Trisha, I agree with Frank, I'm not able to visualize your dataset. You might be interested in an ICC but I'm not sure (or sure of which one) and I don't think that PSPP does that calculation (it's an option in RELIABILITIES in SPSS).
So, if you have several correlations, I recommend that you compute them using PSPP and combine them meta-analytically. The simplest accumulation would be to take the weighted average (if each company has the same sample size, then just the average). A more interesting question would be whether the correlations are homogeneous or if there are moderators. Neither PSPP nor SPSS is particularly well suited for these kinds of (meta-analytic) calculations. -Alan On 9/15/2015 3:20 PM, Trisha Carr wrote: > Hi, > > I have a PSPP question and any help at all would be much appreciated! > I have a data set with a likelihood to recommend rating and > performance on attribute ratings for multiple companies. I'm > interested in calculating the correlation for likelihood to recommend > and performance on the attributes. I know how to use PSPP to calculate > this correlation for each brand individually. > > My question is, how can I calculate the correlation for likelihood to > recommend and performance on attributes for all companies as a whole? > Thanks in advance for any and all help. > > > _______________________________________________ > Pspp-users mailing list > Pspp-users@gnu.org > https://lists.gnu.org/mailman/listinfo/pspp-users -- Alan D. Mead, Ph.D. President, Talent Algorithms Inc. science + technology = better workers +815.588.3846 (Office) +267.334.4143 (Mobile) http://www.alanmead.org Announcing the Journal of Computerized Adaptive Testing (JCAT), a peer-reviewed electronic journal designed to advance the science and practice of computerized adaptive testing: http://www.iacat.org/jcat
_______________________________________________ Pspp-users mailing list Pspp-users@gnu.org https://lists.gnu.org/mailman/listinfo/pspp-users