Log in

Econometrics Forum [entries|archive|friends|userinfo]
Econometrics Forum

[ userinfo | livejournal userinfo ]
[ archive | journal archive ]

Binary Dependent Variables and Oversampling [Aug. 14th, 2009|08:39 pm]
Econometrics Forum


I am running a probit analysis of a set of variables. However, the observations that report y=0 are very low (79) compared to y=1 (2700).

Could I oversample from the first lot - i.e. duplicate samples - to get something more of an even keel? As I am not interested in the incidence of yes/no, just what makes yes happen, and no happen, I can't see why it would be a problem...

Your thoughts appreciated. If you have any other solution, that would be great also!

linkpost comment

weakly dependent time series [Jul. 28th, 2009|11:00 pm]
Econometrics Forum
Can anyone help me with the variance of a weakly dependent time series? Or point to resources that might help?

link2 comments|post comment

hello there [Jul. 26th, 2009|09:58 pm]
Econometrics Forum
Anyone wish they had my user name? :)
link2 comments|post comment

need help: ARDL [May. 20th, 2009|06:27 pm]
Econometrics Forum
Dear all,

I need some reference to help me doing my thesis about ARDL cointegration method

anybody can tell me where i can find this journal without any charges:

Pesaran, M.H., Shin, Y. (1998). An autoregressive distributed-lag modelling approach to cointegration analysis.

linkpost comment

Vector Autoregression with exogenous variable (VARX) [Apr. 30th, 2009|10:52 am]
Econometrics Forum

Hi to everybody,

my problem is the following.

I have four time series.

Three are used for a common vector autoregression (VAR) model to predict thei values in t+1.

I now want to add the fourth as an exogenous variable, but I do not understand how to do it - since I did not find any good documentation which could explain me the theory behind it.

I want to program it in MatLab, and with regards to the exogenous variable I am requested to add "

Exogenous inputs. nPX paths of regression design matrices associated with T observations of an n-dimensional time series process, where each design matrix linearly relates nX exogenous inputs to each time series at each observation time. X is a T-by-nPX matrix of cell arrays with n-by-nX design matrices in each cell. If Y has multiple paths, X must contain either a single path or no fewer than the same number of paths as in Y. Extra paths are ignored."

Let's say that the three variables are given by the vectors:


and the exogenous variable by:


How should this work, both from a theoretical and programming point of view??

I am using the vgxvarx function found here: http://www.mathworks.com/access/helpdesk/help/toolbox/econ/index.html?/access/helpdesk/help/toolbox/econ/brzylmf.html


link1 comment|post comment

autocorrelation and cross country analysis (NO panel data) [Apr. 13th, 2009|05:58 pm]
Econometrics Forum

I have the task to check a macroeconomic log log regression model for autocorrelation. The data I am working with is from 2006. It is NOT a time line. So I do not even have an idea what autocorrelation could possibly look like or how I could imagine it. I was reading quite a lot in my econometric books. I did check google and some blogs. All I know is there CAN be autocorrelation in cross section data. But that is about all I found on this topic. My Statistic program (stata) requires (logically) a time variable to be defined before I can check fore autocorrelation. So I can not make the Durbin Watson test. Any Idea?

Thanks for any answerer.

link5 comments|post comment

Real face of crisis [Apr. 13th, 2009|12:04 am]
Econometrics Forum

Crisis in Zimbabwe has begun in 2000 after president Mugabe has taken away the graund of white and has given to black people. At once all agrarian sector was stopped, against the country have entered sanctions, inflation has begun.
This year inflation has made record 231 million percent a year.
Have you understood this figure? 231 000 000 % a year. Unemployment - 80 %, third of population have left the country.

Now let's look photos which you hardly will see in other countries of the world.

Here the boy the beggar receives a trifle in December of last year. Notes on 200 000 Zimbabwean dollars.

Read more about crisis (26 photos inside) →
linkpost comment

Functional Form [Apr. 8th, 2009|11:21 am]
Econometrics Forum

I'm looking at a linear multiple regression investigating demand functions relative to the price of other goods, and have decided to change the functional form of the linear model.

In doing this I have found that a Log-Log model is far better than a Lin-Lin or Lin-Log model as it passes both normality and hetroskedasity.

Why is this is the case?

Also, I have read that it helps make the variable independant or something (basically i have no clue!)

So does anyone know why you'd change the functional form, other than to try and pass tests of normality etc?

If you do know and happen to know a reference could you add that?


link2 comments|post comment

A graduate question [Feb. 28th, 2009|06:31 pm]
Econometrics Forum
 Hi everyone,

This is my first ever post here and I don't know things work here. I have been trying to solve this question from Greene's Econometric Analysis since quite some time but not been able to do it..
It would be great if any of you could help me out..The answer's not given in the solution manual either.
Here's the question - 

I would be extremely thankful if someone could help me.
link1 comment|post comment

Time Series [Feb. 19th, 2009|02:34 pm]
Econometrics Forum
Hi guys this is my first post on livejournal. So im currently studying time series analysis and have a massive assignment due on it. the problem is that  im not too sure if i have understood the order of methodology correctly and was wondering if you guys could help out.
So lets say you have some series Y(t) which you want to forecast.
Now is the first thing to do is to determine the model structure (i.e. lag lengths) i.e. AR(p), MA(q) or ARMA(p,q), and then estimate the model (after adjusting for trends etc)
after this has been determined do you then carry out unit root tests(i.e DF or ADF) on the AR component of the selected model(even if the model is ARMA) and then forecast if the series turns out to be stationary

THanks for the help .
link1 comment|post comment

[ viewing | 10 entries back ]
[ go | earlier/later ]