Lecture 1 - Overview and fundamental hurdles

.title[
# Lecture 1 - Overview and fundamental hurdles
]
.subtitle[
## Topics in Econometrics
]
.author[
### Vincent Bagilet
]
.date[
### 2025-09-11
]

---

# Introduction and Steps of Econometric Analyses

???

I introduce myself, they introduce themselves (ask them what they'd like to do later)

---
class: titled, middle

# Objective of the class

- Discuss **practical issues** and challenges that one may face when doing applied economics:

- Help you be aware of some of them
  
  - Provide you with some tools to be able to spot others by yourself

- These hurdles may arise at any step of the research process

- *Topics* class: will not cover everything but instead pick points within topics

---
# Steps of Applied Economics Analyses

- Find, get, wrangle and clean data

- Summary statistics

- Define an identification strategy

- Build a regression model
]
.pull-right[

- Estimate your model

- Specification checks

- Additional inference

- Robustness checks

- Communicate
]

???

- I need a running example here. My MA thesis on gasoline prices? 
- 4: You had a class on this last year, that's fun, that's also very much discussed in economics. Same for 7
- 6: You had a lot of classes and there are a lot of resources on this. That's also very much discussed in economics but clearly, not fun

- 5: Talked about it last year but will talk more about it this year

- For other points, pitfalls less discussed

---
class: titled, middle

# A More Structured Version

- **Design**: decisions of data collection and measurement

- *eg*, decisions related to sample size and ensuring exogeneity of the treatment
  
- **Modeling**: define statistical models

- In between design and analysis

- **Analysis**: estimation and questions of statistical inference

- *eg* standard errors, hypothesis tests, and estimator properties
  
???

- We can actually group these points into relevant categories: take some perspective
- Let's talk about the main thing in the previous list that we will not discuss at all because it is not the purpose of the class: good research questions

---
class: titled, middle

# Outline of the class

1. Overview and fundamental hurdles

1. Simulations

1. Design: beyond identification

1. Design: identification (Fixed Effects and related)

1. Data visualization

1. Design: identification (IV and RDD)

1. Modelling

1. Analysis

???

- Provide more details on the content of each section
1. Data visualization: how can we use data viz to put some of our modeling and identification hypotheses to test?

---
class: right, middle, inverse

# Research questions

---
class: titled, middle

# What is a good research question?

- It **can be answered**

- There is some sort of objective answer

- It should **improve our understanding of the world**

- Should **inform theory** in some way
  
  - Takes us from theory to an hypothesis (statement about what we will observe in the world)
  
- A solid econometric analysis only matters to the extent that you have a good research question (but the opposite might be true as well)

???

---
class: titled, middle

# Example

- Impact of the size of motors of boats in Norway and cod catch under a catch cap

- Not that interesting in itself, is it? Would be more interesting if, for instance:

- Look at this from a game theory and forced technological adoption perspective
  
  - Find a way to use this case to say something *new* or *different* on management of renewable natural resources
  
- Can produce radically different papers on the same topic and setting
  
- **Use theory to put light on your specific case *and* your specific case to inform theory**

???

- Example: motor size of boats in Norway on cod catch, in a situation where we have a catch cap/quota. Not really interesting in itself is it?
- But might be more interesting if for instance you look at this from a game theory perspective and a perspective of forced technological adoption and use this theory to put light on your particular case and your particular case to inform theory
- But

---
class: titled, middle

# Identifying a research question
  
- Can start with a research question/hypothesis or from theory
  
- **Or** can find a natural experiment and come up with a question

- Know your literature to identify **gaps**

- We are interested in **why** and not **what**

- **Avoid data mining**: it can help but to identify questions to test on **other** data sets

---

# Is your research question good?

- **Relevance**: is it interesting, important or policy relevant ?

- **Potential results**: what would any result tell you about your theory?

- **Feasibility**: is the right data available?

- **Scale**: how much resources would you need?

- **Research design**: is there a good one that would allow you to answer your question?

- **Keep it simple**: avoid building several questions into one

???

---
class: right, middle, inverse

# Logistics

---
# Website

https://vincentbagilet.github.io/metrics_m2/

</center>

---
class: titled, middle

# A typical lecture

1. I introduce concepts and intuition

1. We discuss a paper together (when reading assigned)

1. Some R coding together *and* on your own

---
class: titled, middle

# Grading and assignments

|     Assignment     | Percentage of final grade  | Due date           |
|--------------------|:--------------------------:|-------------------:|
| Final report       | 30 %                       | November 7, 8pm    |
| Final presentation | 20 %                       | November 4, 8:30am |
| Participation      | 10 %                       | -                  |
| Replication        | 20 %                       | October 13, 8pm    |
| Homework           | 20 %                       | Throughout         |

