Econometrics of Commods
Econometrics of Commods
Econometrics of Commods
Aaron Smith
UC Davis
1
Before we begin
2
Outline
1. Introduction
I start with the data
2. Models
I Structural (rational storage model estimated by ML)
I Structural Time Series (linear VAR)
I Financial Time Series (linear factor model)
I Mostly Harmless (linear regressions with carefully chosen
instruments)
3. Example
I What was the effect of biofuel mandates on agricultural
commodity prices?
4. Conclusion
3
Where to Begin?
I You have a question
I What was the effect of biofuel mandates on food and fuel prices?
I What explains the run-up in oil prices in the 2000s?
I How much does financial speculation affect commodity prices?
I How much would an X% carbon tax reduce carbon emissions?
I etc
4
Start with the Data
140
120
100
80
60
40
20
0
1970 1975 1980 1985 1990 1995 2000 2005 2010 2015
5
Crude Oil Price (U.S. Refiner Acquisition Cost)
140
120
100
80
60
40
20
0
1970 1975 1980 1985 1990 1995 2000 2005 2010 2015
6
Natural Log of RAC Crude Oil Price
5
4.5
3.5
2.5
2
1970 1975 1980 1985 1990 1995 2000 2005 2010 2015
4.5
3.5
2.5
1970 1975 1980 1985 1990 1995 2000 2005 2010 2015
1.5
0.5
1970 1975 1980 1985 1990 1995 2000 2005 2010 2015
1.5
0.5
1970 1975 1980 1985 1990 1995 2000 2005 2010 2015
0.2
0.15
0.1
0.05
0.05
0.1
0.15
0.2
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
5000
4000
3000
$/MWh
2000
1000
1000
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
5000
4000
3000
$/MWh
2000
1000
1000
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
500
400
300
$/MWh
200
100
100
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
80
60
$/MWh
40
20
20
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
80
60
$/MHw
40
20
5:00am 5:00pm
20
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
2.5
1.5
0.5
2.5
1.5
0.5
2.5
1.5
1
Sep Mar
0.5
I Significant seasonality
I March price exceeds Sept price, at least since 1960
I Why?
19
Which price?
I Commodities vary in attributes and quality
2.5
2 Wellhead
Residential
1.5 HenryHub
0.5
1975 1980 1985 1990 1995 2000 2005 2010 2015
20
Which price?
I Several varieties of wheat are grown in the US, each with
different characteristics and used for different purposes
20
18
16
14
12
Minneapolis
10
Chicago
8
KansasCity
6
4
2
0
1990 1995 2000 2005 2010
4.5
WTI
3.5
Brent
2.5
1990 1995 2000 2005 2010 2015
23
Common themes and why they matter
I Trend and autocorrelation can cause spurious inference
I Can your variable of choice explain anything after controlling for
past prices and a trend?
24
We have a question and we know our data
I Possibilities include
1. Structural (rational storage model estimated by ML)
2. Structural Time Series (linear VAR)
3. Financial Time Series (linear factor model)
4. Mostly Harmless (linear regressions with carefully chosen
instruments)
25
Rational Storage Model (e.g., Wright (2011))
I Take supply and demand curves as given
I Q = S(P) and Q = D(P)
S D
I Net supply: I = g(P) S(P) D(P)
I Inverse net supply: P = g1 (I )
Price
S(P) g(P)
inventory
D(P) demand
QD QS Quantity I Inventory
26
Representative Storage Firm
I Net supply is subject to shocks ( t ). Each period, firm chooses
how much inventory to hold (It ) and pays storage fees ()
I Equilibrium condition: P t = g 1 ( It , t )
27
Rational Storage Model Implies Kinked Demand
I Inventory mitigates price shocks demand is elastic
1
Pt = 1+r Et [Pt+1 ] if It > 0 3
1
Pt > 1+r Et [Pt+1 ] if It = 0
Price
Price
S(P) g(P)
totaldemand
inventory
D(P) demand
QD QS Quantity I Inventory
28
Temporary Supply Shock Depletes Inventory
I Zero inventory implies price spike and inelastic demand
1
Pt = 1+r Et [Pt+1 ] if It > 0
1
Pt > 1+r Et [Pt+1 ] if It = 0 3
Price
Price
S(P) g(P)
totaldemand
inventory
D(P) demand
29
Simulating Prices (Deaton and Laroque (1992))
I Large shocks more likely to be positive than negative
I Spikes occur when inventory goes to zero (i.e., market is tight)
30
What does the model imply for econometrics?
