Suppose we would like to compare two raters using a kappa statistic but the raters have different range of scores. This situation most often presents itself where one of the raters did not use the same range of scores as the other rater.

Let us consider an example where two graduate students where asked to rate 12 movies based on a scale from 1-3. One rater used all of the three scores possible while rating the movies whereas the other student did not like any of the movies and therefore rated all of them as either a 1 or a 2. Thus, the range of scores is the not the same for the two raters.

To obtain the kappa statistic in SPSS we are going to use the crosstabs command with the statistics = kappa option. By default, SPSS will only compute the kappa statistics if the two variables have exactly the same categories, which is not the case in this particular instance. We can get around this problem by adding a fake observation and a weight variable shown below. The weight variable takes value of 1 for all the real observations and value of 0.00001 (something very small) for the fake observation that we have just added. The trick is then to weight the observations using the weight command.

data list list /rater1 rater2. begin data. 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 3 2 3 2 3 2 3 2 end data. save outfile = kappa. data list list /rater1 rater2. begin data. 3 3 end data. add files file = * /file = kappa. exe. compute weight = 1. if ( rater1 =3 & rater2 =3 ) weight = .00001. exe. weight by weight. crosstabs /tables=rater1 by rater2 /statistics=kappa.Symmetric Measures |---------------------|-----|---------------|----------|------------| | |Value|Asymp. Std. |Approx. T |Approx. Sig.| | | |Error(a) | (b)| | |---------------|-----|-----|---------------|----------|------------| |Measure of |Kappa|.500 |.156 |3.000 |.003 | |Agreement | | | | | | |---------------|-----|-----|---------------|----------|------------| |N of Valid Cases |12 | | | | | | | | | | |---------------------|-----|---------------|----------|------------| a. Not assuming the null hypothesis. b. Using the asymptotic standard error assuming the null hypothesis.