13.6) Python: Fuzzy RD

6.1) Book Review: Mostly Harmless Econometrics

6.2) Mostly Harmless Econometrics: The Experimental Ideal

6.3) Book Review: Econometric Analysis of Cross Section and Panel Data

6.4) Why Economists created Econometrics methods rather than run Experiments?

6.5) Is Regression a Necessary Tool to Analyze Experimental Data?

6.6) Book Review: A Guide to Econometrics

6.7) Book Review: Econometrics

6.8) Introductory Books for Econometrics

6.9) Mathematical Exposition of Why Random Assignment Eliminates Selection Bias

6.10) Regression Analysis of Experiments

6.11) Field Centipedes

6.12) Bias Caused by Bad Controls

6.13) Structural Econometrics vs Experiment

6.14) Are Emily and Greg More Employable Than Lakisha and Jamal?

6.15) Times Series vs Cross Section vs Panel Data

7.1) Criteria for Estimators: Unbiasedness

7.2) Criteria for Estimators: Efficiency

7.3) Criteria for Estimators: Mean Square Error (MSE)

7.4) Asymptotic Properties of Estimators

7.5) Intuition: Maximum Likelihood Estimator

7.6) Simple vs Multiple Regression

7.7) T-Test vs F-Test: Joint Hypothesis

8.1) Law of Iterated Expectation

8.2) Geometric Interpretation of OLS

8.3) Ordinary Least Squares: Key Assumption

8.4) Conditional Independence Assumption (CIA)

8.5) Unconditional vs Conditional Variance

8.6) Homoskedastic vs Heteroskedasticity Errors

9.1) Minimize the Residual Sum of Squares (RSS)

9.2) OLS Matrix Notation

9.3) Projection Matrix: Idempotent and Symmetric

9.4) Orthogonal Projection Matrix

9.5) Derivation of R-Squared

9.6) Orthogonal Partitioned Regression

10.1) Unbiasedness of OLS

10.2) Consistency of OLS

10.3) OLS: Variance

10.4) Weighted Least Squares (WLS)

10.5) Generalized Least Squares (GLS)

11.1) Omitted Variable Bias: Proxy Solution

11.2) Measurement Error in the Dependent Variable

11.3) Measurement Error in an Explanatory Variable

11.4) Classical Errors-in-Variables and Attenuation Bias

12.1) Instrumental Variables (IV): Assumptions

12.2) Why Instrumental Variable?

12.3) Two-Stage Least Squares (2SLS)

12.4) Python: IV and 2SLS

13.1) Sharp Regression Discontinuity

13.2) Regression Discontinuity in Python

13.3) Regression Discontinuity (RD)

13.4) Fuzzy Regression Discontinuity (FRD)

13.5) Fuzzy vs Sharp RD

13.6) Python Fuzzy RD

14.1) First-Difference Estimator

14.2) Algebra of Difference-in-Differences (DID)

14.3) Python: Diff-in-Diff (DD)

14.4) Quasi-Experiment Diff-in-Diff (DID)

15.1) Fixed Effects (FE): Time-Demeaned

15.2) Random Effects (RE) vs Fixed Effects (FE)

15.3) Random Effects (RE) is Generalized Least Squares (GLS)

15.4) Covariance Matrix: Random Effects (RE)

15.5) Random Effects as a Weighted Average of OLS and FE

15.6) Python: Fixed and Random Effects

[yahiaabdelbar]

Viewing the first stage of the instrument variable was very efficient when being compared to the simple mean comaprison

[Erika]

Hi Professor! What indicates to us in this example that we should use the border distance variable as the running variable?

[davidcriss]

Say we're writing a paper on this. We find that SRD underestimates the impact of Protestants compared with the FRD result. Do we mention the results of both? Or do we only note the FRD result which plainly says the share of Protestants decreases preference for leisure?

[ayoubelmezughi]

Were you saying that the protestant preference fo Leisure is 90 % less in Sharpe regression while it was 13 % less using Fuzzy regression?

[jacobwren]

When using IV2SLS.from_formula(iv, df).fit(), have you ever ran into the error: "ValueError: regressors [exog endog] do not have full column rank"? It seems to be triggered when a dummy variable has too many categories. Not sure of a work around. Thanks.

[carolineadamczyk]

Within the model, do you have to control for population size?