![Coming to Your Field Soon: A Primer on VAR’s and VECM’s A time series methodology originating in macroeconomics [Sims 1980], now popular in finance – soon to take over your field too! efrizal on VAR's and VECM's](https://image.slidesharecdn.com/vecm-100625123132-phpapp02/85/Vecm-1-320.jpg)
![The math – page 2 Now substitute the right hand sides of the backshifted equations for the right hand side variables in the original equations to get: x t = 0 + 1 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + 2 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + t y t = 0 + 1 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + 2 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + t efrizal on VAR's and VECM's](https://image.slidesharecdn.com/vecm-100625123132-phpapp02/85/Vecm-16-320.jpg)
![The math – page 3 These equations are a mess, but we can gather terms to get: x t = [ 0 + 1 0 + 2 0 ] + [( 1 ) 2 + 2 1 ]x t-2 + [ 1 2 + 2 2 ]y t-2 + [ t + 1 t-1 + 2 t-1 ] y t = [ 0 + 1 0 + 2 0 ] + [( 1 1 + 1 2 ]x t-2 + [ 1 2 + ( 2 ) 2 ]y t-2 + [ t + 1 t-1 + 2 t-1 ] This is still a mess, but the essential point is that each variable still depends on lags of both variables, and a more complex set of errors efrizal on VAR's and VECM's](https://image.slidesharecdn.com/vecm-100625123132-phpapp02/85/Vecm-17-320.jpg)
![What’s a variance decomposition? Once we’re done backshifting and substituting, what’s left is a constant plus errors Any variance of the variable must come from those errors But….the errors have a variance that we already know because it gets estimated when we run the regression Again, for x (after one backshift and substitution): Var(x) = E[( t + 1 t-1 + 2 t-1 )( t + 1 t-1 + 2 t-1 )] Var(x) = ( ) 2 + ( 1 ) 2 ( ) 2 + ( 2 ) 2 ( ) 2 Note that the first term is from t, and the last two are not So, 100% of the variance of x at t comes from shocks to x ( ’s) However, the variance of x at t+1 comes from 2 sources {( 1 ) 2 ( ) 2 /[( 1 ) 2 ( ) 2 + ( 2 ) 2 ( ) 2 ]} from x {( 2 ) 2 ( ) 2 /[( 1 ) 2 ( ) 2 + ( 2 ) 2 ( ) 2 ]} from y efrizal on VAR's and VECM's](https://image.slidesharecdn.com/vecm-100625123132-phpapp02/85/Vecm-23-320.jpg)
More Related Content
Vecm
- 1. Coming to Your Field Soon: A Primer on VAR’s and VECM’s A time series methodology originating in macroeconomics [Sims 1980], now popular in finance – soon to take over your field too! efrizal on VAR's and VECM's
- 2. What do the acronyms stand for? VAR: vector autoregression Vector indicates the more than one variable will be predicted Thus, a set of regressions is run (simultaneously) Autoregression indicates that variables will be regressed on their own past values VECM: vector error correction model Simply a VAR with a specific type of coefficient restriction imposed Cointegration indicates whether those restrictions are useful efrizal on VAR's and VECM's
- 3. What’s the practical benefit of a VAR? How do you capture a relationship that changes through time? Probably not with a linear regression However, a VAR, which amounts to a set of inter-related linear regressions can do this efrizal on VAR's and VECM's
- 4. Example 1 from Macroeconomics Fisher Effect Suppose the Federal Reserve pursues an expansionary monetary policy – essentially they put new money into circulation Interest rates drop in the short-run Since the Fed buys bonds to get the money out Interest rates rise in the long-run Because the additional money in circulation allows the prices of goods to be bid up efrizal on VAR's and VECM's
- 5. Example 2 from Macroeconomics The J-Curve Suppose a country devalues their currency to improve their trade position GDP goes down in the short-run Since prices of foreign intermediate products rise immediately, production falls GDP goes up in the long-run Ultimately, domestic producers are able to adjust quantities and export more at a low price efrizal on VAR's and VECM's
- 6. What’s the benefit to a researcher of using a VAR? A VAR requires less restrictive (easier to justify) assumptions than other multi-variable methods It doesn’t obviate the identification problem, but it does: Eliminate the linear algebra associated with it Couch the problem in terms that are simpler for the practitioner to apply efrizal on VAR's and VECM's
- 7. What do you need to choose to set up a VAR? A (small) set of variables Six is about the upper limit A decision on a lag length The same length for each variable Longer is preferable with this method A decision about whether you need to include any other deterministic variables Like trends, dummies, or seasonal terms efrizal on VAR's and VECM's
- 8. What would the resulting VAR look like? A system of equations One for each variable of interest This VAR consists of two variables, 1 lag (of each variable on the right hand side), and a constant x t = 0 + 1 x t-1 + 2 y t-1 + error y t = 0 + 1 x t-1 + 2 y t-1 + error efrizal on VAR's and VECM's
