PWEIGHT= allows for differential weighting of persons. The standard weights are 1 for all persons. To change the weighting of items, specify PWEIGHT=

 

 

Raw score, count, and standard error of measurement reflect the absolute size of weights as well as their relative sizes.

Measure, infit and outfit and correlations are sensitive only to relative weights.

 

If you want the standard error of the final weight-based measure to approximate the S.E. of the unweighted measure, then ratio-adjust case weights so that the total of the weights is equal to the total number of independent observations.

 

Formats are:

 

PWEIGHT=file name

the weights are in a file of format:

person entry number weight

 

PWEIGHT=*

person entry number weight

....

*

 

PWEIGHT=$S...$W... or $S...$E...

weights are in the data records using the column selection rules, e.g., starting in column S... with a width of W... or starting in column S and ending in column E. This can be expanded, e.g, PWEIGHT = $S23W1+"."+$S25W2 places the columns next to each other (not added to each other)

 

PWEIGHT= increases the influence of that person's observations on the estimation. For instance, suppose 3 persons respond to a dichotomous item: 0 0 1 - this yields a marginal score of 1 out of a possible 3.

Then

Pweight=*

3 2  ; weight person 3 twice

*

The response are now: 0 0 1*2 - this yields 2 out of a possible 4. So that the PWEIGHT= item is easier than the unweighted item.

 

Example 1:

In a sample of 20 respondents, person 1 is to be given a weight of 2.5, all other persons have a weight of 1.

 PWEIGHT=*

 1 2.5

 2-20 1

 *

 

A better weighting, which would make the reported item standard errors more realistic by maintaining the original total sum of weights at 20 , is:

 PWEIGHT=*

 1 2.33 ; 2.5 * 0.93

 2-20 0.93 ; the sum of all weights is 20.0

 *

+---------------------------------------------------------------------------------+

|ENTRY    RAW                   MODEL|   INFIT  |  OUTFIT  |PTMEA|     |          |

|NUMBER  SCORE  COUNT  MEASURE  S.E. |MNSQ  ZSTD|MNSQ  ZSTD|CORR.|WEIGH| KID      |

|------------------------------------+----------+----------+-----+-----+----------|

|     1      4     10   -1.20     .85| .65   -.9| .41    .3|  .82| 2.33| Richard M|

|     2      7     10    1.70    1.17| .18  -1.2| .10   -.4|  .94|  .93| Tracie  F|

|     3      7     10    1.70    1.17|2.04   1.2|1.32    .7|  .84|  .93| Walter  M|

 

Example 2:

The data records contain the weights in columns 16-18 of the record. The person label starts in column 15, so this is also column 2 of the person label

 PWEIGHT= $C16W3 ; or $C16E18 ; column in data record

or

 NAME1 = 15  ; start of person label

 NAMELEN = 20  ; length of person label

 PWEIGHT= $S2W3 ; location in person label

 

 &END

 ...

 END NAMES

 10110110011001 0.5 Person A

 01001100011011 0.7 Person B

 ......

 

Example 3:

Person 4 is a dummy case, to be given weight 0.

 

 PWEIGHT=*

 4 0 ; Person 4 has weight 0, other persons have standard weight of 1.

 *