Advanced Econometrics Midterm 2

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/243

encourage image

There's no tags or description

Looks like no tags are added yet.

244 Terms

1
New cards

Unbiased estimator

An estimator whose expected value equals the true parameter, E(β̂) = β, across repeated samples.

2
New cards

Consistent estimator

An estimator that converges to the true parameter as the sample size grows, plim β̂ = β.

3
New cards

Efficient (BLUE) estimator

The linear unbiased estimator with the smallest variance, which OLS is under the Gauss-Markov assumptions.

4
New cards

OLS slope after substituting the true model

β̂₁ = β₁ + Σ(xᵢ − x̄)uᵢ / SSTₓ, the starting point for nearly every bias derivation.

5
New cards

Probability limit of the OLS slope

plim β̂₁ = β₁ + Cov(x,u)/Var(x), so OLS is inconsistent whenever x is correlated with the error.

6
New cards

Why Σ(xᵢ − x̄)ū drops out

Deviations from a mean always sum to zero, so ū times Σ(xᵢ − x̄) equals zero.

7
New cards

MLR.4 zero conditional mean

E(u | x₁,…,xₖ) = 0, nothing in the error is systematically related to the regressors.

8
New cards

What MLR.1–MLR.4 deliver

Unbiasedness of the OLS coefficients.

9
New cards

What MLR.1–MLR.5 deliver

OLS is BLUE and the usual variance formula σ²/[SSTⱼ(1 − Rⱼ²)] is correct.

10
New cards

Omitted variable bias formula

E(α̂₁) = β₁ + β₂b₂₁, where b₂₁ is the slope from regressing the omitted x₂ on the included x₁.

11
New cards

Intercept bias with an omitted variable

E(α̂₀) = β₀ + β₂(x̄₂ − b₂₁x̄₁), which stays biased even when b₂₁ = 0.

12
New cards

When omitted variable bias disappears

When the omitted variable has no effect (β₂ = 0) or is uncorrelated with the included regressor (b₂₁ = 0).

13
New cards

OVB sign: β₂ > 0 and Corr(x₁,x₂) > 0

Upward bias, so OLS overstates the effect of x₁.

14
New cards

OVB sign: β₂ > 0 and Corr(x₁,x₂) < 0

Downward bias, so OLS understates the effect of x₁.

15
New cards

Standardized coefficient relationship

γ₁ = β₁·σₓ/σᵧ, and the standardized intercept equals zero because standardized means are zero.

16
New cards

Problems that break only the standard errors

Heteroskedasticity, serial correlation with exogenous regressors, and within-cluster correlation leave β̂ unbiased but SEs wrong.

17
New cards

Problems that break the coefficients

Omitted variables, unit heterogeneity correlated with x, measurement error in x, simultaneity, and lagged y with AR(1) errors.

18
New cards

Heteroskedasticity

The error variance depends on the regressors, Var(u | x) = σᵢ², violating MLR.5.

19
New cards

Effect of heteroskedasticity on OLS coefficients

OLS remains unbiased and consistent, and R² is unaffected.

20
New cards

Effect of heteroskedasticity on inference

OLS is no longer BLUE and conventional standard errors, t, and F statistics are invalid.

21
New cards

OLS variance under heteroskedasticity (8.2)

Var(β̂₁) = Σ(xᵢ − x̄)²σᵢ² / SSTₓ², which reduces to σ²/SSTₓ when variances are equal.

22
New cards

White robust variance (8.3)

Replace each unknown σᵢ² with the squared residual ûᵢ², giving Σ(xᵢ − x̄)²ûᵢ² / SSTₓ².

23
New cards

Why White's estimator works with noisy ûᵢ²

Only the weighted sum is needed, and averaging over many observations washes out the noise in each ûᵢ².

24
New cards

Breusch-Pagan test

Regress squared residuals on the regressors and test joint significance with LM = nR² ~ χ²ₖ or an F test.

25
New cards

Null hypothesis of heteroskedasticity tests

H₀: Var(u | x₁,…,xₖ) = σ², meaning homoskedasticity (MLR.5 holds).

26
New cards

White test

Regress squared residuals on the regressors, their squares, and cross products, then use nR² as a χ² statistic.

27
New cards

Number of regressors in a White test with k = 3

Nine: three levels, three squares, and three pairwise cross products.

28
New cards

Why a dummy reduces White test degrees of freedom

A dummy squared equals itself, so its squared term duplicates the level and is dropped.

29
New cards

Power tradeoff between BP and White tests

BP has high power against linear forms, White catches any form but has lower power against a specific one.

30
New cards

Logging the dependent variable

Often removes heteroskedasticity because proportional errors become additive errors in logs.

