Podcast
Questions and Answers
What does the Wald test require for hypothesis testing?
What does the Wald test require for hypothesis testing?
- Estimation of both restricted and unrestricted models
- Estimation of only the unrestricted model (correct)
- Estimation only if the likelihood function is maximized
- Comparison of multiple restricted models
In a likelihood ratio test, what does a larger decrease in the likelihood function indicate?
In a likelihood ratio test, what does a larger decrease in the likelihood function indicate?
- The restriction does not hold (correct)
- The restricted model is preferred
- The unrestricted model is better
- The restriction is likely to hold
What is the distribution of the likelihood ratio test statistic under the null hypothesis?
What is the distribution of the likelihood ratio test statistic under the null hypothesis?
- Poisson distribution
- Chi-squared distribution (correct)
- Binomial distribution
- Normal distribution
Which model type is applicable when the dependent variable is binary?
Which model type is applicable when the dependent variable is binary?
What characterizes Limited Dependent Variable (LDV) models?
What characterizes Limited Dependent Variable (LDV) models?
Which estimation methods are used for a count model?
Which estimation methods are used for a count model?
If a dependent variable y is limited to the range [a, b], what type of model is this?
If a dependent variable y is limited to the range [a, b], what type of model is this?
In qualitative response models, how are the values of the dependent variable characterized?
In qualitative response models, how are the values of the dependent variable characterized?
What is the significance of consistency for an estimator in econometrics?
What is the significance of consistency for an estimator in econometrics?
In the context of multiple regression modeling, what does the notation $y = Xβ + ε$ represent?
In the context of multiple regression modeling, what does the notation $y = Xβ + ε$ represent?
Which statement best describes the law of large numbers in relation to estimators?
Which statement best describes the law of large numbers in relation to estimators?
When discussing regressors in multiple regression models, what does $K$ represent?
When discussing regressors in multiple regression models, what does $K$ represent?
What does the term 'unbiasedness' of an estimator signify?
What does the term 'unbiasedness' of an estimator signify?
What does $etâ_j
ightarrow eta_j$ imply regarding estimators?
What does $etâ_j ightarrow eta_j$ imply regarding estimators?
What type of data censoring occurs when some values are not observed above a certain threshold?
What type of data censoring occurs when some values are not observed above a certain threshold?
What role does the error term $ε_i$ serve in the regression model $y_i = x_iβ + ε_i$?
What role does the error term $ε_i$ serve in the regression model $y_i = x_iβ + ε_i$?
In a censored regression model, which variable is always observed?
In a censored regression model, which variable is always observed?
Why is consistency considered a minimal requirement for estimators in econometrics?
Why is consistency considered a minimal requirement for estimators in econometrics?
What does the parameter β represent in the latent variable framework of censored models?
What does the parameter β represent in the latent variable framework of censored models?
What is an example of a variable that may be right-censored?
What is an example of a variable that may be right-censored?
Which of the following statements is true regarding a censored regression model?
Which of the following statements is true regarding a censored regression model?
What type of models are used for analyzing choice among unordered alternatives?
What type of models are used for analyzing choice among unordered alternatives?
In a multinomial logit model, what does the term 'βj' represent?
In a multinomial logit model, what does the term 'βj' represent?
What do the values of the dependent variable typically represent in qualitative response models?
What do the values of the dependent variable typically represent in qualitative response models?
Which alternative estimation method is noted as more complex than multinomial logit?
Which alternative estimation method is noted as more complex than multinomial logit?
In the explained multinomial logit formula, what does the expression 'exp{xi βj}' represent?
In the explained multinomial logit formula, what does the expression 'exp{xi βj}' represent?
What does the log odds ratio imply about the coefficient βj?
What does the log odds ratio imply about the coefficient βj?
Which STATA command is used for multinomial logit estimation?
Which STATA command is used for multinomial logit estimation?
Ordered response models are best suited for analyzing which type of alternatives?
