Vector Autoregressions as a Guide to Constructing Dynamic General Equilibrium Models

Size: px
Start display at page:

Download "Vector Autoregressions as a Guide to Constructing Dynamic General Equilibrium Models"

Transcription

1 Vector Autoregressions as a Guide to Constructing Dynamic General Equilibrium Models by Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson 1

2 Background We Use VAR Impulse Response Functions as Guide to Constructing Monetary DSGE Models Basic Strategy: Choose Model Parameters to Make Model-based Impulse Responses as Close as Possible to VAR-based Impulse Responses. Problem: The Usefulness of Vector Autoregressions Has Been Questioned For Example: CKM Question the Use of VARs with Long-Run Restrictions... CKM Argue (as do Others) That First Differencing Hours Worked When Hours are Stationary Can Lead to Incorrect VAR Inference (DSVARS) Here, We are Concerned With their Findings for LSVARS, When Hours are Correctly Specified in Levels CKM Report Two Major Findings. VARs Increasingly Distorted and Misleading as Datasets Grow We Do Not Find This. VARs Are Uninformative in Small Samples. We Disagree. 12

3 Findings All Findings Based on Running VARs in Data Generated by DSGE Models. Long-Run Exclusion and Sign Restrictions Our Examples: As Long As there are Enough Variables in the Analysis - Inference from VARs Reliable. There May be Substantial Sampling Uncertainty But, A Conceptual Error Leads CKM to Greatly Overstate that Uncertainty. In Any Case, VAR Methods Accurately Characterize Uncertainty. A User of VARs Would Not Be Misled in Practice Short-Run Exclusion and Sign Restrictions Our Examples Suggest No Evidence of Small-Sample Bias Relatively Little Sampling Uncertainty Robust to Which Variables are Included in VAR 2

4 Outline Analysis Based on Simple RBC Model Long Run Restrictions Short Run Restrictions Analysis Based on Monetized RBC Models With Various Frictions (ACEL) 18

5 DGP: A Generic RBC Model Preferences: E X t= (β (1 + γ)) t log c t + ψ log l lt. Constraints: c t +(1+τ x,t )[(1+γ) k t+1 (1 δ) k t ] (1 τ lt ) w t l t + r t k t. Shocks: c t +(1+γ) k t+1 (1 δ) k t k α t (Z t l t ) 1 α. log (Z t )=µ Z +log(z t 1 )+σ z ε z t, τ lt+1 =(1 ρ l ) τ l + ρτ lt + σ l ε d t+1, τ xt+1 = ρ x τ xt + σ x ε x t+1. 22

6 Quarterly Model: CKM Parameter Values Nonstochastic Part /4 5/4 Parameters Estimated by Maximum Likelihood: log ( )=154+log( 1 ) =(1 938) Following Parameters Vary Across Examples. +1 =

7 Alternative Parameterizations of RBC Model Prescott Version (One Important Shock) log ( )=154+log( 1 )+1 +1 = = CKM Benchmark (Two Important Shocks) log ( )=154+log( 1 ) =(1 938) = 22

8 Alternative Parameterizations of RBC Model... Three Shocks, Two Important log ( )=154+log( 1 ) =(1 938) =1 Three Important Shocks log ( )=154+log( 1 ) =(1 938) =

9 Using VARs to Estimate the Effects of a Positive Technology Shock VAR: = = =, = = = log log =[ ] = 1 2 = 3 Impulse Response to Positive Technology Shock ( 1 ): 1 = = = Need:

10 Identification Problem From Applying OLS To Both Equations in VAR, We Know : 1 Problem, Need first Column of 1 Restrictions (Bivariate Case): three equations in four unknowns = Identification Problem: Not Enough Restrictions to Pin Down 1 Need More Restrictions 25

11 Identification Problem... Two Key Properties of DGP: Long-Run Exclusion Restriction: lim [ ]=( only) Sign Restriction: increasing in These Properties Provide Sufficient Restrictions to Pin Down 1 26

12 Characterizing Restrictions Note: [ +1 ] 1 [ +1 ]=[ ]+[ 1 ] Then ( =1) [ +1 ] 1 [ +1 ]=(1 ) [ + ] [ +2 ] 1 [ +2 ]=(1 ) [ + ] 1 [ + ]=(1 ) as : lim [ + ] 1 [ + ] = lim (1 ) =(1) [ ] 1 29

13 Characterizing Restrictions... As j (for arbitrary p) : lim j E t[a t+j ] E t 1 [a t+j ]=(1, ) [I B(1)] 1 Ce t 37

14 Characterizing Restrictions... The VAR: X t = B 1 X t 1 + B 2 X t B p X t p + u t Identification: Solve for C Such that - (exclusion restriction) (1, 2) element of [I B(1)] 1 C = number,..., numbers numbers (sign restriction) (1, 1) element of [I B(1)] 1 C is positive CC = V There Are Many C That Satisfy These Constraints. All Have the Same C 1. 38

15 Let Proof of Uniqueness of C 1 D [I B(1)] 1 C so, DD = [I B(1)] 1 V [I B(1) ] 1 S (Since CC = V ) Exclusion Restriction Requires: D = d11 D 21 D 22 So d DD 2 = 11 d 11 D21 D 21 d 11 D 21 D21 + D 22 D22 = Sign Restriction: d 11 >. Then, First Column of D Uniquely q Pinned Down: d 11 = S 11,D 21 = S 21 /d 11 First Column of C Uniquely Pinned Down: C 1 =[I B(1)] D 1. S 11 S 21 S 21 S

16 Proof of Uniqueness of C 1... Remark: Sign of C 11 (Impact Effect of Technology Shock) unrestricted (1, 1) Element of [I B(1)] 1 C Must Be Positive (Long Run Effect) Could Lead to Contemporaneous Drop in Productivity 41

17 Proof of Uniqueness of C 1... Remark: Sign of C 11 (Impact Effect of Technology Shock) unrestricted (1, 1) Element of [I B(1)] 1 C Must Be Positive (Long Run Effect) Could Lead to Contemporaneous Drop in Productivity Remark: CKM Sign Restriction: C 11 >, (1, 1) Element of [I B(1)] 1 C unrestricted Positive Technology Shock Leads to Contemporaneous Rise in Productivity Positive Technology Shock Could Lead to Permanent Reduction in Productivity This Pattern is Impossible in CKM DGP 42

18 Assessing the VAR With Long-Run Restrictions Using RBC as DGP Experiments Simulate 5 Artificial Data Sets, Each of Length 18 From Various Versions of DGP Estimate VAR On Each Artificial Data Set and Compute Dynamic Response of Hours to Positive Technology Shock Report Mean Impulse Response Function and Plus/Minus Two Standard Error Bounds (Grey Area) 39

19 Assessing the VAR With Long-Run Restrictions Using RBC as DGP... General Findings: If there are Enough Variables, Relative to the Number of Important Shocks to the Economy, then VAR Reliable Precision May be Low, But VAR Will Tell You When this is So. Often, But not Always, One Can Discriminate Between Interesting Hypotheses CKM Finding of Enormous Sampling Uncertainty Reflects CKM s Mistaken Sign Restriction We are Less Pessimistic than CKM About What Happens as More Data Come In (These Findings are Somewhat Tentative, Until We Fully Understand Why Our Results Differ from CKM.) 42

20 Notes on Figures and 1 Figure : Prescott RBC Model with Standard Deviation,.1, on Technology Shock Other Shocks Tiny: +1 = +1 = Range of Impulse Responses Small If the Model is True, Econometrician Would Reject Interesting Alternatives (e.g., King-Wolman and Francis-Ramey Models in Which Hours Fall After Technology Shock). This presumes that +/- 2 standard deviation bounds in Figure corresponds to confidence intervals that an econometrician would find if the model were true. In fact, Figure 2 indicates that this is a reasonable approximation. Fig 2 reports the actual standard deviation of econometrician s estimator of the impulse response function (light blue line with dots) as well as the mean (and plus/minus two standard error bands) of the econometrician s bootstrap estimator of standard 43

