Table 31.4 summarizes the CLASS Differential Person Functioning statistics for each person shown in Table 31.2. Table 31.2 shows a t-statistic for each CLASS. These are summarized as chi-square statistics for each person, indicating whether the observed DPF within each person is due to chance alone. The null hypothesis is that the DPF is statistically zero across the classes.

 

DPF class specification is: DPF=$S1W1

------------------------------------------------------------------------------

| TAP        SUMMARY DPF               BETWEEN-CLASS       KID               |

| CLASSES    CHI-SQUARE   D.F.  PROB.  MEAN-SQUARE t=ZSTD  Number Name       |

|----------------------------------------------------------------------------|

|       2         .2914      1  .5893       .2291  -.3520       1 Adam    M  |

 

TAP CLASSES is the count of item CLASSES with estimable DPF for the person.

SUMMARY DIF CHI-SQUARE is the sum of the squared normalized t-statistic values from Table 31.2.

D.F. is the degrees of freedom, the count of CLASSES contributing to the chi-square less 1.

PROB. is the probability of the chi-square. Values less than .05 indicate statistical significance.

 

BETWEEN-CLASS are the Between-Group Fit Statistics (Smith & Plackner, 2009) is testing the hypothesis: "The dispersion of the group measures accords with Rasch model expectations."

MEAN-SQUARE is chi-square divided by its degrees of freedom. It is the size of the misfit (expectation = 1.0, overfit <1.0, underfit >1.0).

t=ZSTD is the significance of the MEAN-SQUARE standardardized as a unit-normal deviate (t-statistic with infinite degrees of freedom).

 

KID is the person. Number is the person entry number. Name is the person label.

 

Smith RM, Plackner C. The family approach to assessing fit in Rasch measurement. J Appl Meas. 2009;10(4):424-37