Sunteți pe pagina 1din 28

Computational Toolsfor Econometris andStatistics

Mariano MatillaGarca

Econometric andStatistical Available Software


What for?
Currently you cannot doanything (econometrics) without softwareaid But,there aremany possible choices,what should Ichoose?
First,let us see the options Then we will find aprocuder for choosing the one you need

2generaltypes ofsoftware
Type1:Cannedpackages
Pros:
Youdontneedtoknowtheformulas Youcandoeverydaywork Dontneedprogramming

Cons:
Sometimestheuserdoesnotknowwhatis(s)hedoing: blackbox Youcannotexperimentonnewresults Youcannotupdatenewresultsuntiliscommercially attracive

2types cont
Type2:Languageprograms(nonbasiclevel)
Youneedtolearnhowtointeractwiththeprogram, Youcandowhatyouwanttodo,attheriskofdoingit wrong Therearebunchesofcodeforhandlingeverydaytasks Note:Isuggestreadingthisreference:
McCullough,B.D.andVinod,H.D.(1999):"TheNumerical ReliabilityofEconometricSoftware", JournalofEconomic Literature,vol.27,june,pp.633665

CannedPackages
Forstatistics,andsomeeconometricstools
SPSS(WindowsandMac) SAS(Windows) Bothextremelyfantasticforpresentations

Foreconometricsandstatistics
Eviews:candoalmosteverythingineconometrics
www.eviews.com LinuxandMacusers:(www.tspintl.com)

Stata:realcompetitor
(www.stata.com)

Youpayforthem,butnotforGRETL (http://gretl.sourceforge.net/)

Allofthemhaveveryactivecommunities

Matrix oriented programming languages


Commercial
Matlab:(www.mathworks.com) Gauss(www.aptech.com) Rats

FreeunderGNUlicense
Octave(windows,macandlinux users) R/(http://www.rproject.org/) Ox(http://www.doornik.com/index.html

Arethese all available ones?


NO,ofcourse.Youshouldtakealookat: http://www.oswego.edu/~economic/econsoftw are.htm HowcanIbeabletolearnallofthem?
Youcan,ifwanted;butthereisnoneed Youcanlearnhowtoprograminoneandthenthis knowledgewillsmooththewayforothers(incase youdesperatelyneedthem)

Instalation Octave

Download other Version


Step 1:go to http://sourceforge.net/projects/octave/files/Octave_Win dows%20 %20MinGW/Octave%203.2.4%20for%20Windows%20Mi nGW32%20Installer/ andinstall inthe OCTAVEdirectory,but inadifferent folderthan the other version you have Octave3.2.4_i686pcmingw32_gcc4.4.0_setup.exe Notice that this ISNOTthe version INSTALLEDatclass Step 2:Modify inGUIOCTAVEthe route where you have OCTAVE

Step 2

Steps 3and4
Step 3:Then exit GUIOctave andthen openagain GUIoctave andwrite down the next 3lines (lineby line)
pkg rebuildauto pkg rebuildnoauto adwindows pkg rebuildautojava

Step 4:Go to File>SetPaths>Add folderswith subfolders andselect firstly C\Octave\3.2.4_gcc4.4.0\share\octave\packages andthen C\Octave\3.2.4_gcc4.4.0\libexec\octave\packages

Step 5
Go to file>packages andwait until they appear

Installing GNUOctavefor Windows


Download from: http://octave.sourceforge.net/

Install the .exe file

Executing Octave

Not very friendly interface,but


Install aGraphic User Interface (ie.GUI)
There areseveral Myrecommendation is
http://guioctave.com/?page_id=2
Download and install Look here for some screenshots http://guioctave.com/?page_id=5

New interface

First code
%myfirst code for Octaveand Matlab.Type this%in the command window x =randn(100,1); plot(x)

HowcanIlearn
This is the handbook
http://www.gnu.org/software/octave/doc/interpret er/

But practice is the bestway


There arealot of packages They arecategorized bysubjects Howto knowthe packages you already have got
File>Packages
If you dont find them,then you should download them:

Download packages

What if Iwant to install others?


Go to
http://octave.sourceforge.net/packages.php Alsothereissubstantialdocumentationaboutthe package

Lookforyourneedpackage Seebeforedetailsastheremightbe dependencies Downloadthem(it),andthengobacktoGUI Octave Userefresh,andinstallthem

Plots
hist
help hist Code load forearm subplot(1,2,1) % The hist function optionally returns the % bin centers and frequencies. [n,x] = hist(forearm); % Plot and use the argument of width=1 % to produce bars that touch. bar(x,n,1); axis square title('Frequency Histogram') % Now create a relative frequency histogram. % Divide each box by the total number of points. subplot(1,2,2) bar(x,n/140,1) title('Relative Frequency Histogram') axis square

QQplots
Compare2distributions,samples,
With different scale With different number of observations

Each quantile is considered asapoint


If both setscomefrom the same distribution,then all points will beon the same line xuni=rand(100,1); qqplot (xuni, "uniform", 0, 1)

QQplots for 2samples


What if Iwant to compare2samples of size n and m?? See exampleQQplot

Bivariate NormalDistribution
% Create a bivariate standard normal. % First create a grid for the domain. [x,y] = meshgrid(-3:.1:3,-3:.1:3); % Evaluate using the bivariate standard normal. z = (1/(2*pi))*exp(-0.5*(x.^2+y.^2)); % Do the plot as a surface. surf(x,y,z)

S-ar putea să vă placă și