others. Here are some of the ways in which data analysis is both:

  • Showing that a problem exists. Good analysis can make invisible problems visible, and help others take them seriously.
  • Testing solutions. Does an intervention work? Does it work for everyone? Does it have unintended consequences?
  • Evaluating evidence that affects people’s lives. Showing whether a drug works, does not work, or has serious side effects is not abstract: it shapes real decisions.
  • Questioning powerful claims. Marketing, policy and public messaging often rely on selective statistics. You can learn to ask: what is missing? What is exaggerated?
  • Protecting others, especially those with less power. From children targeted by unhealthy products to communities affected by environmental harm, good analysis can act as a form of protection.
  • Serving something bigger than yourself. Science, public trust, health, biodiversity, fairness: data analysis is one way people contribute to their community and society.

In this course you will work on questions from many areas of biology, from animal behaviour and plant growth to soil organisms and human health. Each time, the pattern is the same: we start with a question (or puzzle, or problem), combine data with analysis, and arrive at an answer (or solution).

But how do we make sure the analysis is a good one?

High-quality data analysis: four principles

Popovic et al. (2024) proposed four principles that lead to reliable findings. They were written for ecology, but they apply to data analysis in all of biology, and they run through the whole of this course.

  1. Define a focused research question, then plan sampling and analysis to answer it.
    • Define the research question before collecting new data or exploring existing data.
    • Match the data collection to the question.
    • Plan (and ideally register) the analysis in advance.
  2. Develop a model that accounts for the distribution and dependence of your data.
    • Use a distribution appropriate for the response variable (for example, counts are not normally distributed).
    • Model all dependence among observations (for example, repeated measurements of the same individual).
    • Check the assumptions of the model.
  3. Emphasise effect sizes, to replace statistical significance with biological relevance.
    • Emphasise and report effect sizes, with confidence intervals.
    • Discuss whether the effects are biologically relevant.
    • De-emphasise p-values.
  4. Report methods and findings in enough detail that the research is valid and reproducible.
    • Publish all data.
    • Provide code that others can run.
    • Visualise the outputs of the model to communicate the results.

You will meet each principle many times. Principle 1 is the first step of the workflow below. Principle 2 is why the course moves from linear models to generalised linear models (for counts and binary data) and mixed models (for grouped data). Principle 3 is why we put so much weight on interpreting estimates and their uncertainty. Principle 4 is one reason we do all analyses with scripts in R.

How the course is organised

Note

The course information website has the current times, dates, and other details that can change from year to year.

The team. You are at the centre of the course, supported by the lectures, the practicals, the discussion forum on OLAT and, when needed, email. The course is taught by Prof. Owen Petchey, with a head teaching assistant, an examinations coordinator, and numerous teaching assistants.

The conceptual side: lectures

  • Apart from this first week, the lectures do not use slides.
  • The course book contains what you need to know. Each week has a chapter.
  • In lectures, the lecturer talks, draws, and asks you questions.

Many of the questions in lectures use think, pair, share: you first think about the question on your own, then discuss it with a neighbour, then share with the class. Peer discussion improves understanding, even when none of the students in a discussion group originally knew the correct answer (Smith et al. 2009).

The practical side.

  • Practicals, where you work on data analysis with help from the teaching assistants.
  • Homework, best done between the lecture and the practical.
  • Weekly practice quizzes, which you can do at any time.

Please keep up with the course material, and reach out to us if you feel you are falling behind. The weeks do not all need the same amount of time, so look ahead and plan early.

Where to find everything. The course uses four websites:

  • OLAT, the hub, which links to everything else and hosts the discussion forum. Please ask questions and make requests in the forum.
  • The course information website, with general information, the learning objectives, and a page for each week.
  • The course book (this book).
  • The site with the homework, practicals and weekly quizzes (on the UZH RStudio Connect server: off campus, connect to the UZH VPN first).

Much of the course material is new or recently revised. If you find something that is unclear, too brief, or wrong, please let us know.

The final examination

Note

Check the course information website for the current examination details.