21 Notes on Figures and 1... deviation. Impulse Response Functions Estimated Very Tightly Can Easily Exclude Interesting Alternatives 44

22 Notes on Figures and 1... Figure 1: 1,1 Element: Two Variables, One Important Shock CKM Estimated Technology Shock Process Other Shocks Tiny: +1 = +1 = Same as in Figure 1,2 Element: Two Variables, Two Important Shocks - Benchmark CKM Example CKM Estimated Technology and Labor Tax Shocks +1 = Substantial Small Sample Bias Sampling Uncertainty Reported Here VERY Different from That Reported for Same Example in CKM (Will Return to this Below). 45

23 Notes on Figures and ,1 Element: Three Variables, Two Important Shocks CKM Estimated Technology and Labor Tax Shock Process Investment Price Shock: +1 =1 +1 VAR Bias Disappears. Sampling Uncertainty Higher, Harder to Reject Interesting Hypotheses 2,2 Element: Three Variables, Three Important Shocks CKM Estimated Technology and Labor Tax Process CKM Price of Investment Example: +1 = Small Sample Bias Reappears 46

24 Notes on Figures and ,2 Element: Four Variables, Three Important Shocks Add to Data in VAR, Plus Additive Measure Error with.1 Standard Deviation CKM Estimated Technology and Labor Tax Process CKM Price of Investment Example. Bias is Gone, But Sampling Uncertainty is Substantial. 47

25 Figure : Bivariate VAR, Prescott RBC Model Mean, Small Sample VAR True Plus, Minus 2 Standard Deviations Quarters Percent Response in Hours to One-Standard Deviation (1 Percent) Technology Shock

26 Bivariate VAR Small: Two Variables, One Important Shock Variables Small: Three Variables, Two Important Shocks Variables CKM: Four Variables, Three Important Shocks Bivariate VAR CKM: Two Variables, Two Important Shocks Variables CKM: Three Variables, Three Important Shocks

27 1.5 Bivariate VAR Small 1.5 Bivariate VAR CKM Variables Small Variables CKM Variables CKM

28 What We Learn From the Examples in Figures and 1: Tentative Conclusion: VAR Inference With Long-Run Identification Not Misleading As Long as there Are Enough Variables in the Analysis. Need at Least One More Variable than the Number of Important Shocks Driving the Data In Practice: Roughly 4-5 Variables (see Sargent-Sims, Quah-Sargent, Uhlig ( What moves real GDP? ), who show that 3-4 shocks account for most fluctuations; see Prescott (1986) who argues 1 shock account for 7% of fluctuations.). 5

29 How Big is the Sampling Uncertainty Associated with Long-Run Identifying Restrictions? CKM Provide a Misleading Answer to this Question Problem: CKM Sign Restriction Leads Them To Confuse Positive and Negative Technology Shocks 51

30 How Big is the Sampling Uncertainty Associated with Long-Run Identifying Restrictions?... Benchmark CKM Model Initial Hours Worked Response Strong, Productivity Response Weak (Fig 3) 52

31 Response of Hours Worked and Labor Productivity in Benchmark CKM Example.65 Labor Productivity Hours Worked

32 How Big is the Sampling Uncertainty Associated with Long-Run Identifying Restrictions?... Benchmark CKM Model Initial Hours Worked Response Strong, Productivity Response Weak (Fig 3) Consequences of CKM Sign Restriction In Some Samples, Hours Response Very Strong and Initial Productivity Small Negative CKM Algorithm Calls this a Negative Technology Shock In These Cases, Their Procedure In Effect Multiplies the Hours Response by -1 (Fig 3a). 53

33 Figure 3a: Example of Mistaken Inference.6 productivity (LR).2 productivity hours (LR) hours

34 How Big is the Sampling Uncertainty Associated with Long-Run Identifying Restrictions?... Benchmark CKM Model Initial Hours Worked Response Strong, Productivity Response Weak (Fig 3) Consequences of CKM Sign Restriction In Some Samples, Hours Response Very Strong and Initial Productivity Small Negative CKM Algorithm Calls this a Negative Technology Shock In These Cases, Their Procedure In Effect Multiplies the Hours Response by -1 (Fig 3a). Is this a Theoretical Curiosum? No...It Happens 23% Of Time. Leads to Pronounced Bimodal Distribution of Impact Effects (upper panel, Fig 4) 54

35 1 Hours Impact.1 Labor Productivity Response

36 How Big is the Sampling Uncertainty Associated with Long-Run Identifying Restrictions?... Benchmark CKM Model Initial Hours Worked Response Strong, Productivity Response Weak (Fig 3) Consequences of CKM Sign Restriction In Some Samples, Hours Response Very Strong and Initial Productivity Small Negative CKM Algorithm Calls this a Negative Technology Shock In These Cases, Their Procedure In Effect Multiplies the Hours Response by -1 (Fig 3a). Is this a Theoretical Curiosum? No...It Happens 23% Of Time. Leads to Pronounced Bimodal Distribution of Impact Effects (upper panel, Fig 4) Actual Distribution of Impact Effects Not Bimodal (lower panel, Fig 4). 55

37 1 Hours Impact.1 Labor Productivity Response Hours Impact 1 x 1 3 Labor Productivity Response

38 How Big is the Sampling Uncertainty Associated with Long-Run Identifying Restrictions?... Benchmark CKM Model Initial Hours Worked Response Strong, Productivity Response Weak (Fig 3) Consequences of CKM Sign Restriction In Some Samples, Hours Response Very Strong and Initial Productivity Small Negative CKM Algorithm Calls this a Negative Technology Shock In These Cases, Their Procedure In Effect Multiplies the Hours Response by -1 (Fig 3a). Is this a Theoretical Curiosum? No...It Happens 23% Of Time. Leads to Pronounced Bimodal Distribution of Impact Effects (upper panel, Fig 4) Actual Distribution of Impact Effects Not Bimodal (lower panel, Fig 4). How Does this Affect Standard Errors? Leads CKM to Substantially Overstate Sampling Uncertainty (Fig. 5) 56

39 Impact of CKM Sign Restriction on Sampling Uncertainty 1.5 Long-run Identification 1.5 CKM Identification

40 Would the Econometrician Be Misled in Large Samples? CKM Say their Benchmark Example Implies Yes We Say No. In Practice, Econometrician Applies Diagnostic Tests for Lag Lengths in VAR Four Monte Carlo Simulations of Artificial Data. Simulate 5 Datasets of length =1; 5 ; 2 ; 5 In Each Artificial Data set We Choose Lag Length, as Solution to min () 445 where () is Akaike criterion. Compute Mean Impulse Response Across 5 Data sets (Fig 6) 6

41 .7.6 T=1 N =5.2 T=5 N=9.8 T=2 N=14.8 T=5 N=18.5 Model

42 Would the Econometrician Be Misled in Large Samples? CKM Say their Benchmark Example Implies Yes We Say No. In Practice, Econometrician Applies Diagnostic Tests for Lag Lengths in VAR Four Monte Carlo Simulations of Artificial Data. Simulate 5 Datasets of length =1; 5 ; 2 ; 5 In Each Artificial Data set We Choose Lag Length, as Solution to min () 445 where () is Akaike criterion. Compute Mean Impulse Response Across 5 Data sets (Fig 6) Key Result: Mean is Converging to Right Solution. Unresolved Puzzle: We Get Faster Convergence As Lag Length Increases (see analytic Plims, Fig 7) 61

43 .7 Figure 7: Response of Hours Worked, Analytic Plims, for Lag Length p = 4, 8, 16, 32; True Response *