- 9. How do you estimate the VAR? (It can be proved that) there are no gains to methods more complex than OLS, provided that each equation has the same set of right hand side variables So, you could estimate this in Excel Generally, you want to produce ancillaries A specialized time series package like RATS, TSP, or E-Views is worthwhile for this efrizal on VAR's and VECM's
- 10. What do the estimates of the VAR look like? You don’t care Personally, I rarely if ever even look at them efrizal on VAR's and VECM's
- 11. How is that justified? When you estimate a parameter in a regression, you estimate two things The parameter itself The standard error of the parameter Omitting a relevant variable from the regression biases the parameter and standard error estimates You can’t easily predict which way Adding an irrelevant variable from the regression biases the standard error estimate (upward) But….the parameter estimate is fine efrizal on VAR's and VECM's
- 12. How is that justified (cont’d)? With a VAR, when in doubt, you add extra lags to the right hand side This make sure that you don’t omit anything So, your parameter estimates are fine However, you almost certainly included too much So, your standard errors go through the roof As a result, your t -statistics are likely to indicate that your parameters are insignificant efrizal on VAR's and VECM's
- 13. If you’re not interested in the significance of the parameters, what is the point of estimating a VAR? VAR’s can be re-expressed as ancillaries Impulse response functions (Forecast error) variance decompositions Historical decompositions The last one is rarely used efrizal on VAR's and VECM's
- 14. Why do we need VAR ancillaries? There is a lot more going on in a simple VAR system than meets the eye x t = 0 + 1 x t-1 + 2 y t-1 + error y t = 0 + 1 x t-1 + 2 y t-1 + error Suppose y changes at t-1 Then x and y change at t Both of which will cause x and y to change again at t+1 This process could continue forever, so you need a way to sort those effects out and organize them efrizal on VAR's and VECM's
- 15. The math – page 1 Write the system more specifically x t = 0 + 1 x t-1 + 2 y t-1 + t y t = 0 + 1 x t-1 + 2 y t-1 + t Note that you can “backshift” the equations x t-1 = 0 + 1 x t-2 + 2 y t-2 + t-1 y t-1 = 0 + 1 x t-2 + 2 y t-2 + t-1 efrizal on VAR's and VECM's
- 16. The math – page 2 Now substitute the right hand sides of the backshifted equations for the right hand side variables in the original equations to get: x t = 0 + 1 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + 2 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + t y t = 0 + 1 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + 2 [ 0 + 1 x t-2 + 2 y t-2 + t-1 ] + t efrizal on VAR's and VECM's
- 17. The math – page 3 These equations are a mess, but we can gather terms to get: x t = [ 0 + 1 0 + 2 0 ] + [( 1 ) 2 + 2 1 ]x t-2 + [ 1 2 + 2 2 ]y t-2 + [ t + 1 t-1 + 2 t-1 ] y t = [ 0 + 1 0 + 2 0 ] + [( 1 1 + 1 2 ]x t-2 + [ 1 2 + ( 2 ) 2 ]y t-2 + [ t + 1 t-1 + 2 t-1 ] This is still a mess, but the essential point is that each variable still depends on lags of both variables, and a more complex set of errors efrizal on VAR's and VECM's
- 18. The math – page 4 If we kept backshifting each equation and substituting back in, we’d ultimately get equations that looked like this: x t = constant + x x t-n + y y t-n + lots of errors y t = constant + x x t-n + y y t-n + lots of errors Note that the ’s and ’s, as well as the errors would be big functions of all of the ’s and ’s from the original equations efrizal on VAR's and VECM's
- 19. How do we sort out what’s going on here? One result that you can count on is that most of the ’s and ’s will be less than one in absolute value Only unstable processes will have a lot of ’s and ’s that are outside of this rang – and we don’t usually think of our world as unstable This is important because: The ’s and ’s are composed of products of ’s and ’s – which go to zero the more we backshift The “lots of errors” are composed of sums of ’s and ’s weighting the errors – which don’t go to zero efrizal on VAR's and VECM's
- 20. The significance of the math If we backshift enough, each series can be shown to be equal to A constant Which is the mean of the variable A (weighted) sum of past errors These come from all variables These are the shocks that buffet the variables efrizal on VAR's and VECM's
- 21. What do we do with this result? We construct two VAR ancillaries to summarize how and why a variable gets away from its mean Impulse response functions These trace out how typical shocks will affect a variable through time Variance decompositions Show which shocks are most important in explaining a variable through time efrizal on VAR's and VECM's
