Approximately 1200 Danish school children aged 8, 11, and 14 participated in a questionnaire study under the caption, "Why I like to read." Data from Denmark formed part of an international study, in which 12 other countries used the same questionnaire to explore various functions of reading and to compare them over different countries. This study concentrated on gathering information by questionnaires, using the "why I like to read" data as examples. The 50 questions are described as dividing points for reducing differentiated information, given in a whole series of questions, down to score information. Such information is calculated based on components resulting from factor analyses indicating a group of questions which belongs to one conceptual unity related to reading. These components are grouped into seven dimensions: enjoyment-stimulation, enjoyment-fiction, future, diversion, my country, professional skill, and improvement of reading. A class of statistical models, especially designed to deal with categorical data, is used for these analytic purposes. The "why I like to read" data is analyzed from the viewpoint of Rasch models and is carried through testing procedures, resulting in homogeneous items. Misfits to the model are considered to be useful conflicts on which to base a new analysis. The appendix contains the questionnaire. (LMO)