Ordered response models are best suited for analyzing which type of alternatives?
What is the primary purpose of the Tobit model?
What is the primary purpose of the Tobit model?
In the Tobit model, what does the notation $yi∗$ represent?
In the Tobit model, what does the notation $yi∗$ represent?
What is the main estimation method used for the Tobit model?
What is the main estimation method used for the Tobit model?
Which of the following is a characteristic of count models?
Which of the following is a characteristic of count models?
In the Poisson count model setup, what does $E[yi |xi]$ represent?
In the Poisson count model setup, what does $E[yi |xi]$ represent?
What kind of distribution is assumed for $yi$ in the Poisson count model?
What kind of distribution is assumed for $yi$ in the Poisson count model?
What does the term $F(xi β)$ imply in the context of the Poisson count model?
What does the term $F(xi β)$ imply in the context of the Poisson count model?
In the context of the Tobit model, how are marginal effects interpreted?
In the context of the Tobit model, how are marginal effects interpreted?
What does the marginal effect represent in the context of probit/logit models?
What does the marginal effect represent in the context of probit/logit models?
In the equations provided, what does $y_i^*$ represent?
In the equations provided, what does $y_i^*$ represent?
Which of the following is NOT a common option for reporting marginal effects?
Which of the following is NOT a common option for reporting marginal effects?
What is the purpose of using maximum likelihood estimation (MLE) in the context of probit/logit models?
What is the purpose of using maximum likelihood estimation (MLE) in the context of probit/logit models?
Which command would you use in STATA to compute marginal effects after running a probit model?
Which command would you use in STATA to compute marginal effects after running a probit model?
What is the significance of the error term ($ε_i$) in the latent variable model?
What is the significance of the error term ($ε_i$) in the latent variable model?
What is the role of the indicator function $y_i$ in the model?
What is the role of the indicator function $y_i$ in the model?
Which marginal effect calculation considers only the average of marginal effects across observations?
Which marginal effect calculation considers only the average of marginal effects across observations?
Flashcards
Consistency (asymptotics)
Consistency (asymptotics)
A minimal requirement for an estimator in econometrics. An estimator is consistent if, as the sample size (n) gets infinitely large, its value gets closer and closer to the true value of the parameter it estimates.
Estimator
Estimator
A rule or formula used to calculate an estimate of a population parameter from a sample of data.
Multiple Regression Model
Multiple Regression Model
A statistical model that describes the relationship between a dependent variable and multiple independent variables. It allows predicting the dependent variable based on several factors.
Independent Variables
Independent Variables
Signup and view all the flashcards
Dependent Variable
Dependent Variable
Signup and view all the flashcards
plim β̂j −→ βj
plim β̂j −→ βj
Signup and view all the flashcards
Law of Large Numbers
Law of Large Numbers
Signup and view all the flashcards
Marginal Effect
Marginal Effect
Signup and view all the flashcards
Probit Model
Probit Model
Signup and view all the flashcards
Logit Model
Logit Model
Signup and view all the flashcards
Latent Variable
Latent Variable
Signup and view all the flashcards
Marginal Effects at Sample Mean
Marginal Effects at Sample Mean
Signup and view all the flashcards
Marginal Effects Evaluation
Marginal Effects Evaluation
Signup and view all the flashcards
