H O M E / I N F O / P R O D U C T S / O R D E R / S U P P O R T

Benchmarks / Linear / Matrices / Miscellaneous / ML+QDV / Nonlinear / Panel Data /
Pindyck & Rubinfeld / Robust / Statistical tests / Time Series / Univariate / Advanced

TSP Examples by type

Benchmarks
AIDS.TSP	Almost Ideal Demand System, with elasticities, Deaton and Muellbauer model, based on SAS example. (LSQ,EQSUB,ANALYZ)
AR2MLP.TSP	Regression with AR(2) residual, exact ML estimation. Uses both ML and ML PROC, with the BJEST option that allows general ARMA residuals. Klein-I consumption function data.
CONDNUM.TSP	Condition number of X'X or any @VCOV matrix (version which is independent of the scale of X). Example using Klein-Goldberger consumption data. The condition number is a measure of multicollinearity.
DH.TSP	reproduces Durbin's h statistic
DIVZERO.TSP	Reproduces DIVIND calculation with zero quantities. Tests Paasche, Fisher, Laspeyres.
DW200.TSP	Verify DW 5% critical values for n=200, k'=2,3,4, using CDF(WTDCHI).
ILLUS41.TSP	Illustrative model from the TSP manual.
JB.TSP	Reproduces Jarque-Bera normality test, starting from small-sample versions of @SKEW and @KURT stored by MSD.
JOH1.TSP	Reproduces Johansen-Juselius cointegration results for Finnish data. More complete than COJOH, and uses VAR. Originally by David Cushman.
KLEINF.TSP	Reproduces pseudo-F test for zero slopes in 2SLS, example using Klein Model I.
KLEINLMC.TSP	Klein-I LIML benchmarks on consumption equation. Reproduces Greene's 3rd edition coefficients & standard errors. Explores alternative standard errors to those produced by the LIML command.
LONGLEY.TSP	Longley benchmark with double precision data; compares precision of default orthonormalized regression (11+ digits) with plain (X'X)"(X'Y) regression (7-9 digits)
LONGLEY2.TSP	Longley benchmark - test regression accuracy on a particular computer by entering the same variable twice in OLSQ and adjusting TOL to range over values that cause failure to detect singularity
NASTY2.TSP	Wilkinson's Statistics Quiz - high precision data
OVID.TSP	Overidentification tests in 2SLS - examples using Klein I
PANHAUS.TSP	Reproduces Hausman test of RE vs. FE in panel data
PPENDERS.TSP	ppzt test on data from 4 countries. Mostly reproduces table on p.263 of Enders, "Applied Economic Time Series", 1995
PRIN.TSP	reproduces results from PRIN (principal components), with MATRIX commands
SKEW.TSP	Reproduce Skewness and Kurtosis equations from MSD in manual, as a check.
SPATCAL.TSP	Example of running spatial.tsp on California plant species data. Reproduces results for Spatial AutoCorrelation and Spatial AutoRegression from Upton and Fingleton (1985).
STACKLP.TSP	Uses LAD and LP to estimate an LAD model on the stackloss dataset
WTDRSQ.TSP	Reproduces @RSQ from a weighted OLS regression, using OLSQ on manually weighted data and MSD.
Linear estimation
ANOVA.TSP	Proc which prints a (formatted) "ANOVA table" after OLS
KLEINLSQ.TSP	Test 3SLS on the Klein-I model (for FIML see Econometric Benchmarks). Shows how to reproduce the 3SLS @PHI criterion function using matrix commands.
LADCEN.TSP	LAD for censored and quantile regression
LPNR.TSP	Linear Programming tests from Numerical Recipes
RIDGE.TSP	Bayesian mixed estimator (combines prior with estimated coefficients and VCOV), works for non-OLS models.
TEST8.TSP	Original testrun from the 1975 TSP 2.7 manual; data originally from Johnston, Econometric Methods, p.127.
WEIGHT.TSP	OLSQ, MSD, and INST with weights; also shows formated read of input data
WHITESE.TSP	OLSQ with Eicker-White standard errors; shows how to compute by hand.
WHITFAST.TSP	OPTIONS FAST for faster regression computation; check with ROBUST
WHITINST.TSP	Tests of INST and LSQ with robust standard errors.
WHITNLSE.TSP	LSQ(ROBUST) on linear equations
WLS_TX04.TSP	Standard errors for predicted values from WLS
Matrix operations
AR1FML.TSP	AR(1) exact ML with the FIML and ML commands.
EIG.TSP	Tests of the eigenvector function in the MATRIX procedure.
MATEST.TSP	Test the new Matrix command introduced in V 4.2 for matrix algebra, including various matrix functions.
MFORM.TSP	MFORM for creating and rearranging matrices
SUBMAT.TSP	PROC to extract a submatrix, given starting/ending row/column
TAB2.TSP	Forms and print 2 x 2 contingency table (crosstab), with ChiSq(1) test for independence. Inputs are 2 dummy variables.
TAB2T.TSP	Examples of calling TAB2.
Miscellaneous and data transformation
ALL.TSP	Test of all TSP commands on dummy data, roughly in alphabetical order
CIRCLEPLOT.TSP	Plots with circles indicating "importance" or "size" of the observation.
CNVMAP.TSP	Tests of the CONVERT procedure for time series with the (MAP=) option
COMMENT.TSP	Testing of reading data (error messages) and ignoring trailing comments in the series.
DBCOPY.TSP	Testing various TSP databank commands including DBCOPY for moving databanks to a different computer
DBTEST.TSP	Simple test of making a databank using OUT.
DBTESTIN.TSP	Simple test of reading a databank using IN.
DBTESTRD.TSP	Tests of reading and writing databanks; deleting series from a databank.
DELOBS.TSP	Deletes some observations permanently from a dataset by placing them at the end of the sample and truncating.
DIVZ.TSP	Testing various DIVISIA options (zero, splice, etc) when data includes negatives, zeroes, or missing values.
DOC.TSP	Tests the DOC command, adding documentation to series.
DOT43.TSP	Test of nested DOT loops.
DOTFILE.TSP	Using DOT loops to construct filename(s). Quadruple DOTs to concatenate strings.