44 Assessing the VAR With Short-Run Restrictions Using RBC as DGP Experiments Simulate 5 Artificial Data Sets, Each of Length 18 From Various Versions of DGP Estimate VAR On Each Artificial Data Set and Compute Dynamic Response of Hours to Positive Technology Shock Report Mean Impulse Response Function and Plus/Minus Two Standard Error Bounds (Grey Area) Timing in Two Shock Model: Labor Tax Shock Realized, Labor Determined, Technology Shock Realized, Consumption, Investment Determined. 62

45 Assessing the VAR With Short-Run Restrictions Using RBC as DGP... Note: log = 1 log = ( ) so least squares regression has error µ log ; log log = Equivalent to VAR With Choleski Ordering: = = =, = = lower triangular µ µ log 1 = log = 2 2 technology shock Everything is Perfect: No Bias and Small Standard Errors (Fig 8) 65

46 Two Variables in VAR Benchmark CKM Model With Timing Restriction Percent Response Three Variables in VAR, Investment Shock Not Persistent (Two Important Shocks) Percent Response Three Variables in VAR, Investment Shock Persistent (Three Important Shocks) Percent Response Periods After the Shock

47 Assessing the VAR With Short-Run Restrictions Using RBC as DGP... Timing in Three Shock Model: Labor Tax Shock Realized, Labor Determined, Technology and Investment Price Shocks Realized, Consumption, Investment Determined. 67

48 Assessing the VAR With Short-Run Restrictions Using RBC as DGP... Note: log = 1 1 log = ( 1 ) log = ( 1 ) so least squares regression has error log = µ log ; log log + 68

49 Assessing the VAR With Short-Run Restrictions Using RBC as DGP... Equivalent to VAR With Choleski Ordering: = = =, = = lower triangular = log log log = technology shock Everything is Perfect: No Bias and Small Standard Errors, Easy to Rule Out Interesting Hypotheses (Fig 8) Standard Error Estimates Unbiased (Fig 9) 69

50 Percent Response Percent Response Percent Response Two Variables in VAR CKM Benchmark Three Variables in VAR, Investment Shock Not Persistent (Two Important Shocks) Three Variables in VAR, Investment Shock Persistent (Three Important Shocks) Periods After the Shock

51 Assessing the VAR With Short-Run Restrictions Using RBC as DGP... Timing in Three Shock Model: Labor Tax Shock Realized, Labor Determined, Technology and Investment Price Shocks Realized, Consumption, Investment Determined. 67

52 Assessing the VAR With Short-Run Restrictions Using RBC as DGP... Note: log = 1 1 log = ( 1 ) log = ( 1 ) so least squares regression has error log = µ log ; log log + 68

53 Assessing the VAR With Short-Run Restrictions Using RBC as DGP... Equivalent to VAR With Choleski Ordering: = = =, = = lower triangular = log log log = technology shock Everything is Perfect: No Bias and Small Standard Errors, Easy to Rule Out Interesting Hypotheses (Fig 8) Standard Error Estimates Unbiased (Fig 9) 69

54 Percent Response Percent Response Percent Response Two Variables in VAR CKM Benchmark Three Variables in VAR, Investment Shock Not Persistent (Two Important Shocks) Three Variables in VAR, Investment Shock Persistent (Three Important Shocks) Periods After the Shock

55 Key Lessons of the RBC Model Analysis With Short Run Exclusion Restrictions, VAR Analysis Highly Accurate With Long Run Exclusion Restrictions: Potential Problems with Large Sampling Uncertainty Property of Our Examples: Conditional on Having Enough Variables, the Analyst Would Know it. 69

56 Motivation for Additional Analysis We Use VAR Impulse Response Functions as part of a Strategy To Formulate and Estimate Monetary DSGE Models Basic Strategy: Choose Model Parameters to Make Model-based Impulse Responses as close as Possible to VAR-based Impulse Responses. Problem: How Reliable are VAR-Based Impulse Response Functions? Solution: Extend Strategy Pursued Above to Larger DSGE Models, Larger VARs and More Shocks and Variables. Run the VAR in Data Generated by the Model. We Look at this in ACEL. 7

57 ACEL Model Final Good Firms: Z 1 () () () Z 1 = () 1 71

58 ACEL Model... Intermediate Good Firm: max X = + { + () + () () ()+ ( + ()) () + } technology: () given () = () ( ()) 1 µ +1 () =(1) () ()+(1 ) () 1 () = = in steady state 72

59 ACEL Model... Calvo Pricing: () : ½ set optimally with probability 1 = 1 1 () with probability Labor Market: Perfectly Competitive Labor Contractor Hires Differentiated Labor Services, and Sells Homogeneous Labor: max Z 1 subject to: = Z

60 ACEL Model... Household... Preferences: " # X 2 + log ( + +1 ) 2 = Asset Evolution Equation: +1 = [ +( 1) ]+ + + (1 + ( )) = : Beginning of Period Base Money; : Transactions Balances 74

61 ACEL Model... Monopoly Supplier of Specialized Labor Input, : ½ set optimally = 1 1 with probability 1 with probability Market Clearing: Loan Market: = +( 1) Resource Constraint: Z 1 (1 + ( )) + 1 ()+( ()) () 75

62 ACEL Model... Exogenous Shocks: Disembodied Technology: 1 = ˆ = ˆ 1 + ˆ Investment specific: 1 = ˆ = ˆ 1 + Balanced Growth: 1 = 1 = 76

63 ACEL Model... Monetary Policy: +1 =1+ ˆ = ˆ +ˆ +ˆ ˆ = ˆ 1 + ˆ = ˆ ˆ = ˆ

64 ACEL Model... Equilibrium Inflation: ˆ = ˆ +1 + ˆ Parameter, : 1 1 = ( ) ½ 31 Firm-specific Capital ( =2 =11 =36) = 1 Homogeneous Capital 79

65 MC 1,f P 1 MC,f P 2 P B MC 1 B A MC Q Q

66 ACEL Model... Intuition About Importance of Firm Specificity of Capital A Firm Contemplates Raising Price This Implies Output Falls Marginal Cost Falls Incentive to Raise Price Falls Effect Quantitatively Important When: Demand Elastic Marginal Cost Steep 8

67 Estimating Parameters in the Model Partition Parameters into Three Groups. Parameters set a priori (e.g.,...) 1 : remaining parameters pertaining to the nonstochastic part of model 1 =[ ] 2 : parameters pertaining to stochastic part of the model Number of parameters, =( 1 2 ) to be estimated - 18 Estimation Criterion () :mapping from to model impulse responses ˆ : 592 impulse responses estimated using VAR Estimation Strategy: ³ ˆ ³ = arg min ˆ () 1 ˆ () : diagonal matrix with sample variances of ˆ along the diagonal. 81

68 Estimated VAR {z} 1 1 = ln (relative price of investment ) ln ( Hours ) ln ( deflator ) Capacity Utilization ln (Hours ) ln ( Hours ) ln ( ) ln ( ) ln ( ) Federal Funds Rate ln( deflator )+ln( ) ln ( ) 82

69 Estimated Parameter Values, a little low... similar to other estimates in literature wages reoptimized on average every 3.6 quarters Parameters important in subsequent discussion... costly to vary utilization of capital close to perfect competition amazingly low! (similar to estimates reported in literature) 83

70 Estimated Parameters of Exogenous Processes, 2 Shocks ˆ = 24 (22)ˆ =3 (4) ˆ = 9 (11)ˆ =7 (4) Monetary Policy ˆ = ˆ +ˆ +ˆ ˆ = 3ˆ =33 (11) (8) ˆ = 33 (25)ˆ 1 +3 (192) +142 (99) 1 ˆ = 82 (12)ˆ (21) +13 (21) 1 84

71 Results Monetary Policy Shocks Substantial Propagation in Response to Policy (R and M move for only a year) Enormous Inertia in Inflation No Noticeable Rise in Inflation for a Year In Model, Prices Reoptimized Frequently. Persistence in Response of Output Neutral Technology Shocks Model Does Well, Although Confidence Intervals Wide Model Failure: Inflation Responds Strongly in Data, Not Strongly in Model Positive Response of Hours to Technology Shock is Due to Monetary Accommodation. Embodied Technology Shocks The model does well on these. 85