Maximum Likelihood Estimation (MLE)
Maximum Likelihood Estimation (MLE)
Signup and view all the flashcards
STATA Commands for Probit/Logit
STATA Commands for Probit/Logit
Signup and view all the flashcards
Wald Test
Wald Test
Signup and view all the flashcards
Likelihood Ratio Test
Likelihood Ratio Test
Signup and view all the flashcards
Likelihood Function
Likelihood Function
Signup and view all the flashcards
LR Test Statistic
LR Test Statistic
Signup and view all the flashcards
χ² Distribution
χ² Distribution
Signup and view all the flashcards
q (in LR test)
q (in LR test)
Signup and view all the flashcards
Limited Dependent Variable (LDV) Models
Limited Dependent Variable (LDV) Models
Signup and view all the flashcards
Binary Models
Binary Models
Signup and view all the flashcards
Censored Models
Censored Models
Signup and view all the flashcards
Count Data Models
Count Data Models
Signup and view all the flashcards
Qualitative Response (QR) Models
Qualitative Response (QR) Models
Signup and view all the flashcards
Qualitative Response Models
Qualitative Response Models
Signup and view all the flashcards
Tobit Model
Tobit Model
Signup and view all the flashcards
Multinomial Logit
Multinomial Logit
Signup and view all the flashcards
Tobit Model: Latent Variable yi*
Tobit Model: Latent Variable yi*
Signup and view all the flashcards
Tobit Model: Estimation
Tobit Model: Estimation
Signup and view all the flashcards
Multinomial Logit Equation
Multinomial Logit Equation
Signup and view all the flashcards
Choice Specific Coefficients (βj)
Choice Specific Coefficients (βj)
Signup and view all the flashcards
Tobit Model: Parameter Interpretation
Tobit Model: Parameter Interpretation
Signup and view all the flashcards
Log Odds Ratio
Log Odds Ratio
Signup and view all the flashcards
Count Models
Count Models
Signup and view all the flashcards
Poisson Count Model
Poisson Count Model
Signup and view all the flashcards
Multinomial Probit
Multinomial Probit
Signup and view all the flashcards
Ordered Response Models
Ordered Response Models
Signup and view all the flashcards
Poisson Model: E[yi|xi]
Poisson Model: E[yi|xi]
Signup and view all the flashcards
Poisson Model: Estimation
Poisson Model: Estimation
Signup and view all the flashcards
Censored Regression Models
Censored Regression Models
Signup and view all the flashcards
Right Data Censoring
Right Data Censoring
Signup and view all the flashcards
Latent Variable
Latent Variable
Signup and view all the flashcards
Censoring Thresholds
Censoring Thresholds
Signup and view all the flashcards
Observed Values
Observed Values
Signup and view all the flashcards
Maximum Likelihood Estimation (MLE)
Maximum Likelihood Estimation (MLE)
Signup and view all the flashcards
Income/Wealth Top-Coding
Income/Wealth Top-Coding
Signup and view all the flashcards
Age at First Birth
Age at First Birth
Signup and view all the flashcards
Impact of x on y*
Impact of x on y*
Signup and view all the flashcards
Study Notes
Advanced Econometrics (ADEC-3070)
- Course offered by Dr. Manini Ojha
- JSGP Elective
- Fall, 2024
Lectures
- Not designed for proficiency in specific models, but rather exposure to many models.
- Key takeaway: No estimator is guaranteed to yield consistent estimates.
- Every estimator relies on a set of assumptions.
- Validity of estimates depends on the validity of underlying assumptions.
- Crucial to understand these assumptions for conducting and assessing applied work.
- Assumptions may no longer hold during the data collection process (measurement error, sample selection, etc.).
Recap: OLS
-
Classical Linear Regression Model (CLRM): yᵢ = α + βxᵢ + εᵢ, i = 1, ..., N
-
α, β = population parameters
-
â, β = parameter estimates
-
εᵢ = idiosyncratic error term (reflects randomness, unobserved factors)
-
Exercise: State the OLS assumptions.
