PROC CAPABILITY and General Statements

Output Data Set

OUTTABLE= Data Set

The OUTTABLE= data set saves univariate statistics and capability indices. The following variables can be saved:

Table 5.4: OUTTABLE= Data Set

Variable

Description

_CP_

capability index $C_{p}$

_CPLCL_

lower confidence limit for $C_{p}$

_CPUCL_

upper confidence limit for $C_{p}$

_CPK_

capability index $C_{pk}$

_CPKLCL_

lower confidence limit for $C_{pk}$

_CPKUCL_

upper confidence limit for $C_{pk}$

_CPL_

capability index $CPL$

_CPLLCL_

lower confidence limit for $CPL$

_CPLUCL_

upper confidence limit for $CPL$

_CPM_

capability index $C_{pm}$

_CPMLCL_

lower confidence limit for $C_{pm}$

_CPMUCL_

upper confidence limit for $C_{pm}$

_CPU_

capability index $CPU$

_CPULCL_

lower confidence limit for $CPU$

_CPUUCL_

upper confidence limit for $CPU$

_CSS_

corrected sum of squares

_CV_

coefficient of variation

_GINI_

Gini’s mean difference

_K_

capability index K

_KURT_

kurtosis

_LSL_

lower specification limit

_MAD_

median absolute difference about the median

_MAX_

maximum

_MEAN_

mean

_MEDIAN_

median

_MIN_

minimum

_MODE_

mode

_MSIGN_

sign statistic

_NMISS_

number of missing observations

_NOBS_

number of nonmissing observations

_P1_

1st percentile

_P5_

5th percentile

_P10_

10th percentile

_P90_

90th percentile

_P95_

95th percentile

_P99_

99th percentile

_PCTGTR_

percentage of observations greater than upper specification limit

_PCTLSS_

percentage of observations less than lower specification limit

_PROBM_

p-value of sign statistic

_PROBN_

p-value of test for normality

_PROBS_

p-value of signed rank test

_PROBT_

p-value of t statistic

_Q1_

25th percentile (lower quartile)

_Q3_

75th percentile (upper quartile)

_QN_

$Q_ n$ (see Robust Estimates of Scale)

_QRANGE_

interquartile range (upper quartile minus lower quartile)

_RANGE_

range

_SGNRNK_

centered sign rank

_SKEW_

skewness

_SN_

$S_ n$ (see Robust Estimates of Scale)

_STD_

standard deviation

_STDGINI_

Gini’s standard deviation

_STDMAD_

MAD standard deviation

_STDMEAN_

standard error of the mean

_STDQN_

$Q_ n$ standard deviation

_STDQRANGE_

interquartile range standard deviation

_STDSN_

$S_ n$ standard deviation

_SUMWGT_

sum of the weights

_SUM_

sum

_TARGET_

target value

_USL_

upper specification limit

_USS_

uncorrected sum of squares

_VARI_

variance

_VAR_

variable name


Note: The variables _CP_, _CPLCL_, _CPUCL_, _CPK_, _CPKLCL_, _CPKUCL_, _CPL_, _CPLLCL_, _CPLUCL_, _CPM_, _CPMLCL_, _CPMUCL_, _CPU_, _CPULCL_, _CPUUCL_, _K_, _LSL_, _PCTGTR_, _PCTLSS_, _TARGET_, and _USL_ are included if you provide specification limits.

The OUTTABLE= data set and the OUT= data set[15] contain essentially the same information. However, the structure of the OUTTABLE= data set may be more appropriate when you are computing summary statistics or capability indices for more than one process variable in the same invocation of the CAPABILITY procedure. Each observation in the OUTTABLE= data set corresponds to a different process variable, and the variables in the data set correspond to summary statistics and indices.

See CAPTAB1 in the SAS/QC Sample LibraryFor example, suppose you have ten process variables (P1-P10). The following statements create an OUTTABLE= data set named Table, which contains summary statistics and capability indices for each of these variables:

proc capability data=Process outtable=Table noprint;
   var P1-P10;
   specs lsl=5 10 65 35 35 5 25 25 60 15
         usl=175 275 300 450 550 200 275 425 500 525;
run;

The following statements create the table shown in Figure 5.4, which contains the mean, standard deviation, lower and upper specification limits, and capability index $C_{pk}$ for each process variable:

proc print data=Table label noobs;
   var _VAR_ _MEAN_ _STD_ _LSL_ _USL_ _CPK_;
   label _VAR_='Process';
run;

Figure 5.4: Tabulating Results for Multiple Process Variables

Process Capability Analysis of Fluid Weight

Process Mean Standard Deviation Lower Specification
Limit
Upper Specification
Limit
Capability Index
CPK
P1 90.76 57.024 5 175 0.49242
P2 167.32 81.628 10 275 0.43972
P3 224.56 96.525 65 300 0.26052
P4 258.08 145.218 35 450 0.44053
P5 283.48 157.033 35 550 0.52745
P6 107.48 52.437 5 200 0.58814
P7 153.20 90.031 25 275 0.45096
P8 217.08 130.031 25 425 0.49239
P9 280.68 140.943 60 500 0.51870
P10 243.24 178.799 15 525 0.42551




[15] See OUTPUT Statement: CAPABILITY Procedure for details on the OUT= data set.