˘ˇˆ˙˝˛˚˜ ˝˜˜! # $% &%’ # ( % % #% # %) ***+ + ,-% ˝˚!, …

1 ! " # $% & % ' # (% % #% # % ) **+ + ,-"% !, " # . ! + / 0 * + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + . + 1 2 # $ +++++++++++++++++++++++++++++++++++++++ +. %3++++++++++++++++++++++++++++++++++++++ ++++++ +4 " %# + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 5% % # + + + +++++++++++++++++++++++++++++++++++++++ ! + % "% ++++++++++++++++++++++++++++++++++++++ ! +. / $% ++++++++++++++++++++++++++++++++++++ 6 +4 / % $% + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 7 + % % +++++++++++++++++++++++++++++++++++++++ +! $% 3 % ++++++++++++++++++++++++++++++++++++++ +8 "% # % 9 9 % + + + + + + + + + + + + + + + + + + + + + + + + + +6 %# "% 3 % + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +.

2 + : % % ;% % * +++++++++++++++++++++++++++++ .+ $% 3 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + .+. 1 3 <# ' ( ++++++++++++++++++++++++++++++++++++++ .+4 % + + + + ++++++++++++++++++++++++++++++++++++ 8.+ "% ' <# ( + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 6.+! ;% % ' <# ( ; + + + + +++++++++++++++++++++++++++ 6 4+ 2 0 / 1 = /$ 1 0 : / ; : 1 + + + + + + + + + + + + + + + + + + 3%" # ++++++++++++++++++++++++++++++++++++++++ ++ 4 + 3%" # ++++++++++++++++++++++++++++++++++++++++ ++ 4 6 Flow of Conditional branching:IF.. Loop statements:DO WHILE/UNTILandFOR.)))

3 267 Suspending Temporary suspension using commands - PAUSE, WAIT .. Terminating a program using commands - END .. 298 Publication Quality Some Commands .. 309 GAUSS Global and Local variables .. Naming Conventions .. Writing Procedures .. Further Examples .. 3510 GAUSS Functions and keywords3711 Monte Carlo Simulations3812 References for this handout .. Useful GAUSS Resources: .. GAUSS Resources for Economists: .. 4013 Appendix: GAUSS Functions and Routines - Quick Linear Regression .. Descriptive Statistics .. Cumulative Distribution Functions .. Di erentiation and Integration Routines .. Root Finding, Polynomial Multiplication and Interpolation.

4 Random Number Generators and Seeds .. 4221 IntroductionGAUSS is a programming language designed to operate with and on matrices. If the core of yourtask is matrix manipulation in any way, then GAUSS is likely to be a better bet than a lower levelprogramming language. However, GAUSS is not appropriate for, say, writing a menu system; ageneral-purpose language is probably easier. Nor is GAUSS appropriate for standard applicationson standard datasets. There is little point in writing a probit estimation routine in GAUSS for asmall dataset. Firstly, there are already routines commercially available for non-linear estimationusing GAUSS. More importantly, TSP, LimDep, etc will already perform the estimation and thereis no necessity to learn anything at all about GAUSS to use these programs.

5 However, to get extraspeci cation tests, for example, a straightforward solution would be to code a routine and amendthe preexisting GAUSS probit program to call the new procedure at the appropriate point in Running GAUSS in Operating ModeIn the graduate computer lab, open GAUSS with Start - Econometrics Softwares - GAUSS -GAUSS instructions can be carried out in two :this is the dialog window you see in front of you when you start GAUSS. Inthis mode, commands typed into the GAUSS interface are executed immediately. This allowsfor an instant response to a command, but the commands cannot be stored. This is thereforenot suitable for writing large programs, or for commands which need to be run place for typing commands is marked by>>.

6 Or batch:In this mode, GAUSS commands are typed into a text le. This le isthen sent to be GAUSS to be run. This allows one to develop and store complex programs are in the directory ExampleLet s run an example In the main menu: File - Open - create new folder C:ndata3. In the main menu: File - Save - In the main menu: File - Change Working Directory - C:ndata35. Run active le6. look at results in the Output window7. note that output is also stored in le The Help MenuGAUSS has two electronic help systems, corresponding to the GAUSS pdf manuals (available ).1. The "Command Reference" is an easy way to pick up information on commands (as long asthey are not deemed "obsolete"), and is organised both alphbetically and by function, whichis useful.

7 It is very The "User Guide" is slightly more chatty, and has more Syntax GAUSS is not case-sensitive Commands are separated by a semi-colon Anything within the /*..*/ markers is ignored by the program - the markers are used forcomments. For example: /* this is a comment */. Note on Numerical PrecisionIn Gauss, eight bytes are used to store each element of a matrix. Hence, each cell in a matrix cancontain up to eight text characters, or numerical data with a range of about1:0E 35. If youenter text of more than eight characters into the cells in a matrix, the text will be data are stored in scienti c notation to around 12 places of Basics Matrix VariablesGAUSS variablesare of two contain numerical data or character data or pieces of text of unlimited length.

8 These are used to give information to theuser. If you try to assign a string value to an element of the matrix, all but the rst eightcharacters will be need to have names to reference them. Acceptable names for variables can containalphanumeric data and the underscore "_", and must not begin with a number . Reserved wordsmay not be used; standard procedure names may be reassigned, but this is not generally a goodidea. Variables names are not variable names:eric Eric eric1 eric_1 _eric1 variable names:1eric 100 if (reserved word) delif (GAUSS procedure -legal, but foolish) Creating brackets[ ]refer to dimensions of a matrix or the coordinates of a block, dependingon context.

9 The rst number refers to the row, the second the bracesfgare used within GAUSS to group variables matrices can be de ned at any point (except inside procedures). The easiest way is to assigna value to one. There are two ways to do this: (1) by assigning a constant value or (2) by assigningthe result of some Creating a matrix using constant assignment (LET)The keywordLETcreates matrices using constants. Two di erent forms of creating a matrix (orvector)xcan be utilized:Specifying the shape of the matrix x with the list of constants on the right-hand sideIf curly braces are not used, a list of constants separated by space will create acolumn commas has no e ect. Hence the following three operations are equivalent:CommandResulting shape of xLET x = 1 2 3 4 5 6;Column vector 6x1 LET x = 1,2,3, 4,5, 6;Column vector 6x1 LET x = 1 2, 3 4, 5 6;Column vector 6x1If the list of constants is enclosed in bracesfg, then arow vectorwill be produced.

10 Insertingcommas in the list of constants instructs GAUSS to form amatrix, breaking the rows at shape of xLET x = {1 2 3 4 5 6};Row vector 1x6 LET x = {1,2,3, 4,5, 6};Column vector 6x1 LET x = {1 2, 3 4, 5 6};Matrix 3x2 Specifying the shape of the matrix x using square brackets at x[ ]Anr cmatrix willbe created using the following constants on the right-hand side will be allocated to the matrix on a row-by-row commas has no e shape of xLET x[3,2] = 1 2 3 4 5 6;Matrix 3x2 LET x[3,2] = 1, 2, 3, 4, 5, 6;Matrix 3x2If only one constant is entered, then the whole matrix will be lled with that shape of xLET x[3,2] = 5;Matrix 3x2 Note:LET x = a*b;isillegalas "a*b" is a value and not considered a "constant".