Assumptions
- (A1) Linearity: yᵢ = α + βxᵢ + εᵢ, i = 1, ..., N
- α, β = population parameters
- εᵢ = disturbance or error term (randomness, unobserved factors)
- (A2) Expected value of error: E[εᵢ] = 0
- (A3) Variance of error: E[εᵢ²] = σ²
- (A4) Covariance of errors: E[εᵢεⱼ] = 0 for i ≠ j
- (A5) Error and regressors: E[εᵢxᵢ] = 0
- (A6) Error distribution: εᵢ ~ N(0, σ²)
OLS Estimation
- Given a random sample {yᵢ, xᵢ}ᵢ₋₁ⁿ, OLS minimizes the sum of squared residuals:
- â, β = argmin ∑ᵢ₋₁ⁿ (yᵢ – â – βxᵢ)²
OLS Solution
- Implies BOLS and AOLS
- BOLS = Cov(yᵢxᵢ) / Var(xᵢ)
- AOLS = ỹ - BOLS*x
Properties of OLS
- â, ẞ are unbiased (finite sample property) and consistent (asymptotic property).
- â, ẞ are efficient (smallest variance of any linear, unbiased estimate).
- Var(β) = σ² / Σᵢ₋₁ⁿ (xᵢ – x)²
Consistency
- As sample size grows, the distribution of β becomes tightly distributed around β.
- For a sufficient collection of data, the estimator is arbitrarily close to β₁.
Maximum Likelihood Estimation (MLE)
- Alternative estimation technique to OLS.
- Equivalent to OLS in classical linear regression models.
- Useful for nonlinear models.
- Maximizes the probability of drawing the observed data given the parameters
- To get ML estimators: need an expression for the likelihood function.
- likelihood function: total probability of observing the realized data (L(θ)).
- joint probability distribution of the data = likelihood function L(θ).
- L(θ) = ∏ᵢ₋₁ⁿ [f(yᵢ|θ)]
Example CLRM
- yᵢ = xᵢβ + εᵢ, εᵢ ~ N(0, σ²)
- Pr(yᵢ|xᵢ, θ) = 1 / (2πσ²) exp[ – (yᵢ – xᵢβ)²/2σ²]
Properties of MLE
- Consistent: plim(θ̂ₙ) = θ
- Asymptotically normal
- Asymptotically efficient
Hypothesis Testing (MLE)
- Wald tests: Equivalent to F-test in OLS.
- Likelihood ratio test : Estimate both restricted and unrestricted model. Compute LR and Lυr
- Intuition: Restrictions/dropping variables generally lead to smaller L(θ).
Likelihood Ratio Test (contd.)
- Test statistic : LR = 2[Lυr – Lr]
- Where q: # of restrictions; LR ~ x²q .
- Maximization typically by numerical methods since analytical derivatives are messy.
Limited Dependent Variable Models (LDV)
- Models where dependent variable(s) is/are not continuous
- Common types: • Binary models (y ∈ {0, 1}) • Censored regression models (y ∈ [a, b]) • Count models (y ∈ {0, 1, 2,...}) • Qualitative response models (y ∈ {0, 1, 2,...})
Binary Models
- Applicable to problems where the dependent variable is binary.
- Examples: Labor force participation, default on a loan, belonging to an FTA.
Linear Probability Model (LPM)
- Setup: yᵢ = xᵢβ + εᵢ , where ɛ; ~ Ν(0, σ²) .
- Estimated by OLS.
- Problems: Heteroskedasticity
- Predictions are not bounded by 0 and 1 (xᵢβ ∉ [0, 1]
- Doesn't correspond to probabilities.
Probit and Logit Models
- Used when dependent variable is binary.
- Models Pr(yᵢ = 1|xᵢ) using a "proper" functional form Pr(yᵢ = 1|xᵢ) = F(xᵢβ)
- F(•) is a cumulative distribution function (CDF).
- Possible solutions include CDFs.
Interpretation of B
- Marginal Effect = dPr(yᵢ = 1) / dxᵢ = dF(xᵢβ) /dxᵢ
- dF(xβ) / dx₁ = { φ(xβ) / dx₁ for probit ; λ(xβ)[1 – Λ(xβ)] / dx₁ for logit}.
Latent Variable Framework
- Probit logit model framed in unobserved variable framework.
- y*= xβ + ε
STATA Commands
- -probit-
- -logit-
- -dprobit-
- -margin-
- -mfx-
- -tobit
- -cnreg-
Censored Regression Models
- Applicable to problems where dependent variable is censored.