One comment here: The exam consists of case studies. In each, you analyse a dataset and answer questions about it. Many conceptual questions are embedded in the case studies. Because the exam asks you to analyse data in R and give numerical answers, the best preparation is to practise doing analyses yourself, every week.

How we will work together

We are here to support you: to give you the knowledge of how to learn more, and the confidence that you can.

  • Everyone here can learn to think analytically and statistically.
  • We will hold you to high standards, because we believe you can meet them. Our job is to support you in reaching them.
  • Struggle is part of growth, not a sign of failure or deficiency.
  • Feeling stressed before a challenge is normal. A higher heart rate, faster breathing and a tight stomach are your body giving you more resources to meet the challenge.

High standards and wise feedback. Feedback in this course follows the idea of “wise feedback” (Cohen et al. 1999): “I’m giving you these comments because I have high standards and I know that you can meet them.” Feedback will be honest and specific. It comes from belief in your potential, not criticism of you as a person. If it ever feels like you are being criticised, try to reframe it as being challenged to grow. This class is a safe space for you, and it is a challenging space for you.

Using AI assistants

AI assistants such as ChatGPT, Claude, Gemini and Copilot can help you learn, if you use them well.

Asking for help understanding is usually a good use. For example:

  • “What is the mode of a distribution?”
  • “I didn’t understand that explanation. Can you give an easier one?”
  • “Can you show me the mode graphically?”
  • “Can you give me an example of getting the mode of a distribution in R?”

Asking for help writing code needs more care. A request like “write code to import data and give the number of missing values in each variable” can save time. A request like “import the data, fit a regression, check the diagnostics, summarise the results, make a nice figure, put it all in a Quarto file, and do it while I go and chill” means you learn nothing, and you cannot check whether the result is correct.

Your relationship with AI assistants. In a strong relationship, the AI is an empowering tool: a knowledgeable collaborator that complements your skills, speeds up your work, and supports your growth. You provide the context, direction and critical judgement. In a poor relationship, you use the AI’s output without understanding it, copying and pasting solutions. This leads to errors, inefficient or misaligned solutions, and your own skills stagnating.

The knowledge and expertise you bring is what makes a good relationship with an AI assistant possible. So we suggest you minimise your use of AI assistants during the course (and minimise your use of the example solutions too). Do the work, and get the benefit.

Guidance and good practice

Important

For the final examination, you will use your own computer, but the test will run inside the Safe Exam Browser, which will be configured to block all access to generative AI tools, browser-based assistants, external software, online services, and any AI code copilots inside RStudio or other IDEs. This means no form of generative AI will be available during the exam. Because of this, please avoid becoming overly reliant on GenAI—such as ChatGPT, Claude, Gemini, Copilot, or similar tools for answering quiz questions, explaining results, fixing errors, guiding your analysis, or writing code. You must be able to perform all tasks independently. We also strongly recommend that you do not use RStudio with Copilot integration during the course, as it will not function in the exam environment and may leave you under prepared. Throughout the semester, be sure to practice writing your own R code, interpreting outputs yourself, and applying statistical reasoning without AI assistance, as your exam performance will depend entirely on your own knowledge and skills.

Generative AI (GenAI) tools can support learning, exploration, and coding in R. They can be powerful assistants, but they must be used with care. This section introduces the types of tools available, provides guidelines for responsible use, highlights red flags for problematic usage, and gives examples of good and poor practice.

Typical uses:

  • asking conceptual questions
  • summarizing methods
  • generating example code
  • explaining error messages

Strengths:

  • flexible and conversational
  • good for brainstorming
  • can generate starter code

Limitations:

  • often wrong in subtle ways
  • may hallucinate functions
  • cannot see your working R session

Guidelines for Good Use of Generative AI

Use GenAI as a Helper, Not a Source of Truth

Best uses:

  • drafting
  • explanation
  • syntax reminders
  • scaffolding

Not reliable for:

  • model choice
  • statistical inference
  • interpreting coefficients
  • designing analysis workflows
  • checking assumptions

Always Verify AI-Generated Code and Explanations

Check:

  • does the code run?
  • do variable names match?
  • is the model appropriate?
  • are assumptions addressed?
  • is the explanation logically correct?