DYNG.TSP	Testing dynamic (recursive) and reverse dynamic GENR
EXCEL.TSP	Various tests of reading spreadsheets (wk3, wks, various Excel formats)
FFW.TSP	Test of free format WRITE with many significant digits.
FILES.TSP	Creating multiple files, automatic closing of files
FISHER.TSP	Paasche, Laspeyres and Fisher price/quantity indices directly. Compare with DIVIND command.
FREQ.TSP	Testing the options for setting the frequency of the data
GNUPLOT.TSP	gnuplot graphics - .GIF file output only, unix versions. (PLOT,GRAPH)
GNUPLOTI.TSP	gnuplot graphics - X window output, unix versions. (PLOT,GRAPH)
GSA.TSP	Tests various froms of the GENR command for variable transformation.
HELP.TSP	Example of using HELP in a batch program.
HIST.TSP	Testing HIST with integer data (DISCRETE option) and CDF, DENSITY, NORMAL, STANDARD options for Oxmetrics graphics
INTERP.TSP	Linear interpolation of missing values, for very simple case of single isolated missing values. Discusses why this may not be a good idea. See interp2 for general case.
INTERP2.TSP	Linear interpolation of missing values, general case.
LAG43.TSP	Testing subscripts for series and double subscripts for matrices
LAGTEST.TSP	New subscript features - integer and static date subscripts for series
LIST.TSP	Test various features of LISTs including implicit dashed lists, leading zeroes, suffixes, etc.
LISTSAVE.TSP	writes a LIST into an external file, formatted as a TSP command. Messy, but the only way to save a list in an external file at present. Could be useful if you are saving an @VCOV matrix in a databank, and you also want to save the @RNMS parameter names for later use by ANALYZ in a separate run.
LISTSORT.TSP	Creates a LIST (R8 R5 R6 ...) from a vector of integers (8 5 6 ...).
LISTSUB.TSP	Demonstrates the use of subscripted lists, useful in PROCs
LNGNAM.TSP	Test of long names ( > 8 characters)
LNGW1.TSP	Test of long names in writing spreadsheet
LNGW2.TSP	Test of long names in reading spreadsheet
MERGE.TSP	Proc which merges two samples by ID variables
MSD43.TSP	MSD with missing data, showing the pairwise option
PERCENT.TSP	Obtain arbitrary quantiles (such as 5%, 95%), using sort.
PI.TSP	Various infinite series for computing pi to arbitrary precision.
PLOTTEST.TSP	Tests of plots and graphs
PROC44.TSP	PROC argument changes in TSP 4.4 - lists, lags, etc
QUINTILE.TSP	Sample Quintiles (20%, 40%, ...) via SORT. Similar to percent example.
RELOP.TSP	Testing the results of relational operators at high precision (btwn 10-16 to 10-17)
SETEST.TSP	SET with all types of subscripts
SHOW.TSP	Illustrates the use of the SHOW command to list contents of TSP memory (series, equations, procs, etc)
SORT.TSP	Test various features of SORT command
SORTL.TSP	Sorts a list of variable names, by the variables' values in a given period. Coding similar to listsave.
STATA.TSP	READ Stata .DTA files versions 2 through 10.
SUBSETL.TSP	Create all subsets of a list; can be used to run subsets of RHS vars in many different commands
SUBSETS.TSP	OLS on all subsets of the RHS variables. Computes X'X once, and then uses submatrices to compute regression coefficients and SSR. Returns the set of coefficients which minimizes SBIC.
SUITS.TSP	Suits transformation of dummy variables (average effect for first dummy, difference from average for others). By Bronwyn Hall.
TERSE.TSP	Test TERSE and SILENT options in many commands
TEST8MV.TSP	TEST8 with missing value handling.
TVH.TSP	Read Excel files with multiple sheets and titles
YEARDUM.TSP	Estimating the average of a set of year dummies (compare the SUITS proc)
Maximum likelihood estimation and qualitative dependent variable models
BILINEAR.TSP	ML estimation of simple bilinear time series model. Uses recursive derivative code; could be made simpler with ML PROC. Granger and Andersen 1978
BIPROB.TSP	Bivariate probit, in ML using CNORM2(z1,z2,rho). Written as a Proc; should be easy to use on real data -- just supply the variable names. (ML)
BIQUAD.TSP	Bivariate normal cdf - how to evaluate probabilities in all 4 quadrants, by changing signs of the arguments to CNORM2(z1,z2,rho).
BIVORD.TSP	Bivariate Ordered Probit (without data). Could be improved in TSP 4.5 and higher by using CNORM(z1,z2,rho) function.
BOXCOX.TSP	Box-Cox with ML command (can also be done with FIML)
BOXCOXJ.TSP	Jacobian term for testing log vs. level and general Box-Cox model.
BOXTID0.TSP	Box-Tidwell regression when the RHS variables are sometimes zero.
CLOGIT.TSP	Example of conditional logit two ways, with data organized by case or choice
CLOGIT2.TSP	Example of conditional logit with data organized by choice, differing number of choices per case.
CLSF.TSP	Example of conditional logit two ways, with data organized by case or choice, demonstrating use of suffix list for choices and missing value behavior
CN4.TSP	4-dimensional cumulative normal integral, approximated with many random draws, CNORM(), CNORMI(), and Cholesky factorization.
COUNT.TSP	14 alternative Count (Poisson and Negative Binomial) models, including Hurdle and Zero-Inflated models. Automated via ML command. Written by Vincenzo Atella, with help from Clint Cummins. (ML)
DISEQ104.TSP	Disequilibrium model, with sample separation known. Section 10.4 of Maddala(1983), p.307-309. (LSQ)
DPDX.TSP	Standard errors for @DPDX from Logit. ANALYZ can also do this.
DPDX3.TSP	Mean and variance of dP/dX for Logit with 3 choices.
EBIPROB.TSP	Bivariate probit where Y2 is not observed unless Y1=1. (ML)
FIML11.TSP	11-equation FIML estimation, via the ML command. An extension of the old fiml4 example.
