significance levels

[Mosi Fagbemide]

1 more question please....

is it possible to change the significance levels in stata?

when I export my significance levels are 0.1%, 1% and 5%..... how do I change it to 1%, 5% and 10%

Thank you

[William Lisowski]

You would be more likely to get advice if you follow the recommendation of the Statalist FAQ linked to from the top of each forum page and show the commands you actually used. Without knowing that, the only possible answer is "Yes, you can change the significance level in many Stata commands. Try looking at the output of help for the particular Stata command you are using."

Assuming you are continuing to use the user-written esttab command as discussed in a previous topic you posted, the output of help esttab describes the star option:

[no]star[(symbol level [...])] causes stars denoting the significance of the coefficients to be printed next to the point estimates. This is the default. Type nostar to suppress the stars. The default symbols and thresholds are: * for p<.05, ** for p<.01, and *** for p<.001. Alternatively, for example, type star(+ 0.10 * 0.05) to set the following thresholds: + for p<.10 and * for p<.05. Note that the thresholds must lie in the (0,1] interval and must be specified in descending order.

This suggests adding the following option to your esttab command:

star(* .10 ** .05 *** .01)

[Mosi Fagbemide]

Hi William,

thank you very much.

I apologise if my posts are substandard, I do type/paste my commands most of the time. I do not know how to use the code and snapshot of results. I will get the hang of it (before my next post). once again thank you.

[Carlo Lazzaro]

Mosi:

I do not know how to use the code and snapshot of results

see FAQ #12.

[Mosi Fagbemide]

 eststo margin: margins, dydx(*) post

[Mosi Fagbemide]

got it.....

[Carlo Lazzaro]

Mosi.
not quite.

eststo margin: margins, dydx(*) post

As an aside, for testing purposes please post on http://www.statalist.org/forums/foru...m-help/sandbox. Thanks.