help for desrep                                                  John Hendrickx


desrep [using filename] [ , fw(#) ndec(#) sigcut(numlist) sigsym(list) sigsep(#) nrwd(#) modinfo sig se zval prob ci all notrunc exp outraw replace ]


desrep is a program for viewing the results of Stata estimation commands. It can be used after estimating any model but is particularly useful in conjunction with with desmat in command model. By default, desrep prints the coefficients, their standard errors, and symbols indicating the significance, of the last model estimated, together with longer descriptive labels. In conjunction with desmat, desrep will print labels on model terms and category values from the [varn] and [valn] characteristics desmat assigns to its dummy variables. If desmat was not used, variable labels are printed instead. Estimates are preceded by a summary of model information, based on results saved in e() by the command.

By default, desrep prints model information, coefficients, standard errors, and symbols indicating the significance. Additional statistics can be requested and printing of standard errors and signficance symbols can be suppressed. Defaults for some of these options can be modified using global macro variables (see below).

If using filename is specified then the results are written to a tab- delimited ascii file. The default extension for filename is .out (cf. outsheet). If filename already exists, desrep will attmept to find a valid filename by appending a number (see outshee2). The replace option can be used to overwrite an existing file.


fw(#) specifies Field Width, the number of columns used to display the estimates, standard errors, and other requested statisics. Default=10.

ndec(#) specifies the number of decimal places. Default=3.

sigcut(numlist) specifies levels of significance to be indicated in the output. desrep places a symbol next to coefficients to indicate whether these are significant at a certain level. The sigcut option is used to modify these levels of significance. The numlist should contain a list of values in descending order with the same number of elements as the string list in sigsym. For example, sigcut(.1 .05 .01 .001) together with sigsym(# * ** ***) will use the symbols # for p < .1, * for p < .05, ** for p < .01, and *** for p < .001. The default is (.05 .01).

sigsym(list) specifies set of symbols corresponding with the levels of significance given by sigcut. Default=(* **).

sigsep(#) spcifies the number of spaces between coefficients and symbols indicating significance. Default=0.

nrwd(#) specifies the number of columns reserved for numbering the effects. Specifying nrwd(0) can be used to suppress numbering. Default=3.

modinfo requests printing of summary information on the model. oUse nomodinfo to suppress this. Default=modinfo.

sig requests printing of symbols indicating levels of significance. Use nosig to suppress this. Default=sig.

se requests printing of standard errors Use nose to suppress this. Default=se.

zval requests printing of z-values for models with a chi2 statistic, t-values for models with an F statistic. Default =nozval.

prob requests printing of p-values. Default=noprob.

ci requests printing of confidence intervals. Default=noci.

all request printing of coefficients, standard errors, z or t-values, probabilities, and confidence intervals, as in the standard Stata output. Equivalent to zval prob ci.

trunc specifies that long labels are to be cut off and only the rightmost section displayed. Use notrunc to suppress this and print results on a separate line if necessary. Default=trunc.

exp requests that multiplicative parameters be reported, If exp is specified the desrep will report multiplicative e.g. incident rate ratios in poisson regression, oddsratios in logistic regression. The parameters are transformed into exp(b) and their standard errors into exp(b)*se, where b is the linear estimate and se its standard error. Note that if exp is not specified, desrep will produce the linear estimates even if the procedure produces multiplicative versions, since the procedure stores the linear estimates and covariance matrix in e(b) and e(V).

Earlier versions of desrep allowed exp to be specified as the only argument. This is still allowed if exp is indeed the only argument. If other options are specified, exp must be specified as an option.

The following two options apply only if using has been specified to write the data to a tab-delimited ascii file:

outraw requests that results be written using their default formats, e.g. %9.0g for floats. In addition, a tab will be inserted between coefficients and significance symbols. Otherwise, the variables are written with a fixed number of decimal places as specified by the ndec option (default 3) and significance symbols are appended to coefficients if sigsep=0. Default=nooutraw.

replace specifies that any existing output file should be replaced. If not specified, desrep appends a number to the filename if it already exists. If no valid name has been found after appending 1 to 20, the process stops and the output is not saved. Default=noreplace.

Note that these options can also be specified in the desrep option of the desmat command.

Macro variables to control layout

Macro variables can be use to alter the default for certain desrep options. The macro variables will still be overridden by options specified at the desrep command. The global variables can be specified once at the beginning of the Stata session or in the user's profile.do for all sessions. The following global variables may be defined:


For example, the following can be used to set the column width for estimates to 8, use 2 decimal places, and symbols and cutpoints for levels of significance:

global D_NDEC 2 global D_FW 8 global D_SIGCUT ".1 .05 .01 .001" global D_SIGSYM "# * ** ***"

Aso see

On-line: help for desmat, outsheet, outshee2 destest, showtrms, xi