Matrix assisted structural hypothesis construction : Further explorations

This paper outlines a novel process for designing a structural hypothesis. Relevant factors in a study are identified and micro-hypotheses are enunciated in a matrix format. Levels of similarity are assigned to each pair of factors. Multi-dimensional scaling tech niques are used to graphically portray the matrix. The example of "Quality of Life" (QoL) is used to illustrate the proposed matrix approach to generate a structural hypothesis. A Smallest Space Analysis (SSA) of the hypothetical Quality of Life matrix shows a struc ture in which four polar regions surround a central region representing "general" QoL. This clear and logical structure of the hypothesized correlation matrix is a strong first confirmation that the approach allows for a detailed, systematic and theoretically based mode of reasoning and didactics. Additionally, the structure found here corresponds to a previous SSA analysis based on empirical Quality of Life data.