Replication of Goolsbee, Lovenheim and Slemrod's 'Playing with Fire: Cigarettes, Taxes and Competition from the Internet' (American Economic Journal: Economic Policy, 2010)
Bibliographic record
Abstract
This study replicates the empirical findings of Goolsbee, Lovenheim and Slemrod (2010) (GLS) and performs a variety of robustness checks. Using taxable cigarette consumption, real cigarette excise tax rates, wholesale cigarette prices, per capita income, and other state-level data for the period 1980-2005, GLS report that rising Internet penetration in the presence of cigarette taxes has a significant causal effect on the elasticity of demand for taxable cigarettes. I am able to exactly replicate GLS’s findings. My robustness checks consist of three parts. First, I check sensitivity to the removal of certain outlier cohorts of states from the data set. Second, I use population unweighted state-year observations in place of GLS’s population-weighted observations. Third, I probe the robustness of GLS’s key interaction term (Internet penetration*cigarette taxes) by (i) adding Internet penetration interaction terms to all main effects in the model and (ii) performing an orthogonalization procedure (Balli and Sorensen, 2013) to prevent the estimate of the key interaction term from picking up the effect of the interaction of the included variables with cigarette taxes due to their correlation with Internet penetration. I found low sensitivity to the first two robustness checks. On the third, GLS’s estimate was robust to the inclusion of additional Internet interaction terms but was not robust to the orthogonalization procedure. This raises the possibility that the effect identified by GLS is an artifact of spurious correlation between Internet penetration and cigarette taxes over time. In sum, GLS’s data may have insufficient power to identify the stand-alone effect of Internet penetration on cigarette tax-sales elasticities in a fully-interacted model.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.029 | 0.121 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.005 | 0.005 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.020 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".