Of many indicators, which few actually carry the signal?
HEC Montréal
StandardScaler inside a pipelineRidge, Lasso, ElasticNet, knowing that scikit-learn calls \(\lambda\) alphaRidgeCV, LassoCV, ElasticNetCVEverything you need to type is on one sheet — how to start Python in VS Codium on your platform, how to make a file and run it, the DataFrame basics, and every name from sessions 1 to 5, each with a line showing it in use.
Python Cheatsheet · Session 05 (PDF) · in the repository at
05-…/PYTHON-CHEATSHEET.pdf
One sheet per package, functions explained with pictures: pandas · NumPy · matplotlib · scikit-learn · statsmodels · SciPy
Print it, or keep it open beside the editor. Nothing on it is examinable; all of it is assumed.
| 00–25 | Test the paper | on the same design, two decades later |
| 25–55 | Apply | the method, to your own angle |
| 55–70 | Break | one assumption, deliberately |
| 70–90 | Write, and report | 250 words, then two minutes to the room |
The presenter is drawn at random when your group is called. All three of you prepare.
Everyone pushes at least once. Replace XX with your group number — group 07 uses group-07.
PowerShell’s mkdir creates the intermediate folders already, and rejects -p. The git log is the participation record. It is not a formality.
Blonigen and Piger ran Bayesian model averaging over 56 candidate determinants of bilateral FDI in 2000, and found about sixteen that mattered. You have the same 56 candidates for 2019.
import numpy as np, qmib
fdi = qmib.load("fdi")
cov = [c for c in fdi.columns if c not in ("parent", "host", "year", "fdi_stock_musd")]
d = fdi[fdi.fdi_stock_musd > 0].dropna(subset=cov) # the log-levels sample
y = np.log(d.fdi_stock_musd)Fit the lasso with \(\lambda\) chosen by cross-validation. Compare what it keeps with the paper’s table 3. Which of their survivors survive for you? Which of their rejects come back?
Standardise inside the pipeline, not before the split. A penalty on \(\beta_j\) is otherwise a penalty on your choice of units.
Paper: Blonigen & Piger (2014), Determinants of foreign direct investment, CJE 47(3) · 10.1111/caje.12091 · data: dictionary
host_is_tax_haven. The paper gave it an inclusion probability of 4%. Look at what it does in 2019, and think about why.A result that disagrees with the paper and is diagnosed earns full marks. One you do not attempt earns none. “It did not work” is not a diagnosis: where did it stop, and what did you check?
core = qmib.load("core")
mine = qmib.load("angle_c_country") # your angle — see your dictionary
df = core.merge(mine, on=["geo", "time"], how="inner")Fit the session’s method on your data, and report what the lecture said to report — in the units of your own variables.
A coefficient without units is not a finding.
Every method in this course rests on something.
Find the assumption this one leans on hardest. Break it deliberately. Record what happened to your answer.
Candidates, if you want one: drop the standardisation · refit on a bootstrap resample and see whether the selected set is the same · keep the zero-FDI pairs instead of logging them away · swap the lasso for the elastic net and watch the correlated pairs come back together.
This is the part that carries the marks. A group that shows how its result falls apart understands it; a group that only shows it holding does not yet know.
250 words in your submissions folder:
And the standing rule: one LLM output you identified as wrong, and how you established that.
git add groups/A2026/group-XX/session-05
git commit -m "Session 05 practice — group XX"
git push -u origin group-XXDeliverable. A penalised fit on your own angle: the path, the chosen \(\lambda\), what survived, and what that does not license you to claim.
And everywhere in this course: an association described in causal language.
| One number | with its units and its uncertainty |
| One assumption | the one you broke, and what happened |
| One limit | what you cannot claim from this |
Listen for traceable evidence, not confidence of delivery.
The QMIB Lab has a knowledge check on what you have just done: warin.ca/qmib-labs
Optional, never a prerequisite for the next lecture, and never marked for correctness. A completed report counts because attempting it is the engagement being measured — it is one of the three routes to the participation mark.
What is required before the next session: the article, the session dataset loaded once, and the self-check. That is the pre-session deck, not this.
MATH60033A · Session 05 practice · Thierry Warin, PhD · HEC Montréal