Differences between revisions 4 and 5
Revision 4 as of 2025-10-24 18:53:40
Size: 501
Comment: Rewrite
Revision 5 as of 2025-11-06 20:48:59
Size: 734
Comment: Notes
Deletions are marked like this. Additions are marked like this.
Line 3: Line 3:
'''`-testparm-`''' performs [[Statistics/WaldTest|Wald tests]]. '''`-testparm-`''' performs [[Statistics/WaldTest|Wald tests]] on regression coefficients.
Line 15: Line 15:
`-testparm-` is functionally identical to [[Stata/Test|-test-]], but it takes a variable list instead of expressions. By default it tests the joint hypothesis that each is 0. `-testparm-` is identical to [[Stata/Test|-test-]] except that it only tests for equivalence to 0. Because it does not allow for non-zero tests, all arguments passed to `-testparm-` are known to be coefficient names, so syntax is generally simpler.
Line 20: Line 20:
test (2.region = 0) (3.region = 0) (4.region = 0)
Line 21: Line 23:
}}}
Line 22: Line 25:
test (2.region=0) (3.region=0) (4.region=0) The following two are also equivalent:

{{{
test (_b[age] = 0) (_b[c.age#c.age] = 0)

testparm c.age c.age#c.age

Stata testparm

-testparm- performs Wald tests on regression coefficients.

See also -test-.


Usage

-testparm- is identical to -test- except that it only tests for equivalence to 0. Because it does not allow for non-zero tests, all arguments passed to -testparm- are known to be coefficient names, so syntax is generally simpler.

The following two are equivalent:

test (2.region = 0) (3.region = 0) (4.region = 0)

testparm i(2/4).region

The following two are also equivalent:

test (_b[age] = 0) (_b[c.age#c.age] = 0)

testparm c.age c.age#c.age


CategoryRicottone

Stata/TestParm (last edited 2025-11-06 20:48:59 by DominicRicottone)