- 22. What’s an impulse response function? Recall the error term obtained for x t on slide 17 (after one backshift and substitution had been made) t + 1 t-1 + 2 t-1 The impulse response function is the pattern of how a shock affects x – it can be read off the coefficients A shock to x (an ) affects x immediately, and continues to affect x next period (the weight, 1 may amplify or diminish the shock), and stops affecting x after that A shock to y (an ), does not affect x at all right away, affects it with a weight of 2 the next period, and stops affecting x after that efrizal on VAR's and VECM's
- 23. What’s a variance decomposition? Once we’re done backshifting and substituting, what’s left is a constant plus errors Any variance of the variable must come from those errors But….the errors have a variance that we already know because it gets estimated when we run the regression Again, for x (after one backshift and substitution): Var(x) = E[( t + 1 t-1 + 2 t-1 )( t + 1 t-1 + 2 t-1 )] Var(x) = ( ) 2 + ( 1 ) 2 ( ) 2 + ( 2 ) 2 ( ) 2 Note that the first term is from t, and the last two are not So, 100% of the variance of x at t comes from shocks to x ( ’s) However, the variance of x at t+1 comes from 2 sources {( 1 ) 2 ( ) 2 /[( 1 ) 2 ( ) 2 + ( 2 ) 2 ( ) 2 ]} from x {( 2 ) 2 ( ) 2 /[( 1 ) 2 ( ) 2 + ( 2 ) 2 ( ) 2 ]} from y efrizal on VAR's and VECM's
- 24. Reporting VAR ancillaries Typically, the software produces a ton of numbers in tabular form when you ask for these The numbers are rarely reported Generally, authors provide plots of both An impulse response function graph shows you whether a shock to one variable has: A positive or negative affect on another variable (or both) An effect the strengthens or diminishes through time A variance decomposition graph shows you how the sources of variation underlying a variables movements wax and wane through time efrizal on VAR's and VECM's
- 25. What’s the biggest problem with VAR ancillaries in published research? The ancillaries are non-linear combinations of a large number of underlying parameter estimates Unfortunately, parameters estimates are point estimates They are correct with probability zero So, all VAR ancillaries are also point estimates How do we get around this? It isn’t very hard, and most programs can produce confidence intervals for VAR ancillaries So …. what’s the beef? Many articles don’t include these confidence intervals because they are very wide – indicating a lot of uncertainty in the results efrizal on VAR's and VECM's
- 26. What’s the catch? At first glance, it seems like applying a VAR is nothing more than applying some (time consuming) arithmetic to plain old OLS regressions This isn’t the case. All multi-variable estimation problems require the researcher to address something called the identification problem Prior to VAR’s (and still with other methods) this required solving a sophisticated linear algebra problem The difficulty of this problem goes up geometrically with the size of the model you’re working with VAR’s still require that the identification issue be addressed, but the question is couched in a form that is easier to tackle The difficulty of this problem need not go up too quickly efrizal on VAR's and VECM's
- 27. What’s the identification problem? Consider a basic microeconomic situation We don’t observe demand and supply What we do observe is a quantity sold and a price This is just one point on the standard microeconomics graph At some other time, we may observe a different quantity sold at a different price This again is just another point on the graph How did we get to that new point? Did supply shift? Did demand shift? Did both shift? This is the identification problem efrizal on VAR's and VECM's
- 28. How do we (conceptually) identify a supply or a demand? This is actually pretty easy If only one of the curves shifts, the equilibrium will move along the other curve – tracing it out In order to get only one curve to shift, it must be pushed by some variable that only affects that curve, and not the other one. For example: Changes in personal income will cause demand to shift, but are often irrelevant to the firms supply decisions Changes in input prices will cause supply to shift but are often irrelevant to the households demand decisions efrizal on VAR's and VECM's
- 29. How do we (mathematically) identify a supply and a demand? Write out an equation for each one. I assume that they each relates prices and quantities, along with two other (shift) variables R and S. For now, it is important to include both of those variables in both equations D: P = a 0 + a 1 Q + a 2 R + a 3 S + demand error S: P = b 0 + b 1 Q + b 2 R + b 3 S + supply error Identification amounts to saying that only one of R or S affects demand, and the other one affects supply. This amounts to the following restrictions: a 2 = b 3 = 0, or alternatively b 2 = a 3 = 0 Justifying restricting a whole bunch of parameters to zero before you even start running regressions makes this tough efrizal on VAR's and VECM's