72 Figure 1: Response to a monetary policy shock (o - Model, - VAR, grey area - 95 % Confidence Interval) Output MZM Growth (Q) Inflation Federal Funds Rate Capacity Utilization Average Hours Real Wage Consumption Investment Velocity Quarters.2.1 Investment Good Price Quarters 2 Total money growth (M) Quarters

73 Figure 2: Response to a neutral technology shock (o - Model, - VAR, grey area - 95 % Confidence Interval) Output MZM Growth (Q) Inflation Federal Funds Rate Capacity Utilization Average Hours Real Wage Consumption Investment Velocity Quarters Investment Good Price Quarters 1.5 Total money growth (M) Quarters

74 Figure 3: Response to an embodied technology shock (o - Model, - VAR, grey area - 95 % Confidence Interval) Output MZM Growth (Q) Inflation Federal Funds Rate Capacity Utilization Average Hours Real Wage Consumption Investment Velocity Quarters Investment Good Price Quarters.5 Total money growth (M) Quarters

75 Question We fit Impulse Responses Reasonably Well, But Do We Have Any Reason to Trust Them? Obvious Experiment: What if the Estimated Model were literally true, How Well Would Our Procedure Work? We Plan to Study the Sampling Distribution of our Parameter Estimator For Now, We Repeated the RBC analysis Described Above. 86

76 Plan Basic Idea: Generate Data from DSGE Model and Fit VARs in Artificial Data Problem: DSGE Model Has Too Few Shocks Empirical Procedure Recognizes We re Short on Shocks and Offers a Natural Solution 87

77 Background The VAR: = () 1 + = () Stochastic Process for Can Be Decomposed Into Two Orthogonal Pieces: = + = () = ()

78 Background... = + Piece, Is Captured By the Equilibrium Model Piece, Is Left Out. Implications of the Analysis: Data Generated From Model Corresponds to Data Generated From Model is Missing. To Run VAR in Artificial Data Generate Artificial Data From Economic Model, Generate Construct: Fit VAR to From = = () µ

79 Experiment Generate Artificial Data Extremely Long Data Set to Get Plim (2, Observations) Many Data Sets of Length 17 Each Feed Each Data Set to Same VAR Fit to US Data Compute Impulse Response Functions Dotted Lines: Small Sample Means Dashed Lines: Plims 91

80 Findings Contents of Figures x s - mean impulse response, plus/minus two times mean standard deviation estimated by econometrician Solid line: truth Dotted line: small sample mean from VAR Gray area: mean impulse response, plus/minus two times actual standard deviation of impulse response. 92

81 Findings... Monetary Policy Shock Bias Reasonably Small Estimator of Uncertainty Acceptable (Though Some Bias Down) Neutral Technology Shock Overall, Bias Small, But Output, Investment and Real Wage Biased Down Notable Finding: Inflation Response Rules Out Estimated VAR Inflation Response VAR Confidence Interval: -.22 to -.8 percent Evidence Against ACEL Model. Evidence of Potential Power of Long-Run Restrictions. Embodied Technology Shock Performs Reasonably, Overall 93

82 Output Fed Funds Real Wage Velocity M2 Growth Capacity Util Consumption Price of Inv Inflation Avg Hours Investment

83 .4.2 Output M2 Growth.2.2 Inflation Fed Funds Real Wage Capacity Util Consumption Avg Hours Investment Velocity Price of Inv

84 .4.2 Output M2 Growth Inflation Fed Funds.5 Capacity Util.4 Avg Hours Real Wage Consumption Investment Velocity Price of Inv

85 Conclusion VARs With Long-Run Restrictions: Can Be Imprecise, But Standard Errors Let You Know Can Have Power See Prescott RBC Model See Evidence Against ACEL Model VARs With Short-Run Restrictions: Appear to Be Precise Simulations Like the Ones Done Here (following Erceg-Guerrieri-Gust, and CKM) Important as Ultimate Guard Against Being Misled However, in Models Which Do Not Specify All Shocks, Must Use Something Like ACEL Procedure to Add Estimate of Other Shocks. 96

Assessing Structural VAR s

Assessing Structural VAR s ... Assessing Structural VAR s by Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson Zurich, September 2005 1 Background Structural Vector Autoregressions Address the Following Type of Question:

More information

Assessing Structural VAR s

Assessing Structural VAR s ... Assessing Structural VAR s by Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson Yale, October 2005 1 Background Structural Vector Autoregressions Can be Used to Address the Following Type

More information

Assessing Structural VAR s

Assessing Structural VAR s ... Assessing Structural VAR s by Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson Columbia, October 2005 1 Background Structural Vector Autoregressions Can be Used to Address the Following

More information

Assessing Structural VAR s

Assessing Structural VAR s ... Assessing Structural VAR s by Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson Minneapolis, August 2005 1 Background In Principle, Impulse Response Functions from SVARs are useful as

More information

Assessing Structural VAR s

Assessing Structural VAR s ... Assessing Structural VAR s by Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson University of Maryland, September 2005 1 Background In Principle, Impulse Response Functions from SVARs

More information

Are Structural VARs Useful Guides for Developing Business Cycle Theories? by Larry Christiano

Are Structural VARs Useful Guides for Developing Business Cycle Theories? by Larry Christiano Discussion of: Chari-Kehoe-McGrattan: Are Structural VARs Useful Guides for Developing Business Cycle Theories? by Larry Christiano 1 Chari-Kehoe-McGrattan: Are Structural VARs Useful Guides for Developing

More information

Identifying the Monetary Policy Shock Christiano et al. (1999)

Identifying the Monetary Policy Shock Christiano et al. (1999) Identifying the Monetary Policy Shock Christiano et al. (1999) The question we are asking is: What are the consequences of a monetary policy shock a shock which is purely related to monetary conditions

More information

Assessing Structural VAR s

Assessing Structural VAR s ... Assessing Structural VAR s by Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson Background Structural Vector Autoregressions Can be Used to Address the Following Type of Question: How

More information

Financial Factors in Economic Fluctuations. Lawrence Christiano Roberto Motto Massimo Rostagno

Financial Factors in Economic Fluctuations. Lawrence Christiano Roberto Motto Massimo Rostagno Financial Factors in Economic Fluctuations Lawrence Christiano Roberto Motto Massimo Rostagno Background Much progress made on constructing and estimating models that fit quarterly data well (Smets-Wouters,

More information

Resolving the Missing Deflation Puzzle. June 7, 2018

Resolving the Missing Deflation Puzzle. June 7, 2018 Resolving the Missing Deflation Puzzle Jesper Lindé Sveriges Riksbank Mathias Trabandt Freie Universität Berlin June 7, 218 Motivation Key observations during the Great Recession: Extraordinary contraction

More information

1.2. Structural VARs

1.2. Structural VARs 1. Shocks Nr. 1 1.2. Structural VARs How to identify A 0? A review: Choleski (Cholesky?) decompositions. Short-run restrictions. Inequality restrictions. Long-run restrictions. Then, examples, applications,

More information

DSGE-Models. Calibration and Introduction to Dynare. Institute of Econometrics and Economic Statistics

DSGE-Models. Calibration and Introduction to Dynare. Institute of Econometrics and Economic Statistics DSGE-Models Calibration and Introduction to Dynare Dr. Andrea Beccarini Willi Mutschler, M.Sc. Institute of Econometrics and Economic Statistics willi.mutschler@uni-muenster.de Summer 2012 Willi Mutschler

More information

Introduction to Macroeconomics

Introduction to Macroeconomics Introduction to Macroeconomics Martin Ellison Nuffi eld College Michaelmas Term 2018 Martin Ellison (Nuffi eld) Introduction Michaelmas Term 2018 1 / 39 Macroeconomics is Dynamic Decisions are taken over

More information

Simple New Keynesian Model without Capital

Simple New Keynesian Model without Capital Simple New Keynesian Model without Capital Lawrence J. Christiano January 5, 2018 Objective Review the foundations of the basic New Keynesian model without capital. Clarify the role of money supply/demand.

