limitations of maximum likelihood estimations
by Arnaud Bervas
Hi
What are the limitations in the format for the formulas of log-likelihood ?
I tried unsuccessfully to make a mle with the following script:
genr BUY = BUYE + BUYF
genr SELL = SELLE + SELLF
genr c1 = 0.5
genr c2 = 0.2
genr c3 = 0.2
mle loglik= log (c3*((1-c1)*((0.5*(1+c2))^BUY *(0.5*(1-c2))^SELL)+
c1*((0.5*(1-c2))^BUY *(0.5*(1+c2))^SELL)) +(1-c3)*0.5^BUY*0.5^SELL)
params c1 c2 c3
end mle
Can you see why ?
Thanks
20 years
Multicollinearity
by Clement L. Rasul
Can anyone help me. I am a new user of gretl.
I am doing OLS regression using multiple dummy independent variables. How
do I deal with multicollinearity? Gretl refuses to calculate because of
perfect collinearity. Is my approach wrong in doing multiple dummy
independent variables?
The equation specification that i am doing is:
NAT = const + b1 Dum1 + b2 Dum2 + b3 Dum3 + b4 Dum4
where:
NAT is the result of achievement tests;
const is the intercept, the value of NAT if there are no project
interventions;
b1 is the value of NAT if there is teacher traning (dummy=1);
b2 is the value of NAT if there is principal training (dummy=1);
b3 is the value of NAT if there is 1:1 student to textbook ratio
(dummy=1); and
b4 is the value of NAT if the classroom is conducive to learning (dummy =1
if it conforms to stated classroom standards)
Thanks!
Clem
20 years
Question about GARCH
by ohinata manabu
I am currently using Gretl to run GARCH model for volatility of daily
return of IBM stock estimation.
However, I can't match the result from gretl and the GARCH formula.
What I know is: ht=ω＋α（ｒ−ｍ）^2＋βσ^2
But, what I got is:
Variable Coefficient
const 0.000553614
alpha(0) 9.90527e-06
alpha(1) 0.108505
beta(1) 0.879647
Mean of dependent variable = 9.79994e-005
Standard deviation of dep. var. = 0.0244575
Unconditional error variance = 0.000836019
Log-likelihood = 2387.036
AIC = -4764.073
BIC = -4739.534
I think α(0) is ω.
But I don't know which is ht and what does const mean.
Thank you for your help.
Have a good weekend.
Manabu Ohinata
manabu0120(a)hotmail.com
20 years
(no subject)
by ohinata manabu
**********************************
MANABU OHINATA （大日向 学）
18520 Prairie St. #4Northridge, CA 91324
manabu0120(a)hotmail.com
manabu.ohinata.569(a)csun.edu
�818-390-2899
**********************************
20 years
small conflict in multiplicative ARMA
by Ignacio Díaz-Emparanza
Hello everybody (although this is specially directed to Jack and Allin)
I was playing with the ARMA dialog box for seasonal models, and I found and
small conflict with the names of the coeffients that gretl assigns in the
output. If I estimate an AR(1)xAR(1)s : (in Latex)
(1-\phi_1L)(1-\Phi_1L^s)Y_t=\epsilon_t
with, for example, quarterly data, the model output reports the coefficients
with names: varname(-1) and varname(-4) which is slightly confusing since the
coeffients of the above multiplicative model are not directly associated to
an specific lag of the dependent variable. Furthermore, if I estimate an
AR(4)xAR(1)s, gretl gives an error, since following the rule, it has to
assign the same name to the fourth AR(4) coefficient and the unique AR(1)s
one. (I obtain: "memory fault error"). Exactly the same occurs with the MA
part.
So I suggest to change the name of the coeffients in the model output:
as the literature is quite standard referring to these coefficients as \phi
and \theta, we could use phi_1, phi_2 etc for the regular AR part, and
sphi_1, sphi_2 etc (or Phi_1, Phi_2, ... with less characters) for the
seasonal part; theta_1, theta_2, ... for the regular MA and stheta_1,
stheta_2 ... for the seasonal MA.
This change is not needed for a non-seasonal model, but could be adopted for
maintaining homogeneity if you want.