Keep Human Judgement Central

GenAI cannot:

  • understand scientific questions
  • evaluate model assumptions
  • know ecological/biological reasoning
  • determine appropriate models

Provide Context Carefully

When asking GenAI:

  • describe variables
  • provide example data
  • specify your goal
  • show your existing code

Better context = better answers.

Use GenAI to Improve Understanding, Not Bypass It

Helpful:

  • “Explain logistic regression.”
  • “Why do residuals fan out?”

Not helpful:

  • “Do my assignment for me.”

Indicators of Problematic Usage

Code That Does Not Reflect Ability

Signs:

  • unfamiliar advanced syntax
  • unexplained packages
  • inconsistent style

Hallucinated Functions or Nonsensical Code

Examples:

  • slope(x) in mixed models
  • missing arguments
  • fabricated packages

Statistical Errors Typical of AI

Common issues:

  • wrong model family
  • wrong inference logic
  • invented assumptions
  • incorrect explanation of coefficients

Lack of Understanding

Indicators:

  • cannot explain model
  • inconsistent interpretations
  • identical phrasing to AI output

Over-Reliance on AI

Signs:

  • using AI for every step
  • no debugging effort
  • stagnation in skill development

Examples of Good and Problematic Use

Good Use Examples

A. Syntax help
“How do I specify a random slope in lme4?”

B. Clarification
“How does adding an interaction change interpretation?”

C. Debugging
“What does ‘object not found’ usually mean?”

D. Brainstorming
“How can I visualise a logistic regression?”

Problematic Use Examples

A. Blindly copying model code

lm(y ~ x1 + x2 * x3 * x1)

B. Incorrect statistical logic
AI code labelled as a bootstrap but is actually a permutation test.

C. Misleading interpretation
Claims that coefficients assume explanatory variable independence.

D. Presenting AI-generated plots without understanding

E. Outsourcing entire workflow
“Write a script that loads data, cleans it, runs models, interprets, and writes the report.”

Summary

Generative AI can:

  • help learning
  • support debugging
  • provide code scaffolds
  • explain concepts

But it can also:

  • hallucinate
  • produce incorrect models
  • misinterpret statistics

Use GenAI as a supportive tool—never as an unquestioned authority.
Good use of GenAI supports learning. Problematic use replaces it.

Common GenAI Errors in R and Statistical Modelling

Generative AI tools can be helpful for writing R code, exploring ideas, and learning syntax.
However, they sometimes produce plausible but incorrect code or explanations.
This section provides real examples of typical GenAI mistakes, with correct solutions and learning points.

Why this matters: GenAI is a pattern-matching system, not a statistical reasoning engine. It does not understand assumptions, inference, or modelling logic.Therefore, students should never accept code or explanations without checking them.

Incorrect formula structure in lm()

Prompt: Fit a linear model with main effects and a two-way interaction between x2 and x3.

Incorrect GenAI output:

lm(y ~ x1 + x2 * x3 * x1, data = df)

This includes an unintended three-way interaction and extra terms.

Correct:

lm(y ~ x1 + x2 * x3, data = df)

Learning point: Always check model formulas carefully. AI often adds or removes interactions.

Confusing bootstrap and permutation tests

Documented case: GenAI was asked for a bootstrap t-test.

Incorrect GenAI code (actually a permutation test):

t_stats <- replicate(1000, {
  perm <- sample(df$group)
  t.test(df$value ~ perm)$statistic
})

Correct bootstrap approach:

t_stats <- replicate(1000, {
  sample_df <- df[sample(nrow(df), replace = TRUE), ]
  t.test(value ~ group, data = sample_df)$statistic
})

Learning point: The logic of inference matters. Code that runs is not necessarily correct.

Incorrect explanation of linear-model coefficients

Incorrect claim: “Coefficients assume independence among explanatory variable.”

This is false. Linear model coefficients describe conditional effects within the model, regardless of collinearity.

