# Applied Asymptotics Project
# Module 5 - Module 5 Applied Project
# Dataset: WAGE1

# Applied Asymptotics Project
#
# Learning goal: Plan a complete large-sample inference workflow.

# Dataset check
# This cell confirms the dataset file is available. Simulation notebooks mount a harmless CSV so public file delivery is still validated.

# %% Cell 3
import os
DATASET = "WAGE1.csv"
VARIABLES = ["wage","educ","exper","tenure"]
if not os.path.exists(DATASET):
    raise FileNotFoundError(
        "Dataset file not installed yet\n"
        "Dataset: WAGE1\n"
        "Variables needed: wage, educ, exper, tenure\n"
        "Course data folder: https://drive.google.com/drive/folders/1_STdcydIcst-opcbwOKRFzUXsgxQgBoS?usp=sharing\n"
        "Admin upload instruction: upload the dataset in Admin -> Datasets, publish it, and make the file available to the notebook runner."
    )
print("Ready:", DATASET)

# Run the lab
# Run the code, inspect the table or graph, and connect the result to the formula in the lesson.

# %% Cell 5
import pandas as pd

checklist = pd.DataFrame({
    "step": ["choose datasets", "fit baseline model", "inspect histograms", "simulate sampling", "compare standard errors", "compute LM test", "write limits"],
    "done": [False, False, False, False, False, False, False]
})
print(checklist)
print("Use the Module 5 notebooks to fill this checklist with real outputs and interpretation.")

# Formula explanation
# Explain the probability limit, asymptotic approximation, standard-error pattern, or LM statistic in words. Do not treat output as automatic causal evidence.

# Short exercise
# Change one sample size, regressor, or restriction. Write two sentences: what changed mechanically, and what assumption still matters?
#
# Check your understanding
# Does increasing n fix nonnormality, endogeneity, heteroskedasticity, or omitted variables? Explain.