31
New cards

Generalized least squares for heteroskedasticity

Divide every term by σᵢ so the transformed error has variance one, making OLS on it BLUE.

32
New cards

Weighted least squares

When Var(u|x) = σ²h(x), divide by √h so noisier observations receive less weight.

33
New cards

Intercept in the WLS-transformed equation

β₀ becomes the coefficient on 1/√hᵢ, so the transformed model has no ordinary intercept.

34
New cards

Feasible GLS (FGLS) for heteroskedasticity

Estimate the variance function from squared residuals, then run WLS with the estimated weights.

35
New cards

Properties of FGLS

Not unbiased, but consistent and asymptotically more efficient than OLS if the variance model is correct.

36
New cards

OLS and FGLS estimates differ greatly

A red flag for misspecification, since both should converge to the same β if the model is right.

37
New cards

Linear probability model variance

Var(y | x) = P(x)[1 − P(x)], so the LPM is heteroskedastic by construction.

38
New cards

Clustered standard errors

SEs allowing any variance and correlation within a group while assuming independence across groups.

39
New cards

Assumption ladder for Var(u|X)

Conventional assumes σ²I, White allows diagonal unequal variances, cluster allows block-diagonal within-unit correlation.

40
New cards

What clustering adds to White's formula

It keeps the within-unit cross terms ûᵢₜûᵢₛxᵢₜxᵢₛ' for t ≠ s that White's method drops.

41
New cards

Moulton factor

V_cluster ≈ [1 + (T − 1)ρᵤρₓ]·V_conventional for equal-size clusters.

42
New cards

Moulton example with T = 10 and ρᵤ = ρₓ = 0.6

The variance rises by a factor of 4.24, so the standard error roughly doubles.

43
New cards

Clustering's asymptotics

Clustered SEs are consistent as the number of clusters grows, not as total observations grow.

44
New cards

Few clusters problem

With fewer than about 30–50 clusters, clustered SEs are biased downward and tests over-reject.

45
New cards

Remedy for few clusters

Use t critical values with n − 1 degrees of freedom or the wild cluster bootstrap.

46
New cards

Correct clustering level for a state policy

Cluster by state, the level at which the key regressor varies and errors are correlated over time.

47
New cards

Why clustering by year fails in a state-year panel

It still treats each state's errors as independent over time, which is the actual problem.

48
New cards

Bertrand, Duflo and Mullainathan placebo laws

Conventional SEs called up to 45% of fake state laws significant, while clustering by state restored about 5%.

49
New cards

Time series data

One unit observed in a meaningful fixed order, a single realization of a stochastic process.

50
New cards

Stochastic process

A random process unfolding over time, {yₜ: t = 1,2,…}.

51
New cards

TS.3 strict exogeneity

E(uₜ | X) = 0 for all t, the error is uncorrelated with regressors in every past and future period.

52
New cards

Contemporaneous exogeneity

E(uₜ | xₜ) = 0, the error is uncorrelated only with same-period regressors.

53
New cards

Strict exogeneity versus contemporaneous exogeneity

Strict exogeneity is needed for unbiasedness, contemporaneous exogeneity is enough for consistency.

54
New cards

Feedback violation of strict exogeneity

A crime shock today raises next year's police hiring, so uₜ is correlated with policeₜ₊₁.

55
New cards

Lagged dependent variable and strict exogeneity

Strict exogeneity always fails because uₜ is part of yₜ, which is a regressor in period t + 1.

56
New cards

TS.5 no serial correlation

Corr(uₜ, uₛ | X) = 0 for all t ≠ s, errors from different periods are uncorrelated.

57
New cards

Why TS.5 has no cross-sectional counterpart

Random sampling delivered independence automatically in cross sections, but ordered time series rarely have it.

58
New cards

What TS.1–TS.6 deliver

Unbiasedness, BLUE, and exact t and F distributions in any sample size.

59
New cards

Static model

yₜ = β₀ + β₁zₜ + uₜ, where β₁ measures only the immediate same-period effect.

60
New cards

Okun's law

Δunemₜ = β₀ + β₁growthₜ + uₜ, with β₁ ≈ −0.5 by Okun's original rule of thumb.

61
New cards

Okun speed limit

The growth rate that holds unemployment steady, g* = β̂₀/(−β̂₁), about 3.15% for the U.S.

62
New cards

Finite distributed lag model

yₜ = α₀ + δ₀zₜ + δ₁zₜ₋₁ + … + δqzₜ₋q + uₜ, letting z affect y over several periods.

63
New cards

Impact propensity

δ₀, the immediate change in y from a one-unit change in z.

64
New cards

Lag coefficient δⱼ

The change in y j periods after a temporary one-unit increase in z.

65
New cards

Long run propensity

LRP = δ₀ + δ₁ + … + δq, the total change in y from a permanent one-unit increase in z.

