logo
Speech Recordings  |  Speech Characteristics  |  Normative Studies  |  Depression  |  Coping Skills  |  Program Package  |  Home
unisig
logo

ITEMS — Analysis of categorial items: frequencies and weights

This program evaluates syndrome check lists on the item level in order to reveal characteristic patterns that may be present in subgroups of a given sample of cases. Subgroups are defined through a special variable that is to be created in a problem-dpendent way. Optional frequency charts may be used to visually identify group-specific patterns as well as unspecific patterns, that is, patterns that show up in all subgroups under comparison.

 
            Specificationlist:       ITEMS
            ------------------------------
            I4 NVAR              Undefined
            I4 NOBS                      0  Default-value
            I4 LGIN                     50  Default-value
            I4 MISS                   -999  Default-value
            I4 ICUT                      1  Default-value
            I4 PROT                      0  Default-value
            I4 PLOT                      0  Default-value
            I4 LPRT                      6  Default-value
               FORM(Format)
 
            01 NVAR Number of variables to be processed
            02 NOBS Maximum number of observations
            03 LGIN Logical unit number of input-device
            04 MISS Specifies how missing data are coded
            05 ICUT Controls whether case is affected/unaffected
            06 PROT Controls output to display/printer
            07 PLOT Controls output to plotter
            08 LPRT Logical unit number of output-device
            09 FORM Optional format-string for data input
            10 DEMO Examples that illustrate program function
 
            - NVAR:     Number of variables to be processed (maximum 100)
 
            - NOBS:     Maximum number of observations
 
            - LGIN:     Logical unit number of input-device (standard=40;
                        valid numbers are 40-98)
 
            - MISS = m: Items with values "m" are treated as missing data
 
            - ICUT = p: Defines cutoff between affected and unaffected
                        individuals: individuals with values < "p" are
                        treated as unaffected
 
            - PROT = 0: No print output
                   = 1: List of empirical frequencies without variable labels
                   = 2: List of empirical frequencies with variable labels
 
            - PLOT = 0: No plot output
                   = 1: Frequency charts on plotter (postscript)
 
            - LPRT:     Logical unit number of plot-device (standard=6;
                        valid numbers are 40-98)
 
            - FORM:     Optional format-string for data input (I-format):
                        must be of FORTRAN-like form: FORM(format-string)
 
 
            - DEMO: Empirical frequencies of alcohol items in males/females
 
           

Example

 
 
            &&START DBANK
            &&START LABEL=COGA alcohol items
             NLAB=37,LGIN=70,MODE=1,PROT=1
             FORM(T9,A8,1X,A40)
            &&START ITEMS=COGA empirical frequencies of alcohol items
             LGIN=71,NOBS=9000,NVAR=37,MISS=-9,ICUT=1,PROT=2,LPRT=72
             FORM(T7,37I2)
 
 
           
voxFig10
Fig. 10: There is a high comorbidity between alcohol dependence on the one hand, and psychiatric disorders on the other. The same is true for substance abuse and heavy smoking. Therefore, one has to distinguish between changes in speaking behavior and voice sound characteristics caused by alcohol or drug abuse and those related to psychiatric illnesses. Differences between males and females are significant in this respect as revealed by the differences in item patterns (Fig. 08: females, Fig. 10: males).

Partners:
Everis, Spain
ETH, Switzerland
UZH, Switzerland
Freiburg, Germany
MA Systems, UK
Bristol, UK
Xiwrite, Italy
Ultrasis, UK
Jaume, Spain
Valencia, Spain
Lanzhou, China

 

EU-Grant (FP7):
248544

[ Comments and suggestions to Webmaster ] k454910@bli.uzh.ch
[ Home ]
Impressum  |  Acknowledgements