TEST Subcommand (PLUM command)
The TEST
subcommand
allows you to customize your hypothesis tests by directly specifying
null hypotheses as linear combinations of parameters.
-
TEST
is offered only through syntax. - Multiple
TEST
subcommands are allowed. Each is handled independently. - The basic format of the
TEST
subcommand is an optional list of values enclosed in a pair of parentheses, an optional label in quotes, an effect name or the keywordALL
, and a list of values. - To specify the coefficient for the intercept, use
the keyword
INTERCEPT
. The number of values afterINTERCEPT
must be equal to the number of response categories minus 1. - When multiple linear combinations are specified within
the same
TEST
subcommand, a semicolon terminates each linear combination, except the last one. - The linear combinations are separately tested for each category of the dependent variable and then simultaneously tested for all the categories.
- If specified, the value list that immediately follows the subcommand name is the constant that the linear combinations are equated to under the null hypotheses. If this value list is omitted, the constants are assumed to be all zeros.
- The optional label is a string with a maximum length
of 255 bytes. Only one label per
TEST
subcommand can be specified. - Only valid effects appearing or implied on the
LOCATION
or theSCALE
subcommands can be specified in a linear combination. If an effect appears in both subcommands, then enter the effect only once on theTEST
subcommand. - To specify coefficient for the intercept, use the
keyword
INTERCEPT
. Only one value is expected to followINTERCEPT
. - The number of values following an effect name must equal the number of parameters (including the redundant ones) corresponding to that effect. For example, if the effect A*B takes up six parameters, then exactly six values must follow A*B.
- A number can be specified as a fraction with a positive denominator. For example, 1/3 or –1/3 are valid, but 1/–3 is invalid.
- When
ALL
is specified, only a list of values can follow. The number of values must equal the combined number ofLOCATION
andSCALE
parameters (including the redundant ones). - Effects appearing or implied on the
LOCATION
or theSCALE
subcommands but not specified on theTEST
are assumed to take the value 0 for all their parameters. - Effect names and the
ALL
keywords are mutually exclusive within a singleTEST
subcommand. - If
ALL
is specified for the first row in aTEST
matrix, then all subsequent rows should begin with theALL
keyword. - If effects are specified for the first row in a
TEST
matrix, then all subsequent rows should use effect name (thusALL
is not allowed).
Example
PLUM
chist BY housng
/CRITERIA = CIN(95) DELTA(0) LCONVERGE(0) MXITER(100) MXSTEP(5)
PCONVERGE(1.0E-6) SINGULAR(1.0E-8)
/LINK = CLOGLOG
/PRINT = CELLINFO CORB COVB FIT HISTORY(1) PARAMETER
SUMMARY TPARALLEL
/TEST(0 0) = ALL 1 -1 0 0 0 0 0;
ALL 0 0 1 -1 0 0 0.
- There are a total of seven parameter coefficients
in the model; four for the thresholds, and three for the factor housng.
TEST
specifies two separate tests: one in which the first and second thresholds are tested for equality, and one in which the third and fourth thresholds are tested for equality.