I Prices are non-Gaussian, even if shocks are Gaussian
I Deaton and Laroque (1992) found that the model didnt fit the
data
I Cafiero, Bobenrieth, Bobenrieth, and Wright (2011) showed that
this result was based on an incorrect solution of the model. A
correct solution provides a much better fit.
31
Extensions
I supply of storage curve
I The Working curve plots the price of storage () as an
increasing function of inventory (I)
I At low inventory, the price of storage can be negative.
I This is known as a convenience yield firms are willing to hold
some inventory at a loss to take advantage of potential
merchandising opportunities.
I shock dynamics
I model fit may be improved by adding autocorrelated shocks
I e.g., an iid shock may represent weather and an autocorrelated
shock may represent demand shifts
32
We have a question and we know our data
I Possibilities include
1. Structural (rational storage model estimated by ML)
2. Structural Time Series (linear VAR)
3. Financial Time Series (linear factor model)
4. Mostly Harmless (linear regressions with carefully chosen
instruments)
33
Linear VAR Models
Xt = 1 Xt1 + 2 Xt2 + ... + p Xtp + c0 + c1 t + t
t WN (0, )
I Multivariate system
I Xt may include time series on production, consumption,
inventory, demand and supply shifters, and futures
I WN white noise no autocorrelation
I Everything is endogenous
demand equation 1 12 13 pt
supply equation 21 1 23 qt = t
temperature equation 31 32 1 wt
2
1 0 0
E[t t0 ] = 0 22 0
0 0 32
I Identification problem: which variable causes which?
I With 3 variables, the data give us 3 covariances, so we can
identify 3 parameters
35
VAR Identification: Triangular system
AXt = t , t WN (0, )
demand equation 1 12 13 pt
supply equation 0 1 23 qt = t
temperature equation 0 0 1 wt
12 0 0
E[t t0 ] = 0 22 0
0 0 32
demand equation 1 12 13 pt
supply equation 0.1 1 23 qt = t
temperature equation 0 0 1 wt
12 0 0
E[t t0 ] = 0 22 0
0 0 32
demand equation 1 12 0 pt
supply equation 21 1 23 qt = t
temperature equation 0 0 1 wt
2 2
1 12 0
0 2 2
E[t t ] = 12 2 0
0 0 32
demand equation 1 12 0 pt
supply equation 21 1 23 qt = t
temperature equation 0 0 1 wt
2 2
1 12 0
0 2 2
E[t t ] = 12 2 0
0 0 32
0 0 32
totaldemand
inventorydemand
D(P)
QD QS Quantity I Inventory
41
We have a question and we know our data
I Possibilities include
1. Structural (rational storage model estimated by ML)
2. Structural Time Series (linear VAR)
3. Financial Time Series (linear factor model)
4. Mostly Harmless (linear regressions with carefully chosen
instruments)
42
Financial Time Series Models (Schwartz (1997))
I Goal: jointly fit the distribution and dynamics of futures and
spot prices
I Model:
dS = ( ) Sdt + 1 Sdz1
d = ( ) Sdt + 2 dz2
I Discrete-time version (approximate)
Xt = Xt1 + t 0.512 + 1 1t
t = + (1 )t1 + 2 2t
where Xt = ln St
1
I Recall Pt = 1+r Et [Pt+1 ]
I price equals last periods price plus price of storage plus shock
43
Financial Time Series Models (Schwartz (1997))
dS = ( ) Sdt + 1 Sdz1
d = ( ) Sdt + 2 dz2
44
We have a question and we know our data
I Possibilities include
1. Structural (rational storage model estimated by ML)
2. Structural Time Series (linear VAR)
3. Financial Time Series (linear factor model)
4. Mostly Harmless (linear regressions with carefully chosen
instruments)
45
Mostly Harmless Method (i.e., Reduced Form)
I Goal: Regress log quantity on log price and interpret the
coefficient as a supply (or demand) elasticity
qt = + pt + ut
I Disadvantage: no dynamics
46
Is the supply or demand elasticity?
qt = + pt + ut
48
History of Ethanol in the U.S.
I mid 1800s: Internal combustion engine invented
I 1920: USGS estimates that peak oil is imminent
I European agriculture recovers from WWI ag prices drop
I 1922: Henry Fords autobiography
I There is fuel in corn; oil and fuel alcohol are obtainable from
corn, and it is high time that someone was opening up this new
use so that the stored-up corn crops can be moved.