- 30. How does identification differ in VAR’s? Part 1 Suppose you are trying to get information about how 2 variables, Y and Z, behave. First, you would right down a system of 2 structural equations: Y t = c 0 + c 1 Z t + c 2 Y t-1 + c 3 Z t-1 + t Z t = d 0 + d 1 Y t + d 2 Y t-1 + d 3 Z t-1 + t These equations are similar to those on the previous slide – I just replaced R and S with past values of Y and Z These equations are structural in the sense that they contain contemporaneous values of both variables of interest in each equation Also, because we are claiming that these represent some underlying structure, we assume that the two errors are uncorrelated efrizal on VAR's and VECM's
- 31. How does identification differ in VAR’s? Part 2 All multi-variable estimations require that the structural equations be estimated by first obtaining and estimating the systems reduced form equations Reduced forms are what is meant in algebra when you solve equations – two equations can be solved for two variables, in this case y t and z t , in each case by eliminating the other variable from the right hand side to get: Y t = e 0 + e 2 Y t-1 + e 3 Z t-1 + a function of both errors Z t = f 0 + f 2 Y t-1 + f 3 Z t-1 + another function of both errors The e’s and f’s will be some messy combination of the underlying c’s and d’s from the structural equations efrizal on VAR's and VECM's
- 32. How does identification differ in VAR’s? Part 3 We now have the original structural system: Y t = c 0 + c 1 Z t + c 2 Y t-1 + c 3 Z t-1 + t Z t = d 0 + d 1 Y t + d 2 Y t-1 + d 3 Z t-1 + t 10 things need to be estimated here: four c’s, four d’s and the variances of the two errors (recall that their covariance is zero) We also have the equivalent reduced form system: Y t = e 0 + e 2 Y t-1 + e 3 Z t-1 + a function of both errors Z t = f 0 + f 2 Y t-1 + f 3 Z t-1 + another function of both errors When we estimate this we get 9 pieces of information about the 10 that we are trying to estimate above (three 3’s, three f’s, variances of two errors, and one covariance between the - now related - errors) efrizal on VAR's and VECM's
- 33. How does identification differ in VAR’s? Part 4 An alternative way of thinking about identification is that we can only estimate as many structural parameters as we have pieces of information from the reduced forms Thus, we have to eliminate one thing of interest in the structural system This may seem somewhat egregious, but recall that in the economic example I gave that we had to restrict two parameters to zero – so we are already better off here! efrizal on VAR's and VECM's
- 34. How does identification differ in VAR’s? Part 5 We can safely eliminate any of the ten parameters in the structural system – but we must eliminate some of them to achieve identification Here’s where a VAR makes your life easier Rather than constraining a parameter on two of the lags to zero, we constrain one of the parameters on the contemporaneous terms to zero The former is tantamount to saying that particular variables from the past do not cause other variables today The latter is saying something less egregious – that certain variables don’t affect other ones right away. This is an easier thing to explain and justify. efrizal on VAR's and VECM's
- 35. How does VAR identification work in practice? Identifying a VAR amounts to choosing an “ordering” for your variables If you have n dependent variables, they can be rearranged into n! orders The researchers job is to pick one of those orders What makes a good order? An argument that one variable (say X) is likely to affect some other variable (say Y) before Y can feed back and affect X efrizal on VAR's and VECM's
- 36. An example of VAR identification A common set of variables in a macroeconomic VAR includes output, money, prices, and interest rates (Y, M, P, and r) There are 24 possible orderings YMPr, YMrP, YPMr, YPrM, rPMY, and so on A plausible ordering would be M, r, Y, P The Federal Reserve controls M, and isn’t likely to respond quickly to the other variables The Federal Reserve is trying to influence r By influencing r, the Federal Reserve hopes to influence Y and P Most first adjust quantities faster than prices, so I put Y before P efrizal on VAR's and VECM's
- 37. How sensitive are VAR’s to ordering? This question doesn’t have a good answer There are big differences across the set of possible orderings, but a good researcher knows that most of those orderings aren’t justifiable A good convention to go by is that if you have trouble figuring out which variable should precede and which should follow, it probably won’t make much difference to the VAR ancillaries either efrizal on VAR's and VECM's