More information

Can News be a Major Source of Aggregate Fluctuations?

Can News be a Major Source of Aggregate Fluctuations? Can News be a Major Source of Aggregate Fluctuations? A Bayesian DSGE Approach Ippei Fujiwara 1 Yasuo Hirose 1 Mototsugu 2 1 Bank of Japan 2 Vanderbilt University August 4, 2009 Contributions of this paper

More information

Simple New Keynesian Model without Capital

Simple New Keynesian Model without Capital Simple New Keynesian Model without Capital Lawrence J. Christiano March, 28 Objective Review the foundations of the basic New Keynesian model without capital. Clarify the role of money supply/demand. Derive

More information

Signaling Effects of Monetary Policy

Signaling Effects of Monetary Policy Signaling Effects of Monetary Policy Leonardo Melosi London Business School 24 May 2012 Motivation Disperse information about aggregate fundamentals Morris and Shin (2003), Sims (2003), and Woodford (2002)

More information

Graduate Macro Theory II: Notes on Quantitative Analysis in DSGE Models

Graduate Macro Theory II: Notes on Quantitative Analysis in DSGE Models Graduate Macro Theory II: Notes on Quantitative Analysis in DSGE Models Eric Sims University of Notre Dame Spring 2011 This note describes very briefly how to conduct quantitative analysis on a linearized

More information

Fiscal Multipliers in a Nonlinear World

Fiscal Multipliers in a Nonlinear World Fiscal Multipliers in a Nonlinear World Jesper Lindé and Mathias Trabandt ECB-EABCN-Atlanta Nonlinearities Conference, December 15-16, 2014 Sveriges Riksbank and Federal Reserve Board December 16, 2014

More information

Taylor Rules and Technology Shocks

Taylor Rules and Technology Shocks Taylor Rules and Technology Shocks Eric R. Sims University of Notre Dame and NBER January 17, 2012 Abstract In a standard New Keynesian model, a Taylor-type interest rate rule moves the equilibrium real

More information

Optimal Inflation Stabilization in a Medium-Scale Macroeconomic Model

Optimal Inflation Stabilization in a Medium-Scale Macroeconomic Model Optimal Inflation Stabilization in a Medium-Scale Macroeconomic Model Stephanie Schmitt-Grohé Martín Uribe Duke University 1 Objective of the Paper: Within a mediumscale estimated model of the macroeconomy

More information

Do Long Run Restrictions Identify Supply and Demand Disturbances?

Do Long Run Restrictions Identify Supply and Demand Disturbances? Do Long Run Restrictions Identify Supply and Demand Disturbances? U. Michael Bergman Department of Economics, University of Copenhagen, Studiestræde 6, DK 1455 Copenhagen K, Denmark October 25, 2005 Abstract

More information

1 The Basic RBC Model

1 The Basic RBC Model IHS 2016, Macroeconomics III Michael Reiter Ch. 1: Notes on RBC Model 1 1 The Basic RBC Model 1.1 Description of Model Variables y z k L c I w r output level of technology (exogenous) capital at end of

More information

Fiscal Multipliers in a Nonlinear World

Fiscal Multipliers in a Nonlinear World Fiscal Multipliers in a Nonlinear World Jesper Lindé Sveriges Riksbank Mathias Trabandt Freie Universität Berlin November 28, 2016 Lindé and Trabandt Multipliers () in Nonlinear Models November 28, 2016

More information

Structural VARs II. February 17, 2016

Structural VARs II. February 17, 2016 Structural VARs II February 17, 216 Structural VARs Today: Long-run restrictions Two critiques of SVARs Blanchard and Quah (1989), Rudebusch (1998), Gali (1999) and Chari, Kehoe McGrattan (28). Recap:

More information

Dynamics and Monetary Policy in a Fair Wage Model of the Business Cycle

Dynamics and Monetary Policy in a Fair Wage Model of the Business Cycle Dynamics and Monetary Policy in a Fair Wage Model of the Business Cycle David de la Croix 1,3 Gregory de Walque 2 Rafael Wouters 2,1 1 dept. of economics, Univ. cath. Louvain 2 National Bank of Belgium

More information

The Basic New Keynesian Model. Jordi Galí. June 2008

The Basic New Keynesian Model. Jordi Galí. June 2008 The Basic New Keynesian Model by Jordi Galí June 28 Motivation and Outline Evidence on Money, Output, and Prices: Short Run E ects of Monetary Policy Shocks (i) persistent e ects on real variables (ii)

More information

Macroeconomics Theory II

Macroeconomics Theory II Macroeconomics Theory II Francesco Franco FEUNL February 2011 Francesco Franco Macroeconomics Theory II 1/34 The log-linear plain vanilla RBC and ν(σ n )= ĉ t = Y C ẑt +(1 α) Y C ˆn t + K βc ˆk t 1 + K

More information

4- Current Method of Explaining Business Cycles: DSGE Models. Basic Economic Models

4- Current Method of Explaining Business Cycles: DSGE Models. Basic Economic Models 4- Current Method of Explaining Business Cycles: DSGE Models Basic Economic Models In Economics, we use theoretical models to explain the economic processes in the real world. These models de ne a relation

More information

An Estimated Dynamic, General Equilibrium Model for Monetary Policy Analysis (Preliminary and Incomplete)

An Estimated Dynamic, General Equilibrium Model for Monetary Policy Analysis (Preliminary and Incomplete) An Estimated Dynamic, General Equilibrium Model for Monetary Policy Analysis (Preliminary and Incomplete) David Altig, Lawrence J. Christiano, Martin Eichenbaum and Jesper Linde June 16, 22 Abstract We

More information

Small Open Economy RBC Model Uribe, Chapter 4

Small Open Economy RBC Model Uribe, Chapter 4 Small Open Economy RBC Model Uribe, Chapter 4 1 Basic Model 1.1 Uzawa Utility E 0 t=0 θ t U (c t, h t ) θ 0 = 1 θ t+1 = β (c t, h t ) θ t ; β c < 0; β h > 0. Time-varying discount factor With a constant

More information

NBER WORKING PAPER SERIES ASSESSING STRUCTURAL VARS. Lawrence J. Christiano Martin Eichenbaum Robert Vigfusson

NBER WORKING PAPER SERIES ASSESSING STRUCTURAL VARS. Lawrence J. Christiano Martin Eichenbaum Robert Vigfusson NBER WORKING PAPER SERIES ASSESSING STRUCTURAL VARS Lawrence J. Christiano Martin Eichenbaum Robert Vigfusson Working Paper 353 http://www.nber.org/papers/w353 NATIONAL BUREAU OF ECONOMIC RESEARCH 5 Massachusetts

More information

Real Business Cycle Model (RBC)

Real Business Cycle Model (RBC) Real Business Cycle Model (RBC) Seyed Ali Madanizadeh November 2013 RBC Model Lucas 1980: One of the functions of theoretical economics is to provide fully articulated, artificial economic systems that

More information

Estimating and Identifying Vector Autoregressions Under Diagonality and Block Exogeneity Restrictions

Estimating and Identifying Vector Autoregressions Under Diagonality and Block Exogeneity Restrictions Estimating and Identifying Vector Autoregressions Under Diagonality and Block Exogeneity Restrictions William D. Lastrapes Department of Economics Terry College of Business University of Georgia Athens,

More information

What Happens After A Technology Shock?

What Happens After A Technology Shock? What Happens After A Technology Shock? Lawrence J. Christiano, Martin Eichenbaum and Robert Vigfusson March 6, 23 Abstract This paper examines the economic impact of permanent shocks to technology. We

More information

New Notes on the Solow Growth Model

New Notes on the Solow Growth Model New Notes on the Solow Growth Model Roberto Chang September 2009 1 The Model The firstingredientofadynamicmodelisthedescriptionofthetimehorizon. In the original Solow model, time is continuous and the

More information

Comment on Gali and Rabanal s Technology Shocks and Aggregate Fluctuations: HowWellDoestheRBCModelFitPostwarU.S.Data?

