Part I. Data, Python, and Economic Questions

NREC4107 - Applied Econometrics

Purpose of Part I

Part I introduces the basic workflow of applied econometrics using the actual course milk dataset:

Milk_Data_S2025n.csv

The purpose is not to estimate a model yet. The purpose is to learn how to move from a real dataset to clear empirical questions, careful data inspection, reproducible Python work, and documented cleaning decisions.

The attached dataset contains 258 observations and 11 variables. It includes numeric variables such as Price, Size, Pieces, and Volume, and categorical variables such as Location, Type, Brand, Fat, Fresh, Package, and Flavor.

Why this part matters

Applied econometrics begins before regression. A researcher must first understand:

what each row represents
what each variable measures
which variables are numeric or categorical
whether values are missing
whether constructed variables are consistent
which question the data can reasonably help answer

The course uses Python in Google Colab. The website shows the code, but students run the code in Colab.

Chapters in Part I

Chapter	Topic
Chapter 1	What Is Applied Econometrics?
Chapter 2	Economic Questions and Data Types
Chapter 3	Python, Google Colab, and Reproducible Analysis
Chapter 4	Cleaning and Preparing Agricultural Data

Dataset used in Part I

The running dataset is:

Milk_Data_S2025n.csv

The dataset has the following observed columns:

['Location', 'Type', 'Brand', 'Fat', 'Fresh', 'Price', 'Package', 'Size', 'Pieces', 'Flavor', 'Volume']

The code examples assume the file is saved in Google Drive as:

../data/Milk_Data_S2025n.csv

Students should change the path if they save the file somewhere else.

What students should be able to do after Part I

After completing Part I, students should be able to:

explain applied econometrics as a connection between questions, data, methods, and interpretation
identify numeric and categorical variables in the milk dataset
open Google Colab and load a dataset from Google Drive
inspect missing values, duplicated rows, data types, and constructed variables
explain why cleaning decisions must be documented
distinguish description, association, prediction, and causality

Key message

Good applied econometrics starts with careful data understanding. Software can help us calculate results, but it cannot decide whether the question is meaningful or whether the interpretation is credible.

--- title: "Part I. Data, Python, and Economic Questions" subtitle: "NREC4107 - Applied Econometrics" format: html: toc: true code-fold: false code-tools: true execute: eval: false warning: false message: false --- ## Purpose of Part I Part I introduces the basic workflow of applied econometrics using the actual course milk dataset: ```text Milk_Data_S2025n.csv ``` The purpose is not to estimate a model yet. The purpose is to learn how to move from a real dataset to clear empirical questions, careful data inspection, reproducible Python work, and documented cleaning decisions. The attached dataset contains **258 observations** and **11 variables**. It includes numeric variables such as `Price`, `Size`, `Pieces`, and `Volume`, and categorical variables such as `Location`, `Type`, `Brand`, `Fat`, `Fresh`, `Package`, and `Flavor`. ## Why this part matters Applied econometrics begins before regression. A researcher must first understand: - what each row represents - what each variable measures - which variables are numeric or categorical - whether values are missing - whether constructed variables are consistent - which question the data can reasonably help answer The course uses Python in Google Colab. The website shows the code, but students run the code in Colab. ## Chapters in Part I | Chapter | Topic | |---|---| | [Chapter 1](chapter-01-what-is-applied-econometrics.qmd) | What Is Applied Econometrics? | | [Chapter 2](chapter-02-economic-questions-data-types.qmd) | Economic Questions and Data Types | | [Chapter 3](chapter-03-python-colab-reproducible-analysis.qmd) | Python, Google Colab, and Reproducible Analysis | | [Chapter 4](chapter-04-cleaning-agricultural-data.qmd) | Cleaning and Preparing Agricultural Data | ## Dataset used in Part I The running dataset is: ```text Milk_Data_S2025n.csv ``` The dataset has the following observed columns: ```text ['Location', 'Type', 'Brand', 'Fat', 'Fresh', 'Price', 'Package', 'Size', 'Pieces', 'Flavor', 'Volume'] ``` The code examples assume the file is saved in Google Drive as: ```text ../data/Milk_Data_S2025n.csv ``` Students should change the path if they save the file somewhere else. ## What students should be able to do after Part I After completing Part I, students should be able to: - explain applied econometrics as a connection between questions, data, methods, and interpretation - identify numeric and categorical variables in the milk dataset - open Google Colab and load a dataset from Google Drive - inspect missing values, duplicated rows, data types, and constructed variables - explain why cleaning decisions must be documented - distinguish description, association, prediction, and causality ## Key message Good applied econometrics starts with careful data understanding. Software can help us calculate results, but it cannot decide whether the question is meaningful or whether the interpretation is credible.