66
New cards

Why individual lag coefficients are imprecise

Lags of the same variable are highly collinear, so OLS cannot tell which period an effect arrives in.

67
New cards

Why the LRP is precisely estimated

Collinear lag estimates have negative covariances that cancel when summed, shrinking Var(LRP).

68
New cards

LRP reparameterization

Substitute δ₀ = θ₀ − δ₁ − δ₂ so y = β₀ + θ₀zₜ + δ₁(zₜ₋₁ − zₜ) + δ₂(zₜ₋₂ − zₜ) + u reports θ₀ directly.

69
New cards

Spurious regression from trends

Two series trending for unrelated reasons show a large t and high R², with time as the omitted variable.

70
New cards

Fix for trending series

Include a time trend t as a regressor, which by Frisch-Waugh-Lovell is equivalent to detrending all variables.

71
New cards

Exponential trend coefficient

In ln(yₜ) = α₀ + α₁t + eₜ, α₁ is the average growth rate per period.

72
New cards

Detrended R²

1 − SSR/SST of detrended y, measuring how much non-trend variation the regressors explain.

73
New cards

Seasonal dummies

Indicators for all but one month or quarter, equivalent to deseasonalizing every variable.

74
New cards

Seasonal dummies on seasonally adjusted data

They accomplish nothing because the seasonal pattern was already removed.

75
New cards

Exact percent effect of a dummy in a log model

100(e^δ − 1), with 100δ only an approximation for small δ.

76
New cards

Stationary process

A process whose joint distributions are unchanged when shifted in time.

77
New cards

Covariance stationary

Constant mean, constant variance, and covariances that depend only on the lag h, not on t.

78
New cards

Weakly dependent series

A series where Corr(xₜ, xₜ₊ₕ) → 0 as h → ∞, so it eventually forgets its past.

79
New cards

Why weak dependence matters

It replaces random sampling so the law of large numbers and central limit theorem still apply.

80
New cards

MA(1) process

xₜ = eₜ + α₁eₜ₋₁ with white-noise e, which is weakly dependent for any α₁.

81
New cards

MA(1) variance

Var(xₜ) = (1 + α₁²)σₑ².

82
New cards

MA(1) first autocorrelation

Corr(xₜ, xₜ₊₁) = α₁/(1 + α₁²), and correlations at lags two and higher equal zero.

83
New cards

AR(1) process

yₜ = ρ₁yₜ₋₁ + eₜ, today's value is a geometrically weighted sum of all past shocks.

84
New cards

AR(1) stability condition

|ρ₁| < 1, required for the AR(1) to be stable, covariance stationary, and weakly dependent.

85
New cards

AR(1) variance

Var(yₜ) = σₑ²/(1 − ρ₁²), derived from the geometric series 1 + ρ² + ρ⁴ + ….

86
New cards

AR(1) autocorrelation at lag h

Corr(yₜ, yₜ₊ₕ) = ρ₁ʰ, decaying geometrically.

87
New cards

Half-life of a shock in an AR(1)

h = ln(0.5)/ln(ρ), the periods until a shock's effect is halved.

88
New cards

Random walk

yₜ = yₜ₋₁ + eₜ = y₀ + e₁ + … + eₜ, an AR(1) with ρ₁ = 1.

89
New cards

Random walk variance

Var(yₜ) = tσₑ², growing without bound, so the series is not covariance stationary.

90
New cards

Random walk correlation

Corr(yₜ, yₜ₊ₕ) = √(t/(t + h)), which decays so slowly the series is not weakly dependent.

91
New cards

Random walk with drift

yₜ = α₀ + yₜ₋₁ + eₜ, with a linear trend in the mean and variance growing with t.

92
New cards

Adding a trend to a random walk with drift

Removes the drift but not the persistence, so the series is still not weakly dependent.

93
New cards

I(1) process

A series that is not weakly dependent but whose first difference is, also called a unit root process.

94
New cards

I(0) process

A weakly dependent series that is already suitable for OLS.

95
New cards

Typical I(1) series

Price levels, nominal interest rates, exchange rates, GDP, and the money supply.

96
New cards

Typical I(0) series

Growth rates, returns, the unemployment rate, and changes in inflation.

97
New cards

Informal unit root warning sign

A first-order autocorrelation near one, with 0.9 already alarming because ρ̂ is biased toward zero.

98
New cards

Cost of estimating I(1) series in levels

Spurious regression with meaningless t statistics, which is worse than the efficiency loss of overdifferencing.

99
New cards

Spurious regression symptoms with random walks

Too many rejections, a decent R², and a Durbin-Watson statistic near zero.

100
New cards

TS.1′ in the asymptotic assumptions

The series are stationary and weakly dependent and follow a linear model.