Comment on Gali and Rabanal s Technology Shocks and Aggregate Fluctuations: HowWellDoestheRBCModelFitPostwarU.S.Data? Federal Reserve Bank of Minneapolis Research Department Staff Report 338 June 2004 Comment on Gali and Rabanal s Technology Shocks and Aggregate Fluctuations: HowWellDoestheRBCModelFitPostwarU.S.Data?

More information

Macroeconomics II. Dynamic AD-AS model

Macroeconomics II. Dynamic AD-AS model Macroeconomics II Dynamic AD-AS model Vahagn Jerbashian Ch. 14 from Mankiw (2010) Spring 2018 Where we are heading to We will incorporate dynamics into the standard AD-AS model This will offer another

More information

Dynamic AD-AS model vs. AD-AS model Notes. Dynamic AD-AS model in a few words Notes. Notation to incorporate time-dimension Notes

Dynamic AD-AS model vs. AD-AS model Notes. Dynamic AD-AS model in a few words Notes. Notation to incorporate time-dimension Notes Macroeconomics II Dynamic AD-AS model Vahagn Jerbashian Ch. 14 from Mankiw (2010) Spring 2018 Where we are heading to We will incorporate dynamics into the standard AD-AS model This will offer another

More information

Chapter 6. Maximum Likelihood Analysis of Dynamic Stochastic General Equilibrium (DSGE) Models

Chapter 6. Maximum Likelihood Analysis of Dynamic Stochastic General Equilibrium (DSGE) Models Chapter 6. Maximum Likelihood Analysis of Dynamic Stochastic General Equilibrium (DSGE) Models Fall 22 Contents Introduction 2. An illustrative example........................... 2.2 Discussion...................................

More information

Identifying SVARs with Sign Restrictions and Heteroskedasticity

Identifying SVARs with Sign Restrictions and Heteroskedasticity Identifying SVARs with Sign Restrictions and Heteroskedasticity Srečko Zimic VERY PRELIMINARY AND INCOMPLETE NOT FOR DISTRIBUTION February 13, 217 Abstract This paper introduces a new method to identify

More information

Whither News Shocks?

Whither News Shocks? Discussion of Whither News Shocks? Barsky, Basu and Lee Christiano Outline Identification assumptions for news shocks Empirical Findings Using NK model used to think about BBL identification. Why should

More information

Lecture 1: Information and Structural VARs

Lecture 1: Information and Structural VARs Lecture 1: Information and Structural VARs Luca Gambetti 1 1 Universitat Autònoma de Barcelona LBS, May 6-8 2013 Introduction The study of the dynamic effects of economic shocks is one of the key applications

More information

The Labor Market in the New Keynesian Model: Foundations of the Sticky Wage Approach and a Critical Commentary

The Labor Market in the New Keynesian Model: Foundations of the Sticky Wage Approach and a Critical Commentary The Labor Market in the New Keynesian Model: Foundations of the Sticky Wage Approach and a Critical Commentary Lawrence J. Christiano March 30, 2013 Baseline developed earlier: NK model with no capital

More information

A primer on Structural VARs

A primer on Structural VARs A primer on Structural VARs Claudia Foroni Norges Bank 10 November 2014 Structural VARs 1/ 26 Refresh: what is a VAR? VAR (p) : where y t K 1 y t = ν + B 1 y t 1 +... + B p y t p + u t, (1) = ( y 1t...

More information

Evaluating Structural Vector Autoregression Models in Monetary Economies

Evaluating Structural Vector Autoregression Models in Monetary Economies Evaluating Structural Vector Autoregression Models in Monetary Economies Bin Li Research Department International Monetary Fund March 9 Abstract This paper uses Monte Carlo simulations to evaluate alternative

More information

Formulating, Estimating, and Solving Dynamic Equilibrium Models: an Introduction. Jesús Fernández-Villaverde University of Pennsylvania

Formulating, Estimating, and Solving Dynamic Equilibrium Models: an Introduction. Jesús Fernández-Villaverde University of Pennsylvania Formulating, Estimating, and Solving Dynamic Equilibrium Models: an Introduction Jesús Fernández-Villaverde University of Pennsylvania 1 Models Tradition in macroeconomics of using models: 1. Policy Analysis.

More information

Gaussian Mixture Approximations of Impulse Responses and the Non-Linear Effects of Monetary Shocks

Gaussian Mixture Approximations of Impulse Responses and the Non-Linear Effects of Monetary Shocks Gaussian Mixture Approximations of Impulse Responses and the Non-Linear Effects of Monetary Shocks Regis Barnichon (CREI, Universitat Pompeu Fabra) Christian Matthes (Richmond Fed) Effects of monetary

More information

Labor-Supply Shifts and Economic Fluctuations. Technical Appendix

Labor-Supply Shifts and Economic Fluctuations. Technical Appendix Labor-Supply Shifts and Economic Fluctuations Technical Appendix Yongsung Chang Department of Economics University of Pennsylvania Frank Schorfheide Department of Economics University of Pennsylvania January

More information

Simple New Keynesian Model without Capital

Simple New Keynesian Model without Capital Simple New Keynesian Model without Capital Lawrence J. Christiano Gerzensee, August 27 Objective Review the foundations of the basic New Keynesian model without capital. Clarify the role of money supply/demand.

More information

Inference when identifying assumptions are doubted. A. Theory B. Applications

Inference when identifying assumptions are doubted. A. Theory B. Applications Inference when identifying assumptions are doubted A. Theory B. Applications 1 A. Theory Structural model of interest: A y t B 1 y t1 B m y tm u t nn n1 u t i.i.d. N0, D D diagonal 2 Bayesian approach:

More information

Deviant Behavior in Monetary Economics

Deviant Behavior in Monetary Economics Deviant Behavior in Monetary Economics Lawrence Christiano and Yuta Takahashi July 26, 2018 Multiple Equilibria Standard NK Model Standard, New Keynesian (NK) Monetary Model: Taylor rule satisfying Taylor

More information

A. Recursively orthogonalized. VARs

A. Recursively orthogonalized. VARs Orthogonalized VARs A. Recursively orthogonalized VAR B. Variance decomposition C. Historical decomposition D. Structural interpretation E. Generalized IRFs 1 A. Recursively orthogonalized Nonorthogonal

More information

Gold Rush Fever in Business Cycles

Gold Rush Fever in Business Cycles Gold Rush Fever in Business Cycles Paul Beaudry, Fabrice Collard & Franck Portier University of British Columbia & Université de Toulouse UAB Seminar Barcelona November, 29, 26 The Klondike Gold Rush of

More information

1. Shocks. This version: February 15, Nr. 1

1. Shocks. This version: February 15, Nr. 1 1. Shocks This version: February 15, 2006 Nr. 1 1.3. Factor models What if there are more shocks than variables in the VAR? What if there are only a few underlying shocks, explaining most of fluctuations?

