|
Size: 2219
Comment: Initial commit
|
← Revision 6 as of 2025-04-04 01:03:58 ⇥
Size: 2163
Comment: Cleanup
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 1: | Line 1: |
| = Stata Test = | = Stata test = |
| Line 3: | Line 3: |
| The '''`test`''' command performs [[Econometrics/WaldTest|Wald tests]]. | The '''`test`''' command performs [[Statistics/WaldTest|Wald tests]]. |
| Line 13: | Line 13: |
| The `test` command supports one type of syntax when called as itself, and a second type of syntax when called as `testparm`. | As a demonstration: {{{ . use https://www.stata-press.com/data/r18/census3 (1980 Census data by state) . regress brate medage c.medage#c.medage i.region [snip] . test 3.region=0 ( 1) 3.region = 0 F( 1, 44) = 3.47 Prob > F = 0.0691 }}} The F statistic of the hypothesis is 3.47, corresponding to a significance level of about 0.07. In most settings, this would be considered insufficient to reject the null hypothesis: the factor is not significant. Note that the F distribution with 1 numerator degree of freedom is the t^2^ distribution, so the F statistic can be double-checked by squaring the previously-estimated t statistic on the corresponding coefficient. {{{ . test (2.region=0) (3.region=0) (4.region=0) ( 1) 2.region = 0 ( 2) 3.region = 0 ( 3) 4.region = 0 F( 3, 44) = 8.85 Prob > F = 0.0001 }}} The F statistic of the joint hypotheses is 8.85, corresponding to a significance level very close to 0. This is a strong basis to reject the joint null hypotheses: the variable is significant. |
| Line 17: | Line 45: |
| === Test Syntax === | === Expressions === |
| Line 19: | Line 47: |
| Test that one or more coefficients are equal to 0. | Expressions are interpreted by these patterns, where `a` and `b` represent ''sub-expressions'' and `1` represents a scalar value. |
| Line 21: | Line 49: |
| {{{ // Coefficients represented by variables test x1 test x1 x2 |
* `a`: hypothesis that a coefficient is equal to 0 * `a = 1`: hypothesis that a coefficient is equal to a scalar value * `a = b`: hypothesis that coefficients are equal to each other |
| Line 26: | Line 53: |
| // Coefficients represented by factor indicators test x1.a }}} |
Expressions can be delimited with parentheses. |
| Line 30: | Line 55: |
| Test that two coefficients are equal to each other. | Sub-expressions can be variable names, factor indicators, or linear combinations. For example: |
| Line 32: | Line 57: |
| {{{ // Coefficients represented by variables test x1 = x2 |
* `x1`: variable `x1` * `2.a`: factor indicator 2 of `a` * `2*x1`: linear combination of a variable * `x1+x2`: linear combination of variables |
| Line 36: | Line 62: |
| // Coefficients represented by factor indicators test x1.a = x2.a }}} If used after a multi-equation model was run, by default, these tests check that coefficients are equal to 0 in all equations. To specify an equation, try: {{{ // Test equal to 0 test [y1]x1 test [y1]x1 [y2]x1 // Test equal to each other test [y1]x1 = [y2]x1 // Alternative syntax: test [y1=y2]: x1 }}} Similarly, to test all coefficients between two equations, try: {{{ // Test all coefficients for equality to each other test [y1=y2] // Or, if not all coefficients are common to both equations, try: test [y1=y2], common }}} Linear transformations can also be tested for equality. {{{ test x1 + x2 = 4 test 2*x1 = 3*x2 }}} === TestParm Syntax === Test that one or more coefficients are equal to 0. {{{ // Coefficients represented by variables testparm x1 // Standard varlist syntax applies testparm x1-x9 testparm x* // Coefficients represented by indicators testparm i.x1 // Coefficients represented by interactions of indicators testparm i.x1#i.x2 }}} Test that two or more coefficients are equal to each other. {{{ testparm i.x1, equal }}} If used after a multi-equation model was run, by default, these tests check that coefficients are equal to 0 in all equations. To specify an equation, try: {{{ // Test equal to 0 testparm i.x1, equation(y1) // Test equal to each other testparm i.x1, equal equation(y1) }}} |
If a multiple-equation model has been run, use the `[equation]variable` syntax to specify the hypothesis. For example, `test [y1]x1=[y3]x1`. |
| Line 114: | Line 70: |
| [[Stata/TestParm|testparm]] |
Stata test
The test command performs Wald tests.
Contents
Usage
As a demonstration:
. use https://www.stata-press.com/data/r18/census3
(1980 Census data by state)
. regress brate medage c.medage#c.medage i.region
[snip]
. test 3.region=0
( 1) 3.region = 0
F( 1, 44) = 3.47
Prob > F = 0.0691The F statistic of the hypothesis is 3.47, corresponding to a significance level of about 0.07. In most settings, this would be considered insufficient to reject the null hypothesis: the factor is not significant.
Note that the F distribution with 1 numerator degree of freedom is the t2 distribution, so the F statistic can be double-checked by squaring the previously-estimated t statistic on the corresponding coefficient.
. test (2.region=0) (3.region=0) (4.region=0)
( 1) 2.region = 0
( 2) 3.region = 0
( 3) 4.region = 0
F( 3, 44) = 8.85
Prob > F = 0.0001The F statistic of the joint hypotheses is 8.85, corresponding to a significance level very close to 0. This is a strong basis to reject the joint null hypotheses: the variable is significant.
Expressions
Expressions are interpreted by these patterns, where a and b represent sub-expressions and 1 represents a scalar value.
a: hypothesis that a coefficient is equal to 0
a = 1: hypothesis that a coefficient is equal to a scalar value
a = b: hypothesis that coefficients are equal to each other
Expressions can be delimited with parentheses.
Sub-expressions can be variable names, factor indicators, or linear combinations. For example:
x1: variable x1
2.a: factor indicator 2 of a
2*x1: linear combination of a variable
x1+x2: linear combination of variables
If a multiple-equation model has been run, use the [equation]variable syntax to specify the hypothesis. For example, test [y1]x1=[y3]x1.