FIML4.TSP	4-equation FIML with ML command (HCOV=N, LDL' example). Example of how to parametrize the multivariate normal density, using LDL' factorization of Sigma-inverse.
FRONTE.TSP	Efficiency term for Frontier model from Battesse and Coelli (1988). Extends example in TSP User's Guide, section 9.7.3.
GAMMAR.TSP	gamma estimation of rainfall model. Uses ML PROC and CDF to evaluate igamma() function.
GAMMAS.TSP	gamma simulation of rainfall model, where trace values below 0.1 are truncated to zero.
GRID.TSP	checks a 3-parameter nonlinear model for multiple local optima. 2 different ways of choosing starting values: 1. full grid 2. random draw within bounds (like simulated anealling) reports back optimum found
HAMSIMP.TSP	Markov chain model - simple 2-regime from Hamilton's book, via EM. By David Bivin
HAZARD.TSP	log-linear hazard function with one time-varying covariate
HETPROB.TSP	LM test for heteroskedasticity in Probit. Follows Godfrey's book.
HURDLE2.TSP	Double Hurdle model. Tobit is single hurdle; this is like Tobit with an additional selection equation.
HURDLE2BC.TSP	Double hurdle model with Box-Cox transformation
INTRV.TSP	Test of Interval regression (includes equivalent Probit, Tobit, Ordered Probit)
LOGITBC.TSP	Logit with approximate finite sample bias correction.
LOGITCSU.TSP	Logit - conditional, with shares as dependent variable, unbalanced data. Data has been "balanced" by including all obs, with brand dummies=0 if choice not available. Includes code which takes limits of ratios, to avoid EXP(xb) overflow, when xb is larger than 88.
LOGITF.TSP	Forecasts from a multinomial logit model (picks most likely Y value for a set of X values). not tested.
LOGITFE3.TSP	Fixed effects logit for panel data with 3 time periods (choice taken 1 or 2 times). Follows Hsiao(1986), p.162. (ML)
LOGITMIX.TSP	Mixed logit via ML command
LOGITSH.TSP	Logit with shares as dependent variables.
LOGITSHP.TSP	Mixed Logit on (24) shares (fractional dependent variables aggregated over many choosers), panel data. Calculates predicted shares. Handles missing X values for zero shares.
MARKOVRT.TSP	Simple switching regression models - one with regime known, one with regime unknown. Not really Markov Chain models, because the switching does not involve the probability of the states in the previous period (for regime unknown). Data is generated from a Markov Chain, though.
ML2STAGE.TSP	Calculates corrected VCOV for second stage ML estimator (where estimation in the two stages involves different parameter sets). Automated differentiation. Useful in 2-stage estimation, where the second stage uses data computed from first stage ML parameter estimates. No example model or data.
MLOGIT.TSP	Standard multinomial logit, done by LOGIT and by maximum likelihood.
MLPM.TSP	Simplest ML Proc example - estimating the mean of normal data
MNESTLOG2.TSP	2-level nested multinomial logit.
MSPROBIT.TSP	Real Markov switching Probit model, by Masahito Kobayashi.
MXLOGIT.TSP	LOGIT - mixed - multinomal and conditional variables
NEGBIN.TSP	Simple Poisson and negative binomial examples using ML, with the procedures POISSON and NEGBIN for comparison.
NEST31.TSP	3 level nested logit that can be changed for different model, by Paul Ruud
NESTL.TSP	Nnested logit example from TSP User's Guide. Shows relation to mixed logit model.
NESTLOG2.TSP	2-level nested conditional logit.
NLOGIT.TSP	2-level nested logit (ML)
OLSME.TSP	OLS with measurement errors on the dependent variable, and known variances for these measurement errors (obtained from a first stage estimation). That is, the composite variance is made from these known variances that differ across observations, plus a residual variance that is equal across observations.
OP1R1.TSP	Ordered Probit (3 choices) and Regression / sample selection
OP3.TSP	Ordered Probit with forecasting - examines changes in Y for changes in a dummy variable. Example with 3 choices.
OPDYDX.TSP	dy/dx for Ordered Probit. Computes change in histogram of predicted dependent variable, for changes in a given X variable. More complex version of OP3, but without data.
OPFP.TSP	Ordered Probit forecasted probabilities. (ORDPROB)
OPHE.TSP	Ordered Probit Random Effects by Hermite Quadrature
P1OP1.TSP	2 eqns: Probit and Ordered Probit, correlated, by Bronwyn Hall
P1R2N.TSP	3 eqns: Probit and 2 Regression - non-selection, with simultaneity in Probit eqn
P1R2S.TSP	3 eqns: Probit and 2 Regression - selection model
PROBDER.TSP	Probability derivatives in Probit. Gives an alternative method of assessing changes in Y, for changes to a 0/1 RHS variable. (Derivatives are not appropriate for large changes in a discrete variable).
PROBIT.TSP	Test of Probit showing ML equivalent; also tests all options and prints maximum results
PROBTM.TSP	PROBIT, TOBIT, SAMPSEL with missing data (just a test)
RANCOEF.TSP	ML estimation of a regression with a single random coefficient. Outlines how to extend to multiple random coefficients.
REGIME.TSP	Real Markov switching regression model, by Masahito Kobayashi.
RPL.TSP	Random Parameters (coefficients) Logit. Example with a fixed intercept and one additional RHS variable with a normally distributed random coefficient.
SAMPSEL.TSP	Test of sample selection estimation on simple randomly generated data; compare to ML
SPATIAL.TSP	Proc which estimates Spatial Autocorrelation and Spatial Autoregressive models. User supplies W = spatial proximity weight matrix.
STACKLOS.TSP	LAD and Student's t residuals on classic Stack Loss dataset
STUDENT.TSP	Regression with Student t residuals; see also stacklos example.
SWITCH.TSP	Disequilibrium / switching regression model from 4.3 User's Guide, by Bronwyn Hall. Maddala;s text p.298
SWPROB.TSP	Switching Probits model, regime unknown. Estimated by ML with new CNORM2(z1,z2,rho) function. Follows Kimhi(1999). Like Maddala(1983), p.223, except the equations which switch are probits instead of regressions.
