CRITERIA Subcommand (META BINARY command)

The META BINARY command calls the meta-analysis procedure for binary outcomes when the raw data are provided in the active dataset for the estimation of the effect size. The optional CRITERIA subcommand specifies the general procedure criteria.

SCOPE
The optional keyword controls how the procedure handles missing data. AVAILABLE is the default setting, which includes all cases with sufficient data on the variables used in each particular analysis. LISTWISE includes all cases with sufficient data on all variables used across all analyses specified by the procedure.
CLASSMISSING
The optional keyword controls how user-missing values are treated. EXCLUDE is the default setting, which treats user-missing values as valid values. INCLUDE ignores user-missing value designations and treats user-missing values as valid values.
CILEVEL
The optional keyword specifies the confidence level. The value must be a single numeric value between 0 and 100. The default value is 95.
MAXITER
The optional keyword specifies the maximum number of iterations in the iterative methods. The value must be a single non-negative integer (100 is the default setting). The keyword is available when iterative methods are used. MAXITER = 0 means that no iterations are performed.
MAXSTEP
The optional keyword specifies the maximum step-halving in the iterative methods. The value must be a single non-negative integer (5 is the default setting). The keyword is available when iterative methods are used. MAXSTEP = 0 means that no step-halving is applied.
CONVERGENCE
The optional keyword specifies the convergence tolerance. The value must be a single positive value (1E-6 is the default setting). The keyword is available when iterative methods are used.
DROP
The optional keyword controls whether to exclude the studies with either no cases or only cases in both treatment and control groups. FALSE is the default setting, which keeps the studies in meta-analysis. TRUE rules out the studies.
ZEROCOUNTS
The optional keyword controls how to adjust the zero-count data, when applicable, in the effect size estimation.
ONLY
The default setting adjusts each cell for only those tables containing at least one zero.
IFALL
Adjusts each table cell but only if there exists at least one table containing a zero cell.
ALL
Adjusts each cell for all tables regardless of the existence of zero-counts.
KEEP
Makes no adjustments, which is available when ESTYPE = RD.
ADD
The optional keyword specifies the value added to the zero-count data with 0.5 as the default setting. The value must be a single numeric value greater than 0 and less than or equal to 1. The process is available when ZEROCOUNTS = ONLY, IFALL, or ALL, and is otherwise ignored.