Disclaimer:   I am providing these data and programs without warranty. That said, please contact me if you discover any errors in them so that I can post corrected versions on my web site.



Data:

GAORestate.xls MS-Excel spreadsheet listing accounting restatements collected by the General Accounting Office (GAO). The sheet lists the dates of the restatement announcements (NOT the periods restated), the prompter(s) of the restatements and the reason(s) for restatements as listed in the GAO reports. The sheet has a description tab with links to PDF files of the reports listed on the GAO web site.
 
 
 
 Programs:
 
The .ado files are STATA programs, the .m files are MATLAB programs and the .sas files are SAS programs. Some of the programs require that you have other programs installed. If you encounter an "unrecognized program: <program name>" error in STATA, you can type "findit <program name>" to try to find the missing program on line. This website uses https which, unfortunately, does not 'get along' well with Stata and prevents using the "net from" commands for direct install. You can install any of the following programs individualy by copying the relevant .ado and .hlp files to your ado directory. You can find the directory by typing "personal" into the Stata command line.

See the UCLA Academic Technology Services' excellent statistical computing website http://www.ats.ucla.edu/stat/overview.htm for a variety of examples and references. Also see the programs on the Michigan Accounting PhD web site.


Estimating equations:
bking2.ado Baxter-King (1995) bandpass filter for time series.
xtfmbJ.ado, xtfmbJ.hlp Fama-MacBeth (1973) regressions with options to weight by number of observations as proxy for precision of the years' estimates and an option to use a Newey-West correction for serial correlation in coefficient estimates.
cgmreg.ado,
cgmreg.hlp,
cgmregF.ado,
cgmregF.hlp,
cgmlogit.ado,
cgmlogit.hlp,
cgmflogit.ado,
cgmflogit.hlp,
cgmwildboot.ado,
cgmwildboot.hlp
Implementation of various estimation commands with multi-way clustered standard errors as in Cameron, Gelbach and Miller (2010 Journal of Business and Economic Statistics). Also see Petersen (2009 Review of Financial Studies). Commands include linear regression (cgmreg), linear regression with Fieller (1954) confidence intervals on coefficient ratios (cgmregF), logit (cgmlogit), fractional logit (cgmflogit) and regression with bootstrapped p-values (cgmwildboot - See Cameron, Gelbach and Miller, 2008 Review of Economics and Statistics).

- cgmwildboot updated 2013-09-06
- Updated 2014-02-19 to deal with dropped variables (e.g., fixed effects dropped due to collinearity)
- Updated cgmwildboot 2014-03-26 to fix error introduced by prior fix for dropped variables
- Updated cgmreg 2014-07-03 to disallow pweight
- Updated cgmwildboot 2015-03-10 to fix p-values (e.g., program looks at upper-tail for p-values of positive coefficients, and this was giving p-values greater than one when the coefficient was in the bottom half of the bootstrap distribution)

regFieller.ado, regFieller.hlp OLS regressions with confidence intervals for ratios of regression coefficients based on Fieller's theorem (more robust than delta method)
- Updated 2014-02-19 to deal with dropped variables (e.g., fixed effects dropped due to collinearity)
shumhaz.ado, shumhaz.hlp Shumway (2001) hazard model estimates, which uses a standard logit routine and corrects the chi-squared statistics for the average number of observations per cross-sectional unit.

- Updated 2014-02-10 to include option lroc to report area under ROC curve
mishkin.ado Implementation of Mishkin (1983) rational expectations tests. See comments in the ado file for syntax.
vuong.ado,
vuong.hlp
Computes Vuong (1989 Econometrica) test of two non-nested regressions as implemented and described in Dechow (1994 Journal of Accounting and Economics). Syntax is "vuong mod1 mod2" where mod1 and mod2 are stored regression results.

 

Descriptive statistics:
corrtbl.ado Creates correlation matrix for a list of variables with Pearson correlations below the diagonal and Spearman correlations above.
counttex.ado Generates LaTeX code for a frequency table.
summstattable.ado Generates LaTeX code for a table of summary statistics for a set of variables grouped by a binary indicator. Also reports t-tests for difference in means and chi-squared test for difference in medians.
ttesttable.ado Generates LaTeX code for a table that displays means and t-tests for a set of variables grouped by a binary indicator.
Utilities:
bpagan2.ado Breusch-Pagan test of heteroskedasticity.
collapseJ.ado Variant of STATA's collapse command that preserves variable labels.
ffind.ado, ffind.hlp
Creates Fama-French industry classifications based on SIC codes
prchgJ.ado Computes estimated change in probabilities for user-specified changes in variables following logit/probit estimation.
prvalueJ.ado Computes predicted probabilties and confidence intervals following logit/probit estimation.
truncateJ.ado Creates an indicator variable that identifies observations for which a set of variables are within specified cutoffs.
winsorizeJ.ado Winsorizes variables, allowing, for example, within year truncation points
xtileJ.ado Computes a variable that contains quantiles. The command is similar to STATA's xtile command except that xtileJ allows 'by' groups. This program runs much more quickly than the xtile2 command that allows 'by' groups.

 

judson.sty LaTeX style file with a bunch of functions in it for typesetting equations and so on.