- Right censoring/top-coding
- Examples: Income, wealth, age.
Latent Variable Framework - Censored Models
- Model setup: y*= xβ + ε, where yᵢ = {bᵢ if y* ≥ bᵢ, y* if aᵢ ≤ y* ≤ bᵢ , and aᵢ if y* ≤ aᵢ.}
Tobit Model
- Special case of censored regression models.
- aᵢ=0 , bᵢ → ∞ ; y = {y* if y* > 0 and 0 if y* ≤ 0}.
Count Models
- Applicable to non-negative integer counts of events.
- Examples include number of children, patents, doctor visits.
Poisson Count Model
- Want to model the expected number of events conditional on x, E[yi|xi]= F(xiβ) .
- F(•) ≥ 0.
- Estimation via MLE using Poisson distribution (depends only on the mean).
Additional Estimation Methods for Count models
- Negative binomial
- Zero-inflated Poisson
Qualitative Response Models
- Analyzing choice by agents from many disordered alternatives.
- Examples include brand choice, mode of transportation, types of mortgage, schools
Multinomial Logit
- Model to estimate probabilities of J+1 alternatives given x, Pr(y₁ = j|xᵢ, 0) = [exp(x¡βj) / ∑k exp(x¡βk)].
- Interpreting ẞ: log odds ratio (relative to base choice)
Alternative Estimation Methods
- Multinomial probit (more complex).
- Nested logit
Ordered Response Models
- Analyzing choice by agents from many ordered alternatives.
- Examples include labor force status, schooling, bond ratings.
- Outcomes are discrete integers: 0, 1, 2... Using logit/probit framework, y* = xβ + ε.
Applications and Examples
- Studies by various authors including examples for testing different econometric models using STATA.
Panel Data
- Studying multiple draws on the same basic unit of observation (group).
- Examples: individuals in a household over time.
Pooled OLS
- Estimating relationship with multiple time periods from cross-sectional data.
- Estimation is similar to OLS with a larger sample size (NT).
Extensions of panel data
- Time trend, Quadratic time trend & Structural breaks allowing intercepts to change over time
- Time-specific intercepts, allowing intercept to vary across time periods.
Chow test
- Used to test if there is a break, or change, in the relationship between variables over time.
- H0 : α1 = α2, β₁ = β2; H1 : not all equal
Difference-in-difference estimation
- Frequently used in policy analysis
- Used to analyze the impact of a policy on the outcome given the same variables at different time periods
- Examples: Minimum wage hike, legalized abortion on crime or the death penalty on crime.
Fixed effects
- Used to account for omitted variable bias, variables that do not change across groups.
- Similar setup but allow for individual-specific intercepts
Stata Commands
- -xtreg- (for panel data).
- -fe (Fixed effects).
- -fd (first differences).
- -areg (for average effects).
- -ivreg2- (Instrumental variables regression).
- -mlogit- (for multinomial logit).
- -mprobit- (for multinomial probit).
- -reg-,-probit-, -logit-
Endogenous Variables
- Variables whose change in the model outcome are correlated to changes in other variables. This can lead to biased estimators if the change in the variable is interpreted to only depend one the variable being investigated.
Instrument Variables
- Method used to address endogeneous variables bias in a model where the variable(s) being investigated, are correlated to error terms in the model, or other dependent variables.
- This can be corrected by using an instrumental variable which is correlated with the dependent variable in the model, but not affected by error terms or other dependent variables.
Omitted Variable Bias, Reverse Causation
- Explain how these issues can lead to biased results, what conditions are necessary for this to happen, and alternative methods to analyze the models
Measurement Error
- Explain how data that are measured imprecisely can lead to biased results, how to deal with this problem in panel data, and how to interpret results.
Studying That Suits You
Use AI to generate personalized quizzes and flashcards to suit your learning preferences.