More information

What You Match Does Matter: The Effects of Data on DSGE Estimation

What You Match Does Matter: The Effects of Data on DSGE Estimation Discussion of What You Match Does Matter: The Effects of Data on DSGE Estimation by Pablo Guerron-Quintana Marc Giannoni Columbia University, NBER and CEPR Workshop on Methods and Applications for DSGE

More information

PANEL DISCUSSION: THE ROLE OF POTENTIAL OUTPUT IN POLICYMAKING

PANEL DISCUSSION: THE ROLE OF POTENTIAL OUTPUT IN POLICYMAKING PANEL DISCUSSION: THE ROLE OF POTENTIAL OUTPUT IN POLICYMAKING James Bullard* Federal Reserve Bank of St. Louis 33rd Annual Economic Policy Conference St. Louis, MO October 17, 2008 Views expressed are

More information

Problem 1 (30 points)

Problem 1 (30 points) Problem (30 points) Prof. Robert King Consider an economy in which there is one period and there are many, identical households. Each household derives utility from consumption (c), leisure (l) and a public

More information

Oil price and macroeconomy in Russia. Abstract

Oil price and macroeconomy in Russia. Abstract Oil price and macroeconomy in Russia Katsuya Ito Fukuoka University Abstract In this note, using the VEC model we attempt to empirically investigate the effects of oil price and monetary shocks on the

More information

Inference when identifying assumptions are doubted. A. Theory. Structural model of interest: B 1 y t1. u t. B m y tm. u t i.i.d.

Inference when identifying assumptions are doubted. A. Theory. Structural model of interest: B 1 y t1. u t. B m y tm. u t i.i.d. Inference when identifying assumptions are doubted A. Theory B. Applications Structural model of interest: A y t B y t B m y tm nn n i.i.d. N, D D diagonal A. Theory Bayesian approach: Summarize whatever

More information

Macroeconomics Field Exam. August 2007

Macroeconomics Field Exam. August 2007 Macroeconomics Field Exam August 2007 Answer all questions in the exam. Suggested times correspond to the questions weights in the exam grade. Make your answers as precise as possible, using graphs, equations,

More information

Resolving the Missing Deflation Puzzle

Resolving the Missing Deflation Puzzle Resolving the Missing Deflation Puzzle Jesper Lindé Sveriges Riksbank Mathias Trabandt Freie Universität Berlin 49th Konstanz Seminar on Monetary Theory and Monetary Policy May 16, 2018 Lindé and Trabandt

More information

Combining Macroeconomic Models for Prediction

Combining Macroeconomic Models for Prediction Combining Macroeconomic Models for Prediction John Geweke University of Technology Sydney 15th Australasian Macro Workshop April 8, 2010 Outline 1 Optimal prediction pools 2 Models and data 3 Optimal pools

More information

A Modern Equilibrium Model. Jesús Fernández-Villaverde University of Pennsylvania

A Modern Equilibrium Model. Jesús Fernández-Villaverde University of Pennsylvania A Modern Equilibrium Model Jesús Fernández-Villaverde University of Pennsylvania 1 Household Problem Preferences: max E X β t t=0 c 1 σ t 1 σ ψ l1+γ t 1+γ Budget constraint: c t + k t+1 = w t l t + r t

More information

A Primer on Vector Autoregressions

A Primer on Vector Autoregressions A Primer on Vector Autoregressions Ambrogio Cesa-Bianchi VAR models 1 [DISCLAIMER] These notes are meant to provide intuition on the basic mechanisms of VARs As such, most of the material covered here

More information

Econometrics in a nutshell: Variation and Identification Linear Regression Model in STATA. Research Methods. Carlos Noton.

Econometrics in a nutshell: Variation and Identification Linear Regression Model in STATA. Research Methods. Carlos Noton. 1/17 Research Methods Carlos Noton Term 2-2012 Outline 2/17 1 Econometrics in a nutshell: Variation and Identification 2 Main Assumptions 3/17 Dependent variable or outcome Y is the result of two forces:

More information

Graduate Macro Theory II: Business Cycle Accounting and Wedges

Graduate Macro Theory II: Business Cycle Accounting and Wedges Graduate Macro Theory II: Business Cycle Accounting and Wedges Eric Sims University of Notre Dame Spring 2017 1 Introduction Most modern dynamic macro models have at their core a prototypical real business

More information

MA Advanced Macroeconomics: 7. The Real Business Cycle Model

MA Advanced Macroeconomics: 7. The Real Business Cycle Model MA Advanced Macroeconomics: 7. The Real Business Cycle Model Karl Whelan School of Economics, UCD Spring 2016 Karl Whelan (UCD) Real Business Cycles Spring 2016 1 / 38 Working Through A DSGE Model We have

More information

1 Teaching notes on structural VARs.

1 Teaching notes on structural VARs. Bent E. Sørensen November 8, 2016 1 Teaching notes on structural VARs. 1.1 Vector MA models: 1.1.1 Probability theory The simplest to analyze, estimation is a different matter time series models are the

More information

Animal Spirits, Fundamental Factors and Business Cycle Fluctuations

Animal Spirits, Fundamental Factors and Business Cycle Fluctuations Animal Spirits, Fundamental Factors and Business Cycle Fluctuations Stephane Dées Srečko Zimic Banque de France European Central Bank January 6, 218 Disclaimer Any views expressed represent those of the

More information

COMMENT ON DEL NEGRO, SCHORFHEIDE, SMETS AND WOUTERS COMMENT ON DEL NEGRO, SCHORFHEIDE, SMETS AND WOUTERS

COMMENT ON DEL NEGRO, SCHORFHEIDE, SMETS AND WOUTERS COMMENT ON DEL NEGRO, SCHORFHEIDE, SMETS AND WOUTERS COMMENT ON DEL NEGRO, SCHORFHEIDE, SMETS AND WOUTERS COMMENT ON DEL NEGRO, SCHORFHEIDE, SMETS AND WOUTERS CHRISTOPHER A. SIMS 1. WHY THIS APPROACH HAS BEEN SUCCESSFUL This paper sets out to blend the advantages

More information

Lecture 4 The Centralized Economy: Extensions

Lecture 4 The Centralized Economy: Extensions Lecture 4 The Centralized Economy: Extensions Leopold von Thadden University of Mainz and ECB (on leave) Advanced Macroeconomics, Winter Term 2013 1 / 36 I Motivation This Lecture considers some applications

More information

Simultaneous Equation Models Learning Objectives Introduction Introduction (2) Introduction (3) Solving the Model structural equations

Simultaneous Equation Models Learning Objectives Introduction Introduction (2) Introduction (3) Solving the Model structural equations Simultaneous Equation Models. Introduction: basic definitions 2. Consequences of ignoring simultaneity 3. The identification problem 4. Estimation of simultaneous equation models 5. Example: IS LM model

More information

Macroeconomics Theory II

Macroeconomics Theory II Macroeconomics Theory II Francesco Franco FEUNL February 2016 Francesco Franco Macroeconomics Theory II 1/23 Housekeeping. Class organization. Website with notes and papers as no "Mas-Collel" in macro

More information

Outline. Nature of the Problem. Nature of the Problem. Basic Econometrics in Transportation. Autocorrelation

Outline. Nature of the Problem. Nature of the Problem. Basic Econometrics in Transportation. Autocorrelation 1/30 Outline Basic Econometrics in Transportation Autocorrelation Amir Samimi What is the nature of autocorrelation? What are the theoretical and practical consequences of autocorrelation? Since the assumption

More information

Y t = log (employment t )

Y t = log (employment t ) Advanced Macroeconomics, Christiano Econ 416 Homework #7 Due: November 21 1. Consider the linearized equilibrium conditions of the New Keynesian model, on the slide, The Equilibrium Conditions in the handout,

More information

Chapter 11 The Stochastic Growth Model and Aggregate Fluctuations

Chapter 11 The Stochastic Growth Model and Aggregate Fluctuations George Alogoskoufis, Dynamic Macroeconomics, 2016 Chapter 11 The Stochastic Growth Model and Aggregate Fluctuations In previous chapters we studied the long run evolution of output and consumption, real

More information

Toulouse School of Economics, Macroeconomics II Franck Portier. Homework 1. Problem I An AD-AS Model

Toulouse School of Economics, Macroeconomics II Franck Portier. Homework 1. Problem I An AD-AS Model Toulouse School of Economics, 2009-2010 Macroeconomics II Franck Portier Homework 1 Problem I An AD-AS Model Let us consider an economy with three agents (a firm, a household and a government) and four

