Applied Multidimensional Scaling and Unfolding by Ingwer Borg Patrick J.F. Groenen & Patrick Mair

Author:Ingwer Borg, Patrick J.F. Groenen & Patrick Mair
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

Fig. 5.3MDS with drift vectors for Morse code confusion data

Let us look at a real data example. Rothkopf (1957) studied to what extent 598 test persons confused different acoustic Morse signals. He used 36 different signals, the 26 letters of the alphabet, and the natural numbers from 0 to 9. In the experiment, each person had to judge whether two signals, i and j, presented acoustically one after the other, were the same or not the same. Both (i, j) and (j, i) had to be judged in the experiment. The percentage of “Same!” judgments (i.e., the confusion probability) for each pair is taken as a measure of the psychological similarity of each pair.

The confusion probabilities are not symmetric. For example, the signal for i (di-di) is more frequently confused with a subsequent signal for s (di-di-di) than s is confused with a subsequent i (35% vs. 16%). But do these asymmetries exhibit a systematic pattern or are they just random? We answer this question using the driftVectors() function of the smacof package2:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.