An instruction, which sometimes is called teaching-learning process, is a communication process between teacher's teaching behaviors and learner's learning behaviors, and it can be represented as time series category data of teaching-learning behaviors. This paper describes a method for clustering some behavior sequences and also describes results applied on actual instruction. The method is constructed as follows. Partition of time series category data Cluster analysis for partitioned sequences Time series cluster analysis for some similar partitioned sequences As results can be shown as graph-representation, it is understandable and seems to be useful instructional study.

View full abstract

By using 28 signs and symptoms(SS)commonly used in traditional Chinese medicine, specialists in Chinese medicine classified 377 cases of chronic epigastralgia(wei won tong)into 3 disease categories, that is D1, D2 and D3. The data collected in this study were analysed by correspondence analysis. Both 377 cases and 28 SS were arranged according to the similarity and were assigned on multidimensional coordinates. On the 2 dimensional plane spanned by the first 2 components, 377 cases were plotted and were examined whether the members of the same category could make an isolated cluster and did not mix with those of the different categories. The examination revealed that the members of D1 and those of D2 occupied the left half and the right half of one unseparable group, respectively. On the other hand, those of D3 were scattered below the combined group of D1 and D2. As a result, it was concluded that the separation of D1 and D2 was considerably difficult from the standpoint of the numerical taxonomy alone, whereