Skip to content

Metrics Mondays

(Note: The most recent posts will be added to the top of the list, and posts are generally listed from most recent to oldest.)

  1. Claude Montmarquette (1942-2021)
  2. New Version of “The Paper of How: Estimating Treatment Effects with the Front-Door Criterion”
  3. Peter Kennedy, Judea Pearl, or Both?
  4. Assessing the Extent of SUTVA Violations
  5. Advanced Econometrics–Recent Methods and Issues
  6. It’s Written in the Stars
  7. The Paper of How: Estimating Treatment Effects with the Front-Door Criterion
  8. Lagged Variables as Instruments
  9. Least Squares is But One Approach to Linear Regression
  10. When in Doubt, Standardize
  11. New Version of “Elasticities and the Inverse Hyperbolic Sine Transformation”
  12. Recoding Dummy Variables
  13. Learning Machine Learning
  14. Front-Door Criterion Follow-Up
  15. Using the Front-Door Criterion in a Regression Context
  16. Goodness of Fit with Panel Data in Stata
  17. Identification by Functional Form
  18. Copenhagen Course, Lecture 8 (Tricks of the Trade II)
  19. Copenhagen Course, Lecture 7 (Tricks of the Trade I)
  20. Copenhagen Course, Lecture 6 (Nonstandard Dependent Variables)
  21. Copenhagen Course, Lecture 5 (Regression Discontinuity Designs)
  22. Elasticities and the Inverse Hyperbolic Sine Transformation
  23. Copenhagen Course, Lecture 4 (Panel Data and Difference-in-Differences)
  24. Copenhagen Course, Lecture 3 (Instrumental Variables)
  25. Causality and Copenhagen Course, Lectures 1 and 2
  26. Don’t Overcontrol
  27. Survivorship Bias
  28. Identification Is Not Causality, Causality Is Not Identification
  29. What to Do Instead of log(x + 1)
  30. Advanced Econometrics–Causal Inference with Observational Data
  31. Useless Hausman Tests
  32. The Dogit Model
  33. 2SLS–Chronicle of a Death Foretold?
  34. You Can’t Compare OLS with 2SLS
  35. When (Not) to Cluster
  36. Generated Regressors, or Why Regressing on \hat{X} Can Be a Problem
  37. Good Things Come to Those Who Weight–Part I
  38. Regression and Causality for Dummies
  39. Achieving Statistical Significance with Covariates
  40. Dealing with Imperfect Instruments III
  41. We Wrote a Paper About Lagged Explanatory Variables. Here’s What Happened Next.
  42. Interactions as IVs and Spurious Findings
  43. One IV for Two Endogenous Variable, and Testing for Mechanisms
  44. How Should Econometrics Be Taught?
  45. Combining Bits and Pieces of Likelihood to Study Behavior
  46. Fixed Effects, Random Effects, and (Lack of) External Validity
  47. Dealing with Duration Data
  48. Heteroskedasticity and Its Content
  49. Dealing with Imperfect Instruments II
  50. Dealing with Imperfect Instruments I
  51. Testing for Mechanisms (and Possibly Ruling Out All Other Mechanisms)
  52. How to Systematically Think about Selection
  53. Simpson’s Paradox, or Why “Determinants of …” Papers are Problematic
  54. Lagged Explanatory Variables and the Estimation of Causal Effects
  55. Estimating Nonlinear Relationships
  56. Nothing Compares 2 U
  57. Robustness Check or Data Mining?
  58. What to Do with Repeated Cross Sections?
  59. Interpreting Coefficients II
  60. “Are Those Two Distributions Alike?” Redux
  61. Interpreting Coefficients I
  62. Are Those Two Distributions Alike?
  63. What to do When You Have the Whole Distribution Instead of a Sample?
  64. Statistical vs. Economic Significance
  65. Type III Errors
  66. The Tobit Temptation
  67. There Is More than One Source of Endogeneity
  68. Why You Should Show a Regression of Y on Z
  69. Fads and Fashions in Econometrics
  70. Multicollinearity
  71. Friends Do Let Friends Do IV
  72. Regressions as Ecosystems
  73. When Is Heteroskedasticity (Not) a Problem?
  74. Hypothesis Testing in Theory and in Practice
  75. Statistical Literacy
  76. Data Cleaning
  77. Outliers
  78. Proxy Variables
  79. What to Do with Missing Data
  80. What to Do with Endogenous Control Variables
  81. Control Variables: More Isn’t Necessarily Better
  82. You Can’t Test for Exogeneity: Uninformative Hausman Tests
  83. “Do Both”
  84. You Keep Using that Instrumental Variable; I Do Not Think It Does What You Think It Does
  85. PSA: p-Values Are Thresholds, Not Approximations
  86. The Use and Misuse of R-Square
  87. Big Dumb Data?
  88. Rookie Mistakes in Empirical Analysis
  89. Goodness of Fit in Binary Choice Models
  90. A Nifty Fix for When Your Treatment Variable Is Measured with Error
  91. A Rant on Estimation with Binary Dependent Variables
  92. Love It or Logit, or: Man, People *Really* Care about Binary Dependent Variables
  93. In Defense of the Cookbook Approach to Econometrics
  94. More on the Cookbook Approach to Econometrics
  95. Econometrics Teaching Needs an Overhaul
  96. Hipstermetrics
  97. On the (Mis)Use of Regression Analysis: Country Music and Suicide
  98. Methodological Convergence in the Social Sciences