Quantcast
Channel: EViews
Viewing all 24155 articles
Browse latest View live
↧

HDecomp (historical decomposition)

July 13, 2016, 8:17 am
$
0
0
valleire wrote:Hi Trubador,

When using the historical decomposition, I am looking to identify the SVAR using the Choleski Decomposition which you have provided

However, there does not appear to be any place to provide the casual ordering necessary to identify the SVAR using the Choleski Decomposition approach. (This is present on the other hand on the impulse analysis and variance decomposition pre-programmed eviews options)

How do I set my recursive ordering, similar to the eviews options, with your add in using the Choleski Decomposition?

Many Thanks

There is no need to use SVAR if you'll apply recursive ordering as it is the default factorization of regular VAR. However, you can obtain cholesky decomposition within SVAR framework as follows: viewtopic.php?f=5&t=13431#p46638

↧
Search

Sporadic error in exporting to excel

July 13, 2016, 8:39 am
$
0
0
Dear Forum users,

When running the routine below to extract data into excel, I get sporadic errors saying that the target file does not exist or eviews stops working altogether, Running the program again more often than not the error vanishes. This is a problem because getting to the results is quite time consuming.

Is there something in the routine that is confusing eviews?

many thanks for your help
Michele

Code:

'-------------------------------------------------------
'    4.1 EXPORT 1
'-------------------------------------------------------
vector(7)     percentiles                            'Store percentiles to extract
percentiles.fill 10, 20, 40, 50, 60, 80, 90                'Define percentiles of interest

'Export replications
for %s bl ub lb
    for %perc dgdp pbgdp  ints intlm spread intlnm i_eff iegdp rgy piy w
        group    g_{%s}_{%perc}            'Group to store results
        for %d ps ts
            for !i     =    1 to @rows(percentiles)
                !j    =    percentiles(!i)                                                        
                g_{%s}_{%perc}.add {%d}_{%s}_{%perc}_perc_!j
                next
            next
        wfsave(type=excelxml, mode=update) "Myfile1.xlsx" range={%s}_{%perc} @smpl {%firstp}-4 {%lastp} @keep {%s}_{%perc}_0 g_{%s}_{%perc}
        next
    next

'-------------------------------------------------------
'    4.2 EXPORT 2
'-------------------------------------------------------

group g_baseline
group g_dgdp
for %s bl ub lb
    g_baseline.add {%s}_dgdp_0 {%s}_pbgdp_0 {%s}_iegdp_0 {%s}_intlnm_0 {%s}_i_eff_0 {%s}_w_0
    g_dgdp.add g_{%s}_dgdp
    next

for %group g_baseline g_dgdp
    wfsave(type=excelxml, mode=update) "Myfile2.xlsx" range={%group} @smpl {%firstp}-4 {%lastp} @keep {%group}
    next



↧
↧

Sporadic error in exporting to excel

July 13, 2016, 8:52 am
$
0
0
There is nothing obviously wrong with the code. Off the top of my head, possible causes would be either some network/disk issue, or that Excel is acting funky. The mode=update means that EViews actually uses Excel to create the file, and sometimes Excel can be a bit weird.

↧

programming graphs

July 13, 2016, 9:44 am
$
0
0
Hi,
I am using Eviews 9.
I would like to edit manually program the size of the individual graphs contained in a merged graph object.
Eviews by default makes them all equally sized.
I have been able to alter individual graph sizes by using the menu driven commands:
by selecting each graph individually, selecting Graph Options, Frame & Size, Size and Indents and changing the Frame Size .
The resulting graph exported to png is cool.png, the starting point for my menu driven changes was equitydouble.png

Is there any programming command to change these frame parameters?

Thanks in advance,

giovanni

↧

programming graphs

July 13, 2016, 9:48 am
$
0
0
You have to change each graphs' size prior to merging them into a big one.

↧
↧

DCCGARCH11

July 13, 2016, 11:32 am
$
0
0
debbysoraya wrote:Hey,

So right now I am estimating bivariate dcc garch (return in 2 indices such as s&p500 and klse).
Some of the paper that I read,
define the mean equation such: r_t=γ_0 + γ_1 r_(t-1)+ γ_2 r_(t-1)^us + ε_t ( I attached the paper's method and result) , it uses ar(1) process in the mean equation

My question is, every time I put Rus and Rmy in the return series and put 1 in the ar process for mean equation box, the rho that is produced is not series instead it's only give me one number (for the first day) whereas i supposed the rho_12_01 supposed to give series right?


I wonder, if I put only Rus and Rmy ( I got the series of rho_12_01) without including ar(1) and later I modify the estimation that is saved under eq_garch_r2_01 (meaning after the dcc then i go back to the univariate garch estimation and change the command there and include the ar(1))? is this violating the dcc proposed by engle somehow?


THANKS A LOT!!!


