Stata 9 printed manual errata

The following commands are also of special interest after anova: commands description acprplot augmented component-plus-residual plot avplot added-variable plot avplots all added-variable plots in a single image cprplot component-plus-residual plot lvr2plot leverage-versus-squared-residual plot rvfplot residual-versus-fitted plot rvpplot residual-versus-predictor plot For information about these commands, see [R] regress postestimation.

For the uniform pseudorandom sequence, ... order O(N -1/2).

For the uniform pseudorandom sequence, ... order O{(log log N /N)1/2}.

istdize   ...   using(filename),

istdize   ...   using filename,

The standard population is specified in another Stata data file named in the using option.

The standard population is in another Stata data file specified by using filename, and it must contain popvar and stratavars.

Note that estat ic and lrtest may not be used after glogit and gprobit.

Note that estat ic and suest may not be used after heckman, twostep.

see [G] axis_selection_options. For an explanation ...

see [G] axis_choice_options. For an explanation ...

Wald test of exogeneity:   chi2(1) =     63.90 Prob > chi2 = 0.0000

Wald test of exogeneity:   chi2(1) =      6.50 Prob > chi2 = 0.0108

Note that estat ic and suest may not be used after ivprobit, twostep.

. ivtobit fem_wage fem_educ kids ...	. ivtobit fem_inc fem_educ kids ...
Wald test of exogeneity:   chi2(1) =     103.60 Prob > chi2 = 0.0000	Wald test of exogeneity:   chi2(1) =      4.64 Prob > chi2 = 0.0312

Note that estat ic and suest may not be used after ivtobit, twostep.

fweights and aweights are allowed; see [U] 11.1.6 weight.

fweights, aweights, and iweights are allowed; see [U] 11.1.6 weight.

... We use mfracpol to build a model

... We use mfp to build a model

matrix `negH' = (`d11',`d12' \ `d12',`d22')

matrix `negH' = (`d11',`d12' \ `d12'',`d22')

... The current value of the log likelihood is used to present a likelihood-ratio test unless robust, cluster(), pweights, or svy is specified because, in that case, a likelihood-ratio test would be inappropriate.

... The current value of the log likelihood is used to present a likelihood-ratio test unless robust, cluster(), pweight, svy, or constraints() is specified. A likelihood-ratio test is inappropriate when robust, cluster(), pweight, or svy is specified. We suggest using lrtest when constraints() is specified.

. sqreg y x1 x2, q(.25 .75) . test [q25]x1 = [q75]x2

. sqreg y x1 x2, q(.25 .75) . test [q25]x1 = [q75]x1

regress fits a model of depvar on varlist using linear regression.

regress fits a model of depvar on indepvars using linear regression.

The addplot(plot) option is not available with roccomp. You will receive an error message if you attempt to use this option with roccomp.

binar(#) ... binheight = binwidth × # × sqrt(3) The default is binar(r), where r results in the rendering of regular hexagons.

binar(#) ... binheight = binwidth × # × 2/sqrt(3) where binheight and binwidth are specified in the units of the y and x variables, respectively. The default is binar(r), where r results in the rendering of regular hexagons.

Description: returns subexpression n from a previous regexm() match, where 0 ≥ n < 10. ...

Description: returns subexpression n from a previous regexm() match, where 0 ≤ n < 10. ...

calineplot   correspondence analysis line plot

caprojection   correspondence analysis dimension projection plot

pci   pcline with immediate arguments

pci   pcspike with immediate arguments

options are as defined in [G] graph twoway pcspike

options are as defined in [G] graph twoway pcarrow

Twoway pcarrow with immediate arguments

Twoway paired-coordinate plot with immediate arguments

options are as defined in [G] graph twoway pcarrow

options are as defined in [G] graph twoway pcspike

The log likelihood, L, where , ...

The log likelihood, L, where , ...

!a, when a is a scalar, evaluates to 1 if a is not equal to zero and 1 otherwise.

!a, when a is a scalar, evaluates to 0 if a is not equal to zero and 1 otherwise.

The * comment indicator may not be used within Mata.

For risk differences, the x2 test of homogeneity is calculated as , where ...

For risk differences, the x2 test of homogeneity is calculated as , where ...

The 25th percentile, for instance, is obtained as the maximum value ...

The 25th percentile, for instance, is obtained as the minimum value ...

Schoenfeld residuals are calculated using the Breslow–Peto approach as Using the Efron approach, we have

Schoenfeld residuals are calculated using the Breslow–Peto approach as Using the Efron approach, we have

Max options maximize_options   control the maximization process; seldom used

Opt options optimize_options   control the optimization process; seldom used

Max options maximize_options: [no]log, tolerance(#); see [R] maximize. These options are seldom used.

Opt options optimize_options: itererate(#), [no]log, tolerance(#). iterate() specifies the maximum number of iterations. log/nolog specifies whether or not to show the iteration log. tolerance() specifies the tolerance for the coefficient vector; tolerance(1e-6) is the default. These options are seldom used.

. by person: replace avgbp = bp[_N]

. by person: replace avgbp = avgbp[_N]

[D] rolling

[TS] rolling

[D] dydx

[R] dydx

[R] obs

[D] obs

[R] statsby

[D] statsby

The following were omitted entries: Cronbach, L. J. (1916–2001)   [R] alpha Nelder, J. A. (1924– )   [R] glm