Learning point: Interpretations come from the model structure, not from simplistic assumptions GenAI sometimes invents.

Hallucinated functions in mixed models

Incorrect GenAI output:

lmer(y ~ x + (slope(x) | group), data = df)

slope() does not exist.

Correct random-slope specification:

lmer(y ~ x + (x | group), data = df)

Learning point: Always verify syntax in package documentation.

Wrong variable names

The dataset has variables height and age.

Incorrect GenAI output:

lm(Height ~ Age, data = df)

Correct:

lm(height ~ age, data = df)

Learning point: GenAI often guesses variable names. Check against your data.

Wrong model family for binary data

Incorrect GenAI output (linear regression):

lm(y ~ x, data = df)

Correct logistic regression:

glm(y ~ x, data = df, family = binomial)

Learning point: For binary response variables, specify the model family explicitly.

Incorrect explanation of random intercepts

Incorrect claim:
“Random intercepts eliminate correlation among repeated measures.”

Incorrect — they model correlation, not eliminate it.

Learning point: Random effects structure determines the implied correlation. AI explanations are often vague or wrong here.

Omitting interaction terms in ANOVA

Prompt: Two-way ANOVA with interaction.

Incorrect:

aov(y ~ factor1 + factor2, data = df)

Correct:

aov(y ~ factor1 * factor2, data = df)

Learning point: Confirm that the model matches the experimental design.

Incorrect use of predict()

Prompt: Predict for new x values.

Incorrect GenAI output:

predict(model)

This gives in-sample fitted values, not predictions for new data.

Correct:

predict(model, newdata = data.frame(x = c(1, 2, 3)))

Learning point: Always specify newdata for predictions.

Poor explanations of multicollinearity

Incorrect GenAI claim:
“Multicollinearity is indicated when the model p-value is low but the individual explanatory variable p-values are high.”

This is an unreliable and incomplete diagnostic.

Better diagnostics:

car::vif(model)
cor(df)
model.matrix(model)

Learning point: AI often repeats common internet tropes rather than robust statistical principles.

GenAI Summary

GenAI can:

  • write useful scaffolding code,
  • provide quick reminders,
  • help with simple tasks.

But it can also:

  • hallucinate functions,
  • give subtly incorrect models,
  • invent statistical logic,
  • provide plausible but wrong explanations.

Advice for students:
Use GenAI as a starting point, not an authority.
Always check:

  • function names,
  • model formulas,
  • assumptions,
  • interpretations,
  • and logic.

In statistics, clarity of reasoning matters more than code that merely runs.

RStudio Server

You can use R and RStudio either on your own laptop or in a web browser, through the UZH RStudio Server (https://rstudio.mnf.uzh.ch/).

  • You will have to use RStudio Server in the exam, so whichever you use during the course, make sure you can log in to RStudio Server and work there (the Unit 1 practical starts with this).
  • RStudio Server: much of the setup is already done for you, but you have to be connected to the internet (and to the UZH network or VPN for some resources).
  • Your own laptop: works offline, but you need to install R, RStudio and the add-on packages yourself (see the “Getting R & RStudio” section of the Previous Knowledge self-tests).

Only registered users can log in. Everyone in the OLAT course is registered, so you must be in the OLAT course to get access.

A complete data analysis: reaction times

To give you a feel for what is involved in data analysis, the first lecture includes a live demonstration of the whole workflow, using data collected from you during the lecture. You will understand some of the demonstration, and not other parts of it. That is expected: keep notes about what you do not understand, and look for the answers as the course goes on.

The steps of the workflow are:

  1. Question
  2. Expectation
  3. Planned presentation and analysis
  4. Selection of subjects
  5. How the data will be collected
  6. Ethics and permissions
  7. Data collection
  8. Data wrangling
  9. Visualisation
  10. Statistical test
  11. Critical thinking
  12. Reporting and communicating

Notice that the first six steps all happen before any data are collected. This is Popovic et al.’s first principle in action.

Question

What should our question be? As always, there are some influences and some constraints. We should ask a question that is of interest to us, and of some importance. And we must be able to collect the data needed to answer it, within our current constraints.