SWREG.TSP	Switching regression, regime unknown. Follows Maddala(1983), p.283. by BHH
SWREGUN.TSP	Switching with unknown regime and unknown sample separation, by Augustin de Coulon.
TESTNLOG.TSP	2 level (5 x 10) nested logit, with artificial test data, by Bronwyn Hall
TNP.TSP	Trinomial probit, in ML using the new CNORM2(z1,z1,rho) function in TSP 4.5. Uses one possible normalization for the residual correlation matrix, but it is not clear which normalization is best for an unrestricted model. See also the bunch example, which shows that the probability derivatives are invariant to different parameterizations the residual covariance matrix.
TOB2.TSP	2-equation (bivariate) simultaneous Tobit
TOB2SUR.TSP	2-equation Tobit, but with no RHS endogenous variables
TOBENDOG.TSP	ML estimation of a 2-equation model, where one equation is a tobit (truncated at zero), and the second equation has this variable on the RHS.
TOBIT.TSP	Test of TOBIT procedure including equivalent ML estimation
TOBITHET.TSP	Tobit and Probit, when heteroskedasticity is a function of variables.
TOBPDL.TSP	Test of TOBIT with PDL variable
TOBPRED.TSP	Predictions from Tobit model, conditional and unconditional.
TOBR2.TSP	R-squared for Tobit model, one possible formulation.
TOBRNCF.TSP	Tobit with random coefficients, Ionnatos, JBES July 1995
UNBALSUR.TSP	Does unbalanced SUR estimation (2 equations) in about 4 different ways. Fairly complicated. Users who don't want to compare minimum distance, pairwise deletion, etc. should just use unbalsu1.
WCLOGIT.TSP	Weighted conditional logit.
Nonlinear estimation and equation manipulation
ABDEF.TSP	Arellano-Bond estimation using GMM - simple example
ANALYZR.TSP	Example of using the restricted coefs stored by ANALYZ
ANASER.TSP	Testing ANALYZ for functions of series variables and bootstrap standard errors.
DIFFER.TSP	Test of DIFFER for all possible operations and functions, printing derivatives
DIFTEST2.TSP	Test of DIFFER by doing NLS using manual Gauss-Newton and derivatives from DIFFER
FORM40.TSP	Testing the equation forming procedure FORM.
FORMAR1.TSP	FRML with exact ML first observation for LSQ; includes Jacobian trick so that FIML is not needed.
GMM.TSP	Test GMM on single equation linear model
GMM2.TSP	Test GMM on 2 equations, compare to 3SLS.
GMM3.TSP	Test of GMM with OPTCOV option (to specify that COVOC supplied is the optimal one)
GMMERR.TSP	Test GMM syntax error handling
GMMPANEL.TSP	Documentation for the US---- panel examples.
KLEINMVR.TSP	Test LSQ, SUR on the Klein I model (for FIML see Econometric benchmarks)
MD.TSP	Minimum Distance estimation suing SUR on one observation with VCOV option.
PARAM.TSP	Tests of param and const with output pasted from LSQ for starting values
PEQTEST.TSP	Equation printing and analytic differentiation
SURAR1.TSP	Nonlinear SUR with AR(1) residuals, different RHO for each equation, plus conditional or exact ML
Panel (time series-cross section) data
AH.TSP	Anderson-Hsiao 2SLS for dynamic panel model (avoids finite sample bias in fixed effects estimator).
APD.TSP	Creates artificial panel data. Example of balanced, one-way random effects, 2 Xs correlated with random effects
AR1FMLP.TSP	AR(1) (exact ML) for panel data, using the FIML command. Reproduces AR1(TSCS) results.
AR1HET.TSP	AR(1) model with heteroskedasticity (rho(i), sigma2(i)). This follows Kmenta's "Elements of Econometrics" (1986) p.618-620. Includes a helpful degrees of freedom adjustment. This model has been criticized because rho(i) may proxy for individual effects alpha(i) that are not included.
AR1HETUB.TSP	A version of AR1HET for unbalanced data (Kmenta's GLS model using transformed data)
ARELBON2.TSP	Arellano-Bond example of setting up mask matrix and equations for GMM estimation on a linear model with 3 RHS variables.
ARELBOND.TSP	Simple Arellano-Bond example, 1-step and 2-step estimators (balanced panel data). Reproduces Table 5 of A-B. HAC standard errors hand-computed.
ARTSCS.TSP	Examples of working with a small panel dataset: AR(1) estimation, dealing with gaps, obtaining within firm sums, etc.
BAL2WFE.TSP	Balanced 2-way fixed effects in panel data
BALU.TSP	Panel - example of how to "balance" unbalanced data by adding artificial observations with zeros for all variables.
COV1STEP.TSP	Arellano-Bond 1-step COVOC matrix - GMM/panel
COV2STEP.TSP	Arellano-Bond 2-step COVOC matrix - GMM/panel
COXPANEL.TSP	ML estimation of Cox proportional hazards model, balanced data example with 3 time periods. Uses lagged EQSUB feature.
DATA2WAY.TSP	generates artificial data for 2-way model (RANDOM)
EC2SLS.TSP	2SLS with 2-way error components, balanced panel. Uses transformed data with 2SLS commands. See Hsiao's panel data book.
EC3SLS.TSP	3SLS with 2-way error components, balanced panel. Uses transformed data with 3SLS commands. See Hsiao's panel data book.
FEI.TSP	Test of FEI (group fixed effect) option in several commands (OLS, 2SLS, 3SLS, FIML)
FEIHAT.TSP	Compute hat matrix (leverage) for fixed effects model.
FIRSTDIF.TSP	Automates creation of first-differenced variables for GMM panel models, where the variables are named by time period, like y1 y2 y3, etc.
FRONTP1.TSP	Frontier production function, unbalanced panel, error components, v_it - u_i. Follows Battese and Coelli, 1992. See frontp2 for a simpler version.
FRONTP2.TSP	Frontier production function, unbalanced panel or cross section, v_it - u_it. Truncation point depends on z*d function. Follows Battese and Coelli, 1995. Simpler than frontp1.