---
class: titled, middle

# Final project

- In pairs

- Build a simulation to replicate an analysis you may do in your master thesis

- Generate realistic fake-data, run your analysis and discuss your results

- Project proposal, short report, presentation

---
class: titled, middle

# Structure of the final project

- Structure it as short research paper (pitch):

- Quick motivation and context
  
  - Research question
  
  - Data section: describe how you generate your data. Start very simple, complexify later
  
  - Modeling and analysis: describe your model, your choices and the outputs of your regressions
  
  - Discussion: what did you learn with this exercise

---
class: titled, middle

# Homeworks (due before lecture)

1. -

2. Non-graded assignment

3. -

4. Graded assignment + reading

5. Graded assignment

6. Graded project proposal + reading

7. Replication + reading

8. Graded assignment + reading

---
class: right, middle, inverse

# Fundamental hurdles

---
class: titled, middle

# Typical pitfalls in economics research

.pull-left[
  - Spurious correlation
  
- Reverse causality
  
- Confounders
  
]
.pull-right[
- Model miss-specification

- External validity

- Insufficient power

]

???

- Spurious correlation: that's in part why theory matter

- Examples of estimates informing policy: 
  - Impact of a public policy on an outcome (eg Social Cost of Carbon)
  - If want to choose between different policies which one to implement, etc

---
## Spurious correlation

---
## Reverse causality

---
layout: true

## Confounders

---

[https://forms.gle/tHcTYqaKPeDTAUn56](https://forms.gle/tHcTYqaKPeDTAUn56)

---

---

---

---

---
layout: false

## Model miss-specification

---
class: titled, middle

# Examples of more subtle hurdles

- Bad controls

- Leverage and outliers

- Measurement error

- Clustering level

- How do identification strategies actually work (*eg* FE and TWFE)

- More complex identification strategies (*eg*, shift-share)

---
class: right, middle, inverse

# Avoiding hurdles

---
# How to avoid hurdles?

**Learn**, understand metrics and applied research

???

- Seriously, that can be helpful to avoid doing some wrong stuff
- Knowing that some things do not work, etc

---
class: center
 
<a href="https://en.wikipedia.org/wiki/The_Barque_of_Dante_(Manet)" target="_blank"><img src="data:image/png;base64,#images/manet_delacroix.jpg" width="580" /></a>

*The Barque of Dante* by Manet, after a painting by Delacroix

**Replication**, a helpful learning tool

???

- La barque de Dante d'après Eugène Delacroix par Edouard Manet

---
layout: true

# How to avoid hurdles?

---

### Derive the maths

- Sometimes relatively straightforward and very illuminating

- *eg* drivers of the variance of your estimator: `\(\mathbb{V}_{\hat{\beta}} = \dfrac{\sigma_u^2}{n \sigma_x^2}\)`

- Deriving the maths can be more complex and time consuming

---
### Simulations can help

- Super easy to implement simple simulations

- Can be informative of **what does not work**

- Can help you identify **where the issue comes from**

- We will discuss that with an example in a second
  
---
### Implement checks

- Check if our identification hypotheses seem to hold

- Check if the hypotheses for estimation seem to hold
]

-------

- Robustness checks

- Evaluate the design retrospectively

???

- Think about: identification strategy, but other aspects as well
- We will study these other

---
class: titled, middle
layout: false

# Objectives for this class

- Build a mindful mindset

- Help you be aware of some of them
  
- Provide you with some tools to be able to spot others by yourself

- Learn how to implement simulations

???

- Sim: learn how to implement them but also learn about their usefulness
- Objective for me (beyond helping you learn important material): develop one of my ongoing research articles
- Learn something that may not be often discussed but that is really helpful

---
class: right, middle, inverse

# Simulations

## Usefulness through an example

---
class: titled, middle

# A simple example: OVB

- How does an **omitted variable** affect our point estimate of interest? Why?

- Under which condition is an omitted variable an issue

- How does it affect the point estimate? The s.e.?

- How does that vary with various parameters? *eg* correlation between variable (sign and magnitude)

- Start very simple and complexify the process

- Let's move to R

???

- You may know that before, it is just a very simple example
- Do you know everything there is to know? How does it affect

---
class: right, middle, inverse

# Lecture summary

---
class: titled, middle

# What did we do today?

- Discussed the structure of applied econometric research and where we may encounter hurdles

- Discussed logistics

- Reviewed some of these common hurdles encountered in applied research

- How to implement a simple simulation to understand the impact of an omitted variable

---
class: titled, middle

## What did you learned, liked, disliked?

???

- First class here, with you
- First time teaching my own material
- First time teaching something like this
- I want to have your opinion for next time
- Was it too simple, too complex?

---
class: right, middle, inverse

# Thank you!