The easiest fix for your problem is to use -float()- to ensure
the same precision on both sides of your -if- comparison, for example:
. replace interval = 3.674772 if float(se) == float(.5773503)
Tom
> -----Original Message-----
> From: [email protected] [mailto:[email protected]]
> Sent: Tuesday, July 23, 2002 3:30 PM
> To: [email protected]
> Subject: st: using replace command and retrieving conf. intervals
>
>
> while trying to figure out how the confidence interval at
> 95% level is linked
> to the standard error, I came up with following problem (as I
> tried to use the
> replace command) : the parts of the command that connect are
> just for standard
> errors 0, .25, .5 and .75 .Obviously the standard errors
> visible on the screen
> are not perfectly consistent with what is visible plus the
> hidden parts
> (lingering parts) .Can anyone help me with that.And while I
> am at it ,can
> anyone tell me how to retrieve the lower boundaries and the
> upper boundaries
> of confidence intervals ?
>
>
> . capture program drop lnsimvz1
>
> .
> . program define lnsimvz1
> 1. if "`1'"=="?" {
> 2. global S_1 " pu pl p se t mean"
> 3. exit
> 4. }
> 5. drop _all
> 6. use clt
> 7. sample 4
> 8. ttest a = 3
> 9. return list
> 10. post `1' r(p_u) r(p_l) r(p) r(se) r(t) r(mu_1)
> 11. end
>
> .
> .
> end of do-file
>
> . simul lnsimvz1 , reps(1000)
>
> . list in 1/5
>
> pu pl p se t mean
> 1. .681191 .318809 .6376181 .4787135 -.5222329
> 2.75
> 2. .7524873 .2475127 .4950253 .6454972 -.7745967
> 2.5
> 3. . . . 0 .
> 4
> 4. .7524873 .2475127 .4950253 .6454972 -.7745967
> 2.5
> 5. .5 .5 1 .7071068 0
> 3
>
> . tab se
>
> se | Freq. Percent Cum.
> ------------+-----------------------------------
> 0 | 34 3.40 3.40
> .25 | 134 13.40 16.80
> .2886751 | 108 10.80 27.60
> .4082483 | 117 11.70 39.30
> .4787135 | 232 23.20 62.50
> .5 | 67 6.70 69.20
> .5773503 | 52 5.20 74.40
> .6291529 | 62 6.20 80.60
> .6454972 | 49 4.90 85.50
> .7071068 | 57 5.70 91.20
> .75 | 80 8.00 99.20
> .8660254 | 8 0.80 100.00
> ------------+-----------------------------------
> Total | 1000 100.00
>
> . do "C:\WINDOWS\TEMP\STD010000.tmp"
>
> . gen interval = 1.837386
>
> . replace interval = 0 if se == 0
> (34 real changes made)
>
> . replace interval = 1.591224 if se == .25
> (134 real changes made)
>
> . replace interval = 1.591224 if se == .2886751
> (0 real changes made)
>
> . replace interval = 2.598456 if se == .4082483
> (0 real changes made)
>
> . replace interval = 3.04696 if se == .4787135
> (0 real changes made)
>
> . replace interval =3.182446 if se == .5
> (67 real changes made)
>
> . replace interval = 3.674772 if se == .5773503
> (0 real changes made)
>
> . replace interval = 4.0044902 if se == .6291529
> (0 real changes made)
>
> . replace interval = 4.1085203 if se == .6454972
> (0 real changes made)
>
> . replace interval =4.5006584 if se == .7071068
> (0 real changes made)
>
> . replace interval = 4.7736697 if se == .75
> (80 real changes made)
>
> . replace interval = 5.5121583 if se == .8660254
> (0 real changes made)
>
> .
> .
> end of do-file
>
> .
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
CONFIDENTIALITY NOTE: This e-mail message, including any attachment(s), contains information that may be confidential, protected by the attorney-client or other legal privileges, and/or proprietary non-public information. If you are not an intended recipient of this message or an authorized assistant to an intended recipient, please notify the sender by replying to this message and then delete it from your system. Use, dissemination, distribution, or reproduction of this message and/or any of its attachments (if any) by unintended recipients is not authorized and may be unlawful.