For the technical difficulties you experience during the estimation, please see previous posts:
trubador wrote:1) Since this is a two-step model, you should check the first step (i.e. estimation of univariate GARCH models) to see if everything is OK. Try alternative GARCH models.
2) Model may become ill-defined or inconsistent after including an exogenous variable or an AR term. Try dropping them or find better RHS variables.
3) Starting values of coefficients may be too far from an optimal solution. Try different initial parameter values (i.e. theta vector).
4) Correlation targeting may be too restrictive. Try unchecking this option.
5) Sample period may not be appropriate to carry out such an analysis. Try adjusting the sample.
6) Optimization algorithm may perform poorly. Try other alternatives.
7) Algorithms may fall out the domain of estimation parameters. Try optimizing the squared coefficients.

Such models are nonlinear in nature and therefore there is no guarantee that they will always converge and yield proper estimation results. It really needs "your" time and effort to get it work.

And note that the estimated model in the paper you cited uses the return of US index as an exogenous variable (i.e. the second box in the add-in).

↧

Root Mean Square Error in Forecasting

July 13, 2016, 11:40 am
$
0
0
That's the way how RMSE (or any other evaluation metric) is computed. There is nothing inherently wrong here. Whether or not to keep insignificant variables in the model is up to you (based on the research question, hypotheses and other statistical criteria of course).

↧

How to read the result of BEKK GARCH model for testing volatility spillover between Asian stock markets

July 13, 2016, 11:50 am
↧
Search

FOR Loop!

July 13, 2016, 1:04 pm
$
0
0
Hi,

I'm actually quite new at programming. To be honest, I don't know much about the subject. I am working on my dissertation at the moment and using a bit database.

For one of the steps I need to run regressions for a great amount of companies against a couple of indices and two more time series. I am trying to build a FOR loop that helps me do this at once and saves one of the coefficients on this new variable that I created.

I would really appreciate if anyone could help me with this.

My data has the dates on the first column and on the first row I have an identifier "firm_name of the companyX" the rest is filled with returns on each stock.

Could anyone tell me if this is anyhow closed to how my FOR should look like? Thanks!


For !columns = @columns(group1)

equation column(group1) c IndVariable1 IndVariable2 IndVariable3 IndVariable4 #Trying to regress each column with the other variables

----------how to save the coefficient from variable lets say 2 into a new series??


next

Notes: group1 - group with all the returns for all the firms analysed <-- is it correct to do that?

↧
↧

FOR Loop!

July 13, 2016, 2:30 pm
↧

Generalized variance decomposition

July 14, 2016, 1:01 am
$
0
0
I do have the same problem. Any answer would be appreciated.

↧

A problem in working with "FOR" Loop

July 14, 2016, 5:41 am
$
0
0
i have problem, when i want to run this program:

Code:

for  !k=-7 to  0  step  0.001
equation  equ1.ls  y  c  x*(x<=!k)   x*(x>!k)    m1  m2  m3
series        ssr11(!k)=equ1.@ssr
series        kkk(!k)=!k
next


this is a threshold model.i must save SSR and !k for each equation.
but negative index or decimal values are not acceptable as index for !k.
please help me.

↧

Help! Comparing Likert Scale Variables with Dummy Variable

July 14, 2016, 7:40 am
$
0
0
Hello,

I have conducted a survey, which consisted 5 questions about buying impulsiveness. The five questions are based on likert scale. The dummy variable is If the respondents have purchased daily deal before or not. I want to see if the impulsiveness in online shopping has positive influence on daily deal purchasing. I don't know how I can compare all 5 questions with the dummy variable or should I do them separately?

Thank you!
Petya

↧
↧

Sporadic error in exporting to excel

July 14, 2016, 8:08 am
$
0
0
Hi Garreth, Thank you for looking through it.
Is there any more reliable way to export data so that it is excel readable?

Thanks
Michele

↧

A problem in working with "FOR" Loop

July 14, 2016, 8:14 am
$
0
0
What are you hoping to do with this:
Code:

series        ssr11(!k)=equ1.@ssr


↧
Search

A problem in working with "FOR" Loop

July 14, 2016, 8:52 am
$
0
0
Make two vectors. Store the argument k in one and the result in the other. Then index by 1,2,3...

↧

A problem in working with "FOR" Loop

July 14, 2016, 9:31 am
$
0
0
I want to save SSR of each equation and also !k values.

↧
↧

A problem in working with "FOR" Loop

July 14, 2016, 11:35 am
$
0
0
Yes, but what exactly are you doing with that line? Explain in words what it is doing.

↧

Threshold Structural VAR

July 14, 2016, 1:23 pm
$
0
0
Hello,

While trying to run the THSVAR program I received the following error message: "Invalid (or out of range) coefficient or matrix index 0."

I'm trying to run a VAR with the following five variables: rgdp_growth, inflation, fedfunds, baa_gs10, and assetsgr. The threshold variable is baa_gs10_ma.

I've tried various combinations of the variables along with different sample periods and options but cannot produce the impulse response functions.

Any help is greatly appreciated. Thanks in advance!

↧

rtadf

July 14, 2016, 4:19 pm
$
0
0
Hey guys i just ran my model today using the add-in.. and i was wondering how exactly can we do see the date-stamping, i am a bit new to this.
Thank you in advance.

Vasileios

↧
Viewing all 24155 articles
Browse latest View live
Search
<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>