I 1920s and beyond: Texas oil boom
I Oil became cheap; no need for ethanol
I 1970s: Oil prices spiked
I 1978 Energy Policy Act - $0.40 per gallon excise-tax exemption for
blending ethanol into gasoline
I 1978, 1987, 1992, 2000, 2001, 2003, and 2004: Legislation
mandating ethanol use introduced into US Congress
49
History of Ethanol in the U.S.
50
The Renewable Fuel Standard Mandates
I The 2007 RFS raised the mandate by 5.5 billion gallons per year
51
Corn Price Rise Coincides With Ethanol Boom
I Possible models
1. Structural (rational storage model estimated by ML)
I Bobenrieth, Wright, and Zeng (2014)
4. Mostly Harmless
I Roberts and Schlenker (2013)
53
Which price?
I VAR. Carter, Rausser, and Smith (2013) use the average daily
price of corn in Central IL in March, deflated by CPI
54
Price effect depends on supply and demand elasticity
Supply equation ln(Qst ) = s + s ln(Pt ) + ut
Demand equation ln(Qdt ) = d + d ln(Pt ) + vt
ln(Q)
I Price effect = s d
Inelastic Elastic
Price
Price
S(P)
S(P)
P1
P1
P0 P0
D1(P)
D1(P)
D0(P) D0(P)
Q0 Q1 Quantity Q0 Q1 Quantity
55
Roberts and Schlenker (2013)
Supply equation ln(Qst ) = s + s ln(Pst ) + s t + fs (t) + ut
Demand equation ln(Qdt ) = d + d ln(Pdt ) + fd (t) + vt
56
Roberts and Schlenker (2013)
57
Replication of Roberts and Schlenker (2013)
Supply equation ln(Qst ) = s + s ln(Pst ) + s t + fs (t) + ut
Demand equation ln(Qdt ) = d + d ln(Pdt ) + fd (t) + vt
58
Results of replication of Roberts and Schlenker (2013)
I Effect on wheat, rice, and soybeans is almost half the corn effect
I Corn makes up about a third of calories, so zero effect on other
commodities would imply 6% total effect
I Implied effect on others is (11.3 0.33 18.1)/0.67 = 8%
59
Carter, Rausser and Smith (2013)
60
Why length of run matters: base case
Price
Price
S(P) g(P)
totaldemand
inventory
D(P) demand
Quantity Inventory
61
Transitory demand shift
Price
Price
S(P) g(P)
totaldemand
inventory
D(P) demand
Quantity Inventory
62
Permanent demand shift
Price
Price
S(P) g(P)
totaldemand
inventory
D(P) demand
Quantity Inventory
63
Carter, Rausser and Smith (2013) 4 variable VAR
1. Real futures price of corn
I Chicago futures Price in March of December futures contract
I Harvest occurs in Sept/Oct; March is middle of crop year
I March is before weather realizations that determine yield
I Deflate by CPI for all items and take logs
2. Convenience yield (negative price of storage)
I F
t,T = (Pt (1 + rt,T ) + ct,T ) (1 yt,T )
I Futures equals spot plus price of storage
I rt,T is yield on one-year Treasury notes plus 200 basis points
I Set ct,T to 5c/bu/mo in 1982-83 dollars
I We use cyt ln(1 yt,T )
3. Crop-year ending inventory in U.S.
4. Index of real economic activity (REA) (Kilian, 2009)
I index is based on dry-cargo shipping rates and is designed to
capture shifts in global demand for industrial commodities
64
Carter, Rausser and Smith (2013) Detrended Data
65
Econometric Model
AXt BXt 1 Zt Ut
REAt u1t
i u
Xt t Zt 1 t Ut 2t
ft u3t
cyt u4t
AXt BXt 1 Zt Ut
1 0 0 0 REAt
1 23 23 i
A 21 Xt t
31 32 1 0 ft
41 42 43 1 cyt
Price
S1D1
We assume Inventory
StoragePrice
Current-year demand elasticity for corn
exceeds -0.1
SS1
I1 Inventory
0 0 0 0
0 0 0 0
0 0 0 0
FuturesPrice
2
1.5
log(realprice)
0.5
0
1960 1965 1970 1975 1980 1985 1990 1995 2000 2005 2010
NoIDShocks
FuturesPrice
2
1.5
log(realprice)
0.5
0
1960 1965 1970 1975 1980 1985 1990 1995 2000 2005 2010
NoIDShocks Observed
FuturesPrice
2
1.5
log(realprice)
0.5
0
1960 1965 1970 1975 1980 1985 1990 1995 2000 2005 2010
1.5
log(realprice)
0.5
0
1960 1965 1970 1975 1980 1985 1990 1995 2000 2005 2010
76