--
Ignacio Díaz-Emparanza
Dpto. de Economía Aplicada III (Econometría y Estadística)
UPV-EHU
20 years, 1 month
Generalized Methods of Moments in Gretl
by Al Leong
Hi,
Thank you for developing a great package. I do enjoy
using Gretl.
I have a query and some suggestion:
Query:
Are you planning to develop a GMM module in gretl?
GMM is increasingly popular amongst economist, see
Hayashi(2001) and Alastair R. Hall (2005).
Suggestions:
1. Importing of Excel and other non-Gretl data file
should be more flexible. I tried importing an Excel
file without headings and could not. Have to type in
headings before import.
2. Very often, I add new variables by defining the
variables myself. But this is 2-3 layers down the
menu.Possible to Define New variables up one level?
3. Heteroskedasticity-correction should apply to panel
models or pooled models as well (may wish to take a
leave from Eviews 5).
4. Aspects of panel data modules could be improved,
making it easier to do fixed effect and random
effect.Panel data is very popular nowadays.
5. Running White's tests for heteroskedasticity often
crash the program.
I would be happy to elaborate on above if required.
Thank you and have a nice day
regards
chee kian
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
20 years, 1 month
further CVS bug fixes
by Allin Cottrell
Jack Lucchetti has pointed out that the fixes I committed earlier
today for the (new) "omit exogenous vars" test for VARs were not
complete: some errors remained.
I think I have now fixed the remaining errors in CVS, and in an
updated Windows snapshot.
One other thing in the Windows snapshot: I think I've fixed the
issue whereby if you chose a monochrome EMF file, you still got a
color representation of the graph.
The new lag selection mechanism still has known bugs, and I'm
working on those. The "bounding box" problem with EMFs copied to
the Windows clipboard has not been addressed yet.
Allin Cottrell
20 years, 1 month
EMF and PNG format
by John Paravantis
Jean, my ...telepathic soulmate, wrote:
---
By the way, I also tried these operations with Abiword (2.4.2) on
WinXP. The main conclusion is that you should save the graph as png
file and insert it into Abiword. Copying to the clipboard did not
work: the "paste" function in Abiword remained greyed out. Saving the
file as emf was not terrible: I was able to insert an emf file into an
Abiword document, but the colors were inverted. I obtained a graph
with a black background. However, inserting a gretl-generated png file
into Abiword worked just fine
---
I just want to reiterate that the PNG format is bitmaped and thus does not zoom gracefully neither it is acceptable for, say, journal submission. So going via PNG is NOT, in my humble opinion, a good option; I had rather import the enhanced metafile into Word/OO and just crop the margins.
I am hoping Allin will eventually pull another one out of his hat and correct this too!
John
20 years, 1 month
function
by Ignacio Díaz-Emparanza
Hello everybody,
I tried to build my first gretl function with no much sucess. The exercise is
very simple: write a function to obtain the theoretical simple correlations
for an AR(2) process, depending only on two parameters phi1 and phi2.
The following script works ok:
---------------
nulldata 20
series y = 1.0
scalar phi1 = 0.4
scalar phi2 = 0.5
scalar rho1 = phi1 / (1-phi2)
genr y[2] = rho1
genr y = phi1*y(-1)+phi2*y(-2)
genr y1 = y(1)
------------
So the series y1 contains the theoretical correlations.
I wrote the following script, based on the information of the manual, but the
function does not work:
--------
nulldata 20
# function definition
function corrAR2 (scalar phi1, scalar phi2)
series y = 1.0
scalar rho1 = phi1 / (1-phi2)
genr y[2] = rho1
genr y = phi1*y(-1)+phi2*y(-2)
genr y2 = y(1)
return series y2
end function
# function call
(y1) = corrAR2 0.4 0.5
--------
Which is the problem?
I tried it with official gretl-1.5.0 in mandrivalinux, and also with the
current Windows snapshot. There were no errors or warnings and I obtained
only a series with zeroes.
--
Ignacio Díaz-Emparanza
Dpto. de Economía Aplicada III (Econometría y Estadística)
UPV-EHU
20 years, 1 month