More information

Optimal Monetary Policy in a Data-Rich Environment

Optimal Monetary Policy in a Data-Rich Environment Optimal Monetary Policy in a Data-Rich Environment Jean Boivin HEC Montréal, CIRANO, CIRPÉE and NBER Marc Giannoni Columbia University, NBER and CEPR Forecasting Short-term Economic Developments... Bank

More information

Gold Rush Fever in Business Cycles

Gold Rush Fever in Business Cycles Gold Rush Fever in Business Cycles Paul Beaudry, Fabrice Collard & Franck Portier University of British Columbia & Université de Toulouse Banque Nationale Nationale Bank Belgischen de Belgique van Belgïe

More information

Neoclassical Business Cycle Model

Neoclassical Business Cycle Model Neoclassical Business Cycle Model Prof. Eric Sims University of Notre Dame Fall 2015 1 / 36 Production Economy Last time: studied equilibrium in an endowment economy Now: study equilibrium in an economy

More information

Dynamic Factor Models Cointegration and Error Correction Mechanisms

Dynamic Factor Models Cointegration and Error Correction Mechanisms Dynamic Factor Models Cointegration and Error Correction Mechanisms Matteo Barigozzi Marco Lippi Matteo Luciani LSE EIEF ECARES Conference in memory of Carlo Giannini Pavia 25 Marzo 2014 This talk Statement

More information

The Price Puzzle: Mixing the Temporary and Permanent Monetary Policy Shocks.

The Price Puzzle: Mixing the Temporary and Permanent Monetary Policy Shocks. The Price Puzzle: Mixing the Temporary and Permanent Monetary Policy Shocks. Ida Wolden Bache Norges Bank Kai Leitemo Norwegian School of Management BI September 2, 2008 Abstract We argue that the correct

More information

Identification of Technology Shocks in Structural VARs

Identification of Technology Shocks in Structural VARs Cahier de recherche/working Paper 7-36 Identification of Technology Shocks in Structural VARs Patrick Fève Alain Guay Octobre/October 27 Fève : Toulouse School of Economics (University of Toulouse, GREMAQ

More information

Lecture 3, November 30: The Basic New Keynesian Model (Galí, Chapter 3)

Lecture 3, November 30: The Basic New Keynesian Model (Galí, Chapter 3) MakØk3, Fall 2 (blok 2) Business cycles and monetary stabilization policies Henrik Jensen Department of Economics University of Copenhagen Lecture 3, November 3: The Basic New Keynesian Model (Galí, Chapter

More information

Computational Macroeconomics. Prof. Dr. Maik Wolters Friedrich Schiller University Jena

Computational Macroeconomics. Prof. Dr. Maik Wolters Friedrich Schiller University Jena Computational Macroeconomics Prof. Dr. Maik Wolters Friedrich Schiller University Jena Overview Objective: Learn doing empirical and applied theoretical work in monetary macroeconomics Implementing macroeconomic

More information

When Do Wold Orderings and Long-Run Recursive Identifying Restrictions Yield Identical Results?

When Do Wold Orderings and Long-Run Recursive Identifying Restrictions Yield Identical Results? Preliminary and incomplete When Do Wold Orderings and Long-Run Recursive Identifying Restrictions Yield Identical Results? John W Keating * University of Kansas Department of Economics 334 Snow Hall Lawrence,

More information

Housing and the Business Cycle

Housing and the Business Cycle Housing and the Business Cycle Morris Davis and Jonathan Heathcote Winter 2009 Huw Lloyd-Ellis () ECON917 Winter 2009 1 / 21 Motivation Need to distinguish between housing and non housing investment,!

More information

Assessing the Fed s Performance through the Effect of Technology Shocks: New Evidence

Assessing the Fed s Performance through the Effect of Technology Shocks: New Evidence through the Effect of Technology Shocks: New Evidence Carlo Coen Castellino September 2010 Abstract In this work I revisit the paper by Galí et al. (2003), which explains how the changes over time in the

More information

Endogenous Information Choice

Endogenous Information Choice Endogenous Information Choice Lecture 7 February 11, 2015 An optimizing trader will process those prices of most importance to his decision problem most frequently and carefully, those of less importance

More information

The Dark Corners of the Labor Market

The Dark Corners of the Labor Market The Dark Corners of the Labor Market Vincent Sterk Conference on Persistent Output Gaps: Causes and Policy Remedies EABCN / University of Cambridge / INET University College London September 2015 Sterk

More information

LECTURE 3 The Effects of Monetary Changes: Statistical Identification. September 5, 2018

LECTURE 3 The Effects of Monetary Changes: Statistical Identification. September 5, 2018 Economics 210c/236a Fall 2018 Christina Romer David Romer LECTURE 3 The Effects of Monetary Changes: Statistical Identification September 5, 2018 I. SOME BACKGROUND ON VARS A Two-Variable VAR Suppose the

More information

1 Teaching notes on structural VARs.

1 Teaching notes on structural VARs. Bent E. Sørensen February 22, 2007 1 Teaching notes on structural VARs. 1.1 Vector MA models: 1.1.1 Probability theory The simplest (to analyze, estimation is a different matter) time series models are

More information

The Ramsey Model. (Lecture Note, Advanced Macroeconomics, Thomas Steger, SS 2013)

The Ramsey Model. (Lecture Note, Advanced Macroeconomics, Thomas Steger, SS 2013) The Ramsey Model (Lecture Note, Advanced Macroeconomics, Thomas Steger, SS 213) 1 Introduction The Ramsey model (or neoclassical growth model) is one of the prototype models in dynamic macroeconomics.

More information

Modelling Czech and Slovak labour markets: A DSGE model with labour frictions

Modelling Czech and Slovak labour markets: A DSGE model with labour frictions Modelling Czech and Slovak labour markets: A DSGE model with labour frictions Daniel Němec Faculty of Economics and Administrations Masaryk University Brno, Czech Republic nemecd@econ.muni.cz ESF MU (Brno)

More information

FEDERAL RESERVE BANK of ATLANTA

FEDERAL RESERVE BANK of ATLANTA FEDERAL RESERVE BANK of ATLANTA On the Solution of the Growth Model with Investment-Specific Technological Change Jesús Fernández-Villaverde and Juan Francisco Rubio-Ramírez Working Paper 2004-39 December

More information

Problem Set 4. Graduate Macro II, Spring 2011 The University of Notre Dame Professor Sims

Problem Set 4. Graduate Macro II, Spring 2011 The University of Notre Dame Professor Sims Problem Set 4 Graduate Macro II, Spring 2011 The University of Notre Dame Professor Sims Instructions: You may consult with other members of the class, but please make sure to turn in your own work. Where

More information

DSGE Methods. Estimation of DSGE models: GMM and Indirect Inference. Willi Mutschler, M.Sc.

DSGE Methods. Estimation of DSGE models: GMM and Indirect Inference. Willi Mutschler, M.Sc. DSGE Methods Estimation of DSGE models: GMM and Indirect Inference Willi Mutschler, M.Sc. Institute of Econometrics and Economic Statistics University of Münster willi.mutschler@wiwi.uni-muenster.de Summer

More information

Estimating and Accounting for the Output Gap with Large Bayesian Vector Autoregressions

Estimating and Accounting for the Output Gap with Large Bayesian Vector Autoregressions Estimating and Accounting for the Output Gap with Large Bayesian Vector Autoregressions James Morley 1 Benjamin Wong 2 1 University of Sydney 2 Reserve Bank of New Zealand The view do not necessarily represent

More information

Technology Shocks and Aggregate Fluctuations: How Well Does the RBC Model Fit Postwar U.S. Data?

Technology Shocks and Aggregate Fluctuations: How Well Does the RBC Model Fit Postwar U.S. Data? Technology Shocks and Aggregate Fluctuations: How Well Does the RBC Model Fit Postwar U.S. Data? by Jordi Gali and Pau Rabanal Comments by Ellen R. McGrattan, Minneapolis Fed Overview of Gali-Rabanal Part

More information