GAPUBAL.TSP	Setting up a gapped SMPL for unbalanced stacked panel data, so that GMM(NMA=k) can be used.
GARCIA.TSP	Growth model, stochastic differential equations, unbalanced panel. Uses recursive EQSUB. This nonlinear panel growth model is used on tree heights.
GCOEFI.TSP	Panel OLS model where some coefficients vary by individual, and others do not. Includes a PROC to automate this.
GRUNFELD.TSP	Test random and fixed effect OLS and AR1 models on Grunfeld data (AR1, PANEL)
GSPD5.TSP	Create duplicate state variables for each industry.
H3B.TSP	Hsiao(1986)'s Appendix 3B - verifies 2-way EC Omega inverse (MATRIX)
HHGFISH.TSP	Models for panel count data (Hausman Hall & Griliches 1984)
HHGNB.TSP	Negative binomial models for panel count data from HHG (84)
HHSIM.TSP	Minimum distance estimation of Hall-Hayashi dynamic factor model. Uses simulated data. by Bronwyn Hall
INFOT.TSP	Information Matrix Test - example with Probit. Shows how to use DIFFER for first and second derivatives of an equation.
LM2TEST.TSP	Arellano-Bond m2 statistic, tests AR(1) and AR(2), by Bronwyn Hall.
LM2TEST2.TSP	Alternative version of lm2test, using explicit lags. Unfortunately, it seems to be about 20% slower than lm2test.
MASK2.TSP	2 different ways to set up a large sparse MASK matrix for use in GMM (different instruments in different equations).
N71A.TSP	PANEL(REI) - 2 local optima automatically detected
P3S.TSP	Three stage least squares with two-way error components (data files are not included).
PANBYT.TSP	PANEL with OPTIONS BYTE for economical storage of variables.
PANCHOW.TSP	Chow test for panel data, within model, where both the coefficients and fixed effects vary across 2 periods.
PANEL.TSP	Basic tests of the linear panel data estimator
PANMEANS.TSP	Removing individual or time means.
PANR.TSP	PANEL estimation with robust s.e.s
PANR2.TSP	Panel estimation in LSQ (IV) with robust s.e.s; uses panel freq to tell it how to group HCOMEGA
PANRW.TSP	Simulates Panel random walk with drift.
PANSD.TSP	Computes standard deviation of a panel series within each individual, and stores result as a series
PANSMPL.TSP	For Panel data with FREQ Q or M. Proc FIRMDATE creates @FIRM (1,2,...,N) and @DATE (197801,197802,...,199712) variables. These can be used to SELECT particular firms and ranges of dates for regressions. For balanced data which does not already have ID and Date variables.
PANUNIT.TSP	Panel unit root test of Im, Pesaran, and Shin. This version has the URL for downloading the paper, and describes how to look up the critical values in IPS Tables 2-4.
PANW.TSP	Weighted fixed effects estimation.
PHE.TSP	Bivariate Probit with Hermite quadrature. Compared with random effects Probit model, and regular CNORM2() version.
PREMASKC.TSP	Two examples of calling premaskg to create a GMM mask.
PREMASKG.TSP	Creates mask for GMM with panel data
PROBFE.TSP	Probit with fixed effects, showing some pathologies with only two groups
PROBITAC.TSP	Probit with SEs robust to autocorrelation.
PROBITRE.TSP	Probit with Random Effects - the Borjas-Sueyoshi 2-stage model. Monte Carlo analysis. Comments on the Pooled vs. Random Effects estimators. Related to PROBIT(REI) in TSP 5.0.
PROBRE.TSP	Tests Probit with random effects (using ML).
PSTR.TSP	Panel Smooth Transition Regression. 2 regimes. grid search and ML PROC estimation, originally written for TSP 5.0, updated to run in TSP 4.5 also
RDUSBAL.TSP	read USBAL dataset for the panel data examples USBALxxxx
TIMEDIFF.TSP	Time dummies in first differenced equations (when differencing to remove individual effects) - interpretation.
UB2WFERE.TSP	Unbalanced 2-way fixed and random effects follows Wansbeek and Kapteyn (J of E, 7/1989). Not tested against any real-world benchmark results. GLS estimation, which depends on the method chosen to estimate the variance components. Compare with PANEL(REIT) in TSP 5.0 which uses ML estimation.
UNBALSU1.TSP	Unbalanced SUR -- 2 equations; some observations missing for the second equation. ML version only (easiest way to get estimates and proper standard errors).
UNBALSU4.TSP	(ML) SUR with 4 equations, in a nested pattern of missing data. In this example, there are 4 drugs that were invented at different times, and then observed up to the present (artificial data are used). The code can be used for 1-4 equations in this type of pattern.
USBALFE.TSP	Fixed Effects and other estimators via PANEL command
USBALGM4.TSP	Strong and weak exogeneity tests GMM (MASK=…)
USBALGMM.TSP	same as USBALPI but with GMM and first differencing
USBALME.TSP	Panel GMM with measurement errors
USBALPI.TSP	Basic Pi matrix with fixed effects and time-varying coef (Chamberlain, Handbook of Econometrics).
USBALPIM.TSP	Pi matrix with measurement errors
Robust methods
CHANGEPT.TSP	Andrews (1993) test for structural change with unknown change point (Maximum Wald test). Includes a Monte Carlo loop to verify that distribution of the test matches his results.
GLEJSER.TSP	Glejser and MSS tests for heteroskedasticity in quantile regression. by Bronwyn Hall
HCTYPE.TSP	OLSQ(HCTYPE=) Heteroscedastic-Consistent SEs
KERLIN.TSP	Computing Partial Linear Regression according to Robinson (1988).
KTAU.TSP	Computes Kendall's tau-b (nonparametric correlation), and its standard error. Compares with Spearman rank correlation, and regular Pearson correlation. Includes Proc to compute number of ties, and an improved Rank Proc which accounts for ties.
