Function Subcommands (RANK command)

The optional function subcommands specify different rank functions. RANK is the default function.

• Any combination of function subcommands can be specified for a RANK procedure, but each function can be specified only once.
• Each function subcommand must be preceded by a slash.
• The functions assign default names to the new variables unless keyword INTO is specified.

RANK. Simple ranks. The values for the new variable are the ranks. Rank can either be ascending or descending, as indicated on the VARIABLES subcommand. Rank values can be affected by the specification on the TIES subcommand.

RFRACTION . Fractional ranks. The values for the new variable equal the ranks divided by the sum of the weights of the nonmissing cases. If HIGH is specified on TIES, fractional rank values are an empirical cumulative distribution.

NORMAL. Normal scores ¹. The new variable contains the inverse of the standard normal cumulative distribution of the proportion estimate defined by the FRACTION subcommand. The default for FRACTION is BLOM.

PERCENT. Fractional ranks as a percentage. The new variable contains fractional ranks multiplied by 100.

PROPORTION . Proportion estimates. The estimation method is specified by the FRACTION subcommand. The default for FRACTION is BLOM.

N. Sum of case weights. The new variable is a constant.

SAVAGE. Savage scores ². The new variable contains Savage (exponential) scores.

NTILES(k) . Percentile groups. The new variable contains values from 1 to k, where k is the number of groups to be generated. Each case is assigned a group value, which is the integer part of 1+rk/(w+1), where r is the rank of the case, k is the number of groups specified on NTILES, and w is the sum of the case weights. Group values can be affected by the specification on TIES. There is no default for k.