The question we address is: do the reaction times of male and female students at the University of Zurich differ? Reaction times matter for safety (for example, when driving) and in sport (for example, at the start of a sprint race).

Expectation

There has already been quite a lot of research on reaction times. In general, males tend to have faster reaction times than females, so we expect the same for students at the University of Zurich.

Planned presentation and analysis

Before collecting any data, we decide what graph we will make and what statistical test we will use.

  • Graph: box plots of reaction time (on the horizontal axis) for females and males. This shows the centre and spread of the two groups side by side.
  • Statistical test: we are comparing the mean of a continuous response variable (reaction time) between two groups (the explanatory variable, sex), so a two-sample t-test is a natural choice. Its assumptions include independent observations, and roughly normally distributed values with similar variances in the two groups.

Selection of subjects

Ideally, the subjects would be a random sample from the population we want to draw conclusions about. Are the students in this lecture a random selection of all humans? Of all students at the University of Zurich? The way subjects are selected limits the population to which our conclusions can be generalised.

How the data are collected, and ethics

You measure your own reaction time using an online test, and record it, along with some other information about yourself, in a form linked from the course information website. Because these are data about people, we need to think about ethical issues, such as consent, anonymity, and how the data will be used and shared.

Data wrangling, visualisation and statistical test

These steps are done live in RStudio, with a script.

Doing the analysis with a script in R, rather than by pointing and clicking, makes it:

  • efficient and scalable: it is quick to re-run, including on more or new data;
  • consistent, repeatable and reliable: the same steps give the same result every time;
  • readable, sharable and persistent: others (and your future self) can see exactly what was done, check it, and re-use it;
  • robust: mistakes can be found and fixed, and the whole analysis re-run.

This is Popovic et al.’s fourth principle in action.

Critical thinking, and reporting

Finally, we think critically about the result. How big is the difference in reaction times, and is it biologically relevant (principle 3)? How precise is our estimate? Could something other than sex explain the difference? To whom do the conclusions apply, given how the subjects were selected? Then we report the result clearly, with a figure and a short description of the estimate, its uncertainty, and the test.

Activate your prior learning

BIO144 builds on knowledge you should already have from earlier courses. The “previous knowledge” resources on OLAT help you review it. If you have not worked through them yet, there is still time. It is useful to already be familiar with:

  • Summarising distributions of data: central tendency (mean, median, mode); spread (range, quartiles, standard deviation, standard error); symmetry (skew); pointedness (kurtosis); number of peaks (unimodal, bimodal, multimodal).
  • Types of variable: numeric, continuous, discrete, categorical; response (dependent) and explanatory (independent) variables.
  • Statistical ideas: expected value, parameter, parameter estimate, variable, the central limit theorem, hypothesis testing, degrees of freedom, p-value; the difference between a population and a sample.
  • Probability: for example, the probability of getting five heads when tossing a fair coin seven times; probability distributions (normal, binomial, Poisson, exponential); frequency distributions (histograms).
  • Basic methods and graphs: the t-test, linear regression and the equation of a straight line; box-and-whisker plots and scatterplots.
  • Notation, described in the next section.

Notation and some definitions

Throughout the course, we will use the following notation:

  • \(x\) for a variable. Typically this variable contains a set of observations. These observations are said to represent a sample of all the possible observations that could be made of a population.
  • \(x_1, x_2, \ldots\) for the values of a variable
  • \(x_i\) for the \(i\)th value of a scalar variable. This is often spoken as “x sub i” or the “i-th value of x”.
  • \(x^{(1)}\) for variable 1, \(x^{(2)}\) for variable 2, etc.
  • The mean of the sample \(x\) is \(\bar{x}\). This is usually spoken as “x-bar”.
  • The mean of \(x\) is calculated as \(\bar{x} = \frac{1}{n} \sum_{i=1}^n x_i\).
  • \(n\) is the number of observations in a sample.
  • The summation symbol \(\sum\) is used to indicate that the values of \(x\) are summed over all values of \(i\) from 1 to \(n\).
  • The standard deviation of the sample is \(s\). The standard deviation of the population is \(\sigma\).
  • The variance is \(s^2\). The variance of the population is \(\sigma^2\).
  • The variance of the sample is calculated as \(s^2 = \frac{1}{n-1} \sum_{i=1}^n (x_i - \bar{x})^2\).
  • The standard deviation of the sample is calculated as \(s = \sqrt{s^2}\).
  • \(y\) is usually used to represent a dependent / response variable.
  • \(x\) is usually used to represent an independent / predictor / explanatory variable.
  • \(\beta_0\) is usually used to denote the intercept of a linear model.
  • \(\beta_1\), \(\beta_2\), etc. are usually used to denote the coefficients of the independent variables in a linear model.
  • Estimates are denoted with a hat, so \(\hat{\beta}_0\) is the estimate of the intercept of a linear model.
  • Hence, the estimated value of \(y_i\) in a linear regression model is \(\hat{y_i} = \hat{\beta}_0 + \hat{\beta}_1 x_i^{(1)}\).
  • \(e_i\) is the residual for the \(i\)th observation in a linear model. The residual is the difference between the observed value of \(y_i\) and the predicted value of \(y_i\) (\(\hat{y_i}\)).
  • Often we assume errors are normally distributed with mean 0 and variance \(\sigma^2\). This is written as \(e_i \sim N(0, \sigma^2)\).
  • SST is the total sum of squares. It is the sum of the squared differences between the observed values of \(y\) and the mean of \(y\). It is calculated as \(\sum_{i=1}^n (y_i - \bar{y})^2\).
  • SSM is the model sum of squares. It is the sum of the squared differences between the predicted values of \(y\) and the mean of \(y\). It is calculated as \(\sum_{i=1}^n (\hat{y_i} - \bar{y})^2\).
  • SSE is the error sum of squares. It is the sum of the squared differences between the observed values of \(y\) and the predicted values of \(y\). It is calculated as \(\sum_{i=1}^n (y_i - \hat{y_i})^2\).
  • The variance of \(x\) can be written as \(Var(x)\). The covariance between \(x\) and \(y\) can be written as \(Cov(x, y)\).
  • Covariance is calculated as \(Cov(x, y) = \frac{1}{n-1} \sum_{i=1}^n (x_i - \bar{x})(y_i - \bar{y})\).
  • \(H_0\) is the null hypothesis.
  • \(\alpha\) is the significance level.
  • df is the degrees of freedom.
  • \(p\) is the p-value.

References and further reading

Cohen, G.L., Steele, C.M. & Ross, L.D. (1999). The mentor’s dilemma: providing critical feedback across the racial divide. Personality and Social Psychology Bulletin, 25, 1302–1318.

Popovic, G., Mason, T.J., Drobniak, S.M., Marques, T.A., Potts, J., Joo, R., et al. (2024). Four principles for improved statistical ecology. Methods in Ecology and Evolution, 15, 266–281.

Smith, M.K., Wood, W.B., Adams, W.K., Wieman, C., Knight, J.K., Guild, N. & Su, T.T. (2009). Why peer discussion improves student performance on in-class concept questions. Science, 323, 122–124.

Students who are curious and would like to explore these topics further (purely for their own interest) may find the following resources useful. Material from these resources will not be examined in the final exam, unless it is also already present in the course book.

If you would like to read more about reaction time differences between men and women, this is a quite interesting paper: On the Implications of a Sex Difference in the Reaction Times of Sprinters at the Beijing Olympics, by Lipps et al (2011). The analyses are relatively simple, and the implications explored are quite interesting. Unfortunately, the data used in the paper is not publicly available, so you cannot use it for practice here.

A more detailed data analysis workflow suggestion is here on the Insights from data website.

Here is an article about Exploring The Ethical Implications Of Ai In Data Analytics: Challenges And Strategies For Responsible Implementation. It is rather brief and high-level, but may be of interest when you seek an ethical perspective on the use of AI tools in data analysis.