LAD2SK.TSP	2-stage LAD estimation of Klein-I consumption equation
LIST7CH3.TSP	Programming with subscripted lists, to choose up to 3 variables to add to a regression. To reproduce Levine-Renelt 1992 EBA results. (LIST)
MBBJEX3.TSP	moving blocks bootstrap (examples with OLS and LAD). Similar to plain bootstrap, but handles autocorrelation as well as heteroskedasticity. by Bernd Fitzenberger
NEURAL.TSP	Neural network regression on Stackloss dataset. Logistic function of RHS variables with 2 nodes.
ODR.TSP	Orthogonal Distance Regression (errors in variables, when ratio of error variances in Ys and Xs is known).
OPAC.TSP	Ordered Probit with AutoCorrelation-robust SEs. Also shows how to do ML via GMM on first order conditions.
PANBOOT.TSP	Panel bootstrapping. Draws residuals within an individual.
PROBKS.TSP	Semiparametric Probit (Klein and Spady) on small dataset (32 obs.). Uses KERNEL estimation.
SCLS.TSP	Symmetrically Censored Least Squares - proposed by Powell (1986) for Tobit model estimator robust to non-normality. The Newton algorithm here improves its iteration performance greatly. Includes test dataset. by Joao Santos Silva.
SIGNTEST.TSP	Sign test for median of zero, with exact binomial p-value
SPLINE3.TSP	Cubic spline with 3 segments. Examples of fitting sin(6x) and log(.1+x).
SPLSBIC.TSP	Cubic spline which chooses the number of segments by minimizing SBIC. Examples of fitting sin(6x) and log(.1+x).
VUONG.TSP	Vuong test of non-nested models. Computed from difference in LogL for each observations. Example with OLS.
VUONGF.TSP	Vuong test, example with FIML.
WILCOXON.TSP	Wilcoxon signed rank test, with p-value. Nonparametric test for symmetry of a series around a given value.
WILD.TSP	Wild bootstrap, used to approximate the distribution of a test statistic. (Davidson and Flachaire)
WINSOR.TSP	Winsorized residuals, and iterative M-estimation. A simple iterative version.
WTDSAMPL.TSP	Randomly sample from a vector with non-uniform weights. Similiar to random(draw=). Proc WSM, with example of using it.
Hypothesis testing
BDE.TSP	Brown-Durbin-Evans CUSUM and CUSUMSQ tests, both automated and manual.
CAPTEST.TSP	Test of the CAPITL procedure
CDF.TSP	Test of CDF proc for normal, t-dist, F-dist, chi-squared, bivariate normal, and Dickey-Fuller
CNORM.TSP	Tests of CNORM(), CNORMI(), LCNORM(), DLCNORM() functions
COEFTAB.TSP	How to print a small table of selected coefs and SEs from a large estimation, by using ANALYZ
EXOG.TSP	Exogeneity test (Hausman-Wu), Sargan test for identification, and also Breusch-Godfrey LM test for autocorrelation in 2SLS.
FITEST.TSP	Goodness of fit statistics after Pi matrix model, used by US panel examples
GMMCHISQ.TSP	chi-squared test of over-id restrictions (@GMMOVID in 4.3)
HAUSTEST.TSP	Example of Hausman specification test for Poisson vs Negative Binomial model on patent data
HYPTEST2.TSP	Hypothesis testing in linear models (OLS,SUR,2SLS,3SLS) - t-tests, F-tests, likelihood ratio and quasi-likelihood ratio tests.
KLEINCHOW.TSP	Multiequation Chow tests on Klein-I model - parameter stability in SUR and 3SLS using LR and QLR tests.
OMNORM.TSP	Omnibus test for multivariate normality. Reproduces results from Doornik and Hansen (1994) for Fisher Iris data.
PHICHOW.TSP	Chow test for 2SLS (pseudo-F test for parameter stability, split sample)
PROBDIST.TSP	Compute various probability distributions and plot them. by Bronwyn Hall
Time series analysis, GARCH, VAR, Kalman filters, etc.
ADDFACTOR.TSP	Two versions of estimation and forecasting with an add factor, on the same equation. First uses OLSQ and the second uses LSQ and SIML (potentially nonlinear).
ADFBRK.TSP	Various ADF (Augmented Dickey-Fuller) tests with trend breakpoints due to Perron; Harvey et al, etc. A PROC for performing the tests is included.
ADFGLS.TSP	GLS version of ADF (Augmented Dickey-Fuller) unit root test with p-value (Elliott, Rothenberg, Stock (1992,1996)), by Yin-Wong Cheung.
AGARCH.TSP	Asymmetric GARCH as in Ding, Granger, and Engle, Journal of Empirical Finance 1993
ALMONK.TSP	Example of PDL and Kernel estimation using original Almon data
ALMONS.TSP	Tests PDL and Shiller lag options using original Almon data
APARCH.TSP	Asymmetric Power GARCH as in Ding, Granger, and Engle, Journal of Empirical Finance 1993
AR1FSE.TSP	AR1 forecast standard errors, via ANALYZ.
AR1MLP.TSP	Regression with AR(1) residual. Reproduces AR1 command with ML PROC and BJEST option.
AR1W.TSP	Weighted AR1 estimation via ML
AR4NL.TSP	AR(4) on single nonlinear equation (conditional ML)
AR9MA5.TSP	Basic example of Box-Jenkins identification and estimation for an ARMA (1,1) model
ARCH2.TSP	Example of ARCH model with two lags, on GNP and Consumption data
ARCHAR1.TSP	ARCH(1) with AR(1)
ARCHDIAG.TSP	Diagnostic tests for asymmetry of ARCH residuals.
ARCHF.TSP	ARCH forecasting for H(t).
ARCHML.TSP	Compare ARCH proc to ARCH via ML.
ARFX.TSP	AR1 forecasting, in and out of sample
ARMA41ML.TSP	regression with ARMA(4,1) residual. exact ML. Sunspot data.
ARMAX.TSP	regression with ARMA(1,1) error term from Harvey EATS book using Gauss-Newton iteration
ARMAX7.TSP	ARMAX(12,2) estimation with 7 rhs variables (P&R example) using Gauss-Newton iteration
ARMAXC.TSP	ARMA(12,2) estimation using Gauss-Newton iteration (Harvey data)
AUTOEXP.TSP	Example of Box-Jenkins estimation and forecasting using data on auto sales, where the forecast is in terms of the original data (rather than its logarithm).
AUTOSALE.TSP	Example of Box-Jenkins estimation and forecasting using data on auto sales
BERNANKE.TSP	VAR: Bernanke-Sims decomposition. This is a way of factoring Sigma, where the user specifies zero restrictions on particular elements of the factorization. Based on RATS code, and includes test examples.
BILIN2.TSP	Second order bilinear model, by Wiedyo Pura Buana
BJEC.TSP	Example of BJIDENT with ESACF on Box and Jenkins chem series
BKF.TSP	Baxter-King filter (an alternative to Hodrick-Prescott).
BOXCOXAR.TSP	Box-Cox with AR(1) residual. Should be revised to use NODROPMISS option. (FIML)
CALENDAR.TSP	PROCs for various calendar date conversions. Use to convert packed dates like 981231 to year,month,day variables; find which weekday, week, and month a particular day of the year is, etc.
COINT.TSP	Comprehensive test run for Unit root/cointegration testing, data from Nelson and Plosser 1982
COINTARP.TSP	Cointegration test with AR(p) residuals - Stock-Watson(1993) and Phillips-Loretan(1991, p.424).
COJOH.TSP	COINT test on Johansen-Juselius data
CUBIC.TSP	Equations for real roots of cubic equation. Also demonstrates imposing various constraints. (EQSUB,LSQ)
DATELOOP.TSP	Looping over a dated sample - simpler than doquart example, and explains 2 different methods for doing this.
DL.TSP	Approximation to dL (lower critical value for Durbin-Waston statistic), using NOB and K1 (# of RHS variables).
DOQUART.TSP	DO loop over time periods with quarterly data. Example with rolling regression and one-period-ahead forecasts. See the DATELOOP example for a simpler loop.
DWNL.TSP	Approximate P-value for Durbin-Watson in nonlinear model, using regression on first derivatives.
DWTEST.TSP	Durbin-Watson test with exact p-values; switch to Imhoff approx. at N=90
DYNAMSOL.TSP	SOLVE, SIML (dynamic simulation)
EGARCH11.TSP	EGARCH(1,1) estimation. Exponential GARCH, where log(h(t)) = alpha0 + alpha1*abs(e(t-1)) + beta1*log(h(t-1)).
EXPSM2.TSP	Double exponential smoothing with arbitrary smoothing parameter. Compared to ARIMA(0,2,2) model using BJEST.
FINANCE.TSP	Financial applications: 1. saving and sorting 60 betas 2. estimates of variance in rolling sample 3. standard deviation of sequential portfolios 4. t-stat for correlation coefficient, by Sotiris Staikouras
FORCST40.TSP	Single equation forecasting
GAMMADL.TSP	Distributed lag with shape from gamma density.
GARCHM.TSP	GARCH-M - testing via ML
GARCHMA.TSP	GARCH (1,1) with MA(1) residual - testing via ML
GARCHML.TSP	GARCH via ML Proc
GIR.TSP	Generalized Impulse Response - invariant to equation order. Reproduces results in Pesaran and Shin (1998) with KPSW data.
GIR2.TSP	Generalized Impulse Response, via LSQ and SOLVE. (extendable to structural VAR)
GMMNS.TSP	GMM on non-stationary data. Follows Hamilton(1994), p.424 / Ogaki(1993). Estimates model as a function of detrended variables.
HPTREND.TSP	Hodrick-Prescott trend decomposition, data example from Kydland-Prescott
HPTREND4.TSP	Faster version of HPtrend (Hodrick-Prescott trend decomposition). Includes modular versions of the PROC for fast use with multiple series.
IGARCH.TSP	Integrated GARCH(1,1), with constraint that alpha1+beta1=1.
ILLUSFOR.TSP	Test dynamic forecasting using illustrative model, also shows use of common factor test for AR1 models
ILLUSOLV.TSP	Test static similation done using three different methods on the illustrative model
KALD.TSP	Kalman filter with dummy variables that are singular in the initial observations (used to test new recursive residuals that no longer assume initial observations are nonsingular).
KALMAN.TSP	Various tests of the basic Kalman Filter procedure, compared to OLS
KALMANHP.TSP	Kalman filter HyperParameter estimation, using ML PROC. Estimates two variance parameters in the transition equation.
KALVT.TSP	Bootstraps the VT (transition variance) matrix for Kalman Filter by estimating without it, forming an estimate, and then estimating with a transition variance.
KFARMA11.TSP	Evaluation of conditional likelihood function for ARMA(1,1) via the KALMAN command.
KFCOMF.TSP	Kalman Filter with Common Factor (stochastic trend)
KFLLT.TSP	Kalman Filter on Local Linear Trend - Harvey(1989), p.170
KFLOOP.TSP	Kalman filter in a DO loop, to compute SEs for state vector at each period. One parameter in state vector, with user-supplied prior.
KFLOOP2.TSP	Kalman filter in a DO loop, to compute SEs for state vector at each period. Two parameters in state vector, with prior computed from initial observations.
KFMA1.TSP	Ditto, but for MA(1) model. Harvey, TSM, 1981, p.103
KFML.TSP	Estimates Kalman Filter transition matrix via grid search (2 parameters). Compare with KALMANHP.
KLEINSOL.TSP	Tests of model simulation (SIML, SOLVE) on Klein-I
KOYCK2.TSP	KOYCKP example applied to a different dataset.
KOYCKP.TSP	Koyck (geometric) distributed lag, with truncation terms for finite sample panel or time series. Example on Almon data.
KWUNIT.TSP	KPSS unit root test, where stationarity is the null. Handles data of any frequency - uses current SMPL to determine range of data and contains test data from Perron. Sample use illustrated for several frequencies.
KWUNIT2.TSP	Procs for KPSS unit root test. Revised version of KWUNIT Proc by Phil Meguire. Handles any frequency, adds argument to control taking log of input series, and includes critical values from the paper. Compare with Clint's revised version (KWUNIT).
LAGDEP.TSP	FORCST, AR1 with lagged dependent variable
LMAR.TSP	LM test of AR(p) residuals due to Breusch & Godfrey; computed directly using regression
LNORMDL.TSP	Distributed lag with shape from lognormal density.
MA.TSP	Simple Proc to calculate moving average of length n
MARCH2.TSP	Multivariate ARCH with 2 equations (not GARCH)
MARCH3.TSP	Multivariate ARCH with 3 equations (not GARCH)
MARCH4.TSP	Multivariate ARCH with 4 equations (not GARCH)
NONSTAT.TSP	BJEST, BJFRCST on nonstationary data
PDLAR.TSP	Proc to estimate with single PDL variable and AR(p) residuals using nonlinear least squares.
PDLAR2.TSP	Example of calling PROC pdlar
PDLCORC4.TSP	Test AR1 (Cochrane-Orcutt method) with PDL variable and forecast.
PDLFARSU.TSP	PDL with FAR restriction and coefficients summing to one.
PDLFORC.TSP	Forecasting with a PDL variable estimation
PDLFS143.TSP	PDL with FAR restriction and coefficients summing to one; different lags & degree
PDLPANEL.TSP	PDL done via the PANEL command.
PDLQTR.TSP	Basic tests of OLSQ with PDL, quarterly data; also tests frequency conversion
PDLSQ.TSP	PDL done with LSQ - example for nonlinear or multi-equation estimation
PDLSQAR2.TSP	PDL and AR(2) errors using LSQ
PDLSQBOTH.TSP	PDL in LSQ, with both NEAR and FAR restrictions
PDLSQFAR.TSP	PDL with FAR restriction only
PEARML.TSP	AR1 on pear data - Hildreth-Lu example, showing exact ML
PLOTAC.TSP	Proc which can be called after BJIDENT to print the autocorrelation function (and its 95% bounds) with color graphics.
PPMEX.TSP	Phillips-Perron "z hat sub t" unit root test on Mexican data.
PPZT.TSP	Phillips-Perron "z hat sub t" version of the Dickey-Fuller unit root test. Differs from "z hat sub alpha" test in the COINT(PP) command.
PREDERR.TSP	Prediction error variance for OLS model using a proc
QTOMW.TSP	Quarterly to Monthly conversion, using ratio to average, and weights (sum and average versions).
QTOMW2.TSP	Examples of calling QTOMW, converting forecasts from quarterly model into monthly forecasts.
REGARMA.TSP	Regression with ARMA(8,2) errors (uses ML PROC). Conditional ML. Easier to modify than previous codes like armax7. See regarma2 for exact ML, which is easier to use.
REGARMA2.TSP	Regression with ARMA(8,2) errors, exact ML. See also regarma for conditional ML (but more complicated).
REGMA1.TSP	Regression with MA(1) residuals.
REGOP2.TSP	Testting various regression output options, especially the Durbin-Watson bounds.
SAMAV40.TSP	Seasonal adjustment on a quarterly GDP series
SFT.TSP	Tests shinfull on artificial data. Test P-values against published table of critical values.
SHINFULL.TSP	Shin-Fuller ARMA(p+1,q) unit root test from Journal of Time Series Analysis 1998. Uses exact ML ARMA estimation with multiplicative seasonal. Computes P-value of test statistic by interpolating critical value table from the paper.
SOLSIM.TSP	Trying MODEL and SOLVE when SIML is needed to check error messages.
STAR.TSP	Smooth Transition AutoRegressive models.
THEILU.TSP	Computing various Theil statistics, comparing to ACTFIT
TRADESOL.TSP	33 equation trade model - shows solution by 3 different methods using SIML and SOLVE.
VAR.TSP	VAR estimation and impulse response computation, also with OLS, SUR, and SIML for forecasting
VARBQ.TSP	VAR Blanchard-Quah decomposition (AER 1989). This is an alternative way of factoring Sigma (vs. the arbitrary Cholesky shocks) for impulse responses. The user orders the equations so that the first variable can have a long-run effect on all variables, and the last variable can have a long-run effect only on itself. Includes an example with 2 variables and 4 lags.
VARDIF.TSP	VAR on differenced series, but compute impulse response for original series
VARF.TSP	VAR forecasts
VARIRA.TSP	Impulse Response standard errors via ANALYZ. Hardcoded example for 3 equations, 4 lags, 6 periods.
VARJB.TSP	VAR example from Judge, et al 1988 (p.759) with bootstrap IR bounds
VARMC.TSP	VAR with Monte Carlo. Runs VAR in a loop with bootstrapped residuals to compute empirical distributions of any item in VAR's output. This example computes standard errors for variance decompositions.
VARSBICI.TSP	Chooses optimal lag orders for VAR by minimizing @SBIC. Allows for different lags on different variables. Example with just 2 variables.
VARSIML.TSP	Use SIML to create impulse responses, after a VAR command.
VARST21.TSP	Same as varst32, but 2 variables with 1 lag (much easier to read and understand)
VARST32.TSP	Uses BJEST to check polynomial roots for stationarity of a VAR (3 variables, 2 lags). See varst21 for simpler version.
VRATIO.TSP	Variance ratio test for unit root. See Campbell, Lo, and McKinley text.
Univariate procedures and distribution functions
CLT.TSP	Central Limit Theorem example - convergence of the mean of uniform random variables to normality.
FUNC.TSP	Testing various functions in GENR (normal, integer, etc.)
GINI.TSP	Compute a Gini index (income distribution measure).
INT.TSP	Integration using trapezoidal rule approximation in a DO loop.
MULTINOM.TSP	Draws multinomial r.v.s for user specified probabilities. Compare to new RANDOM(Multinomial) option, which generates random variables according to a multinomial distribution. by Bronwyn Hall
MW.TSP	Weighted median
RANDOM.TSP	Examples of the use of random number generator, including bootstrapping.
RANTRUNC.TSP	Truncated normal random variables via inverse CDF.
RN.TSP	RANDOM (MEAN=,STDDEV=,VAR=) for series mean, Poisson, Negative binomial, Laplace
TRIGTEST.TSP	Test trig function, normal density, and their derivatives

If you have any questions or comments about TSP please send an email to info@tspintl.com.

Comments or questions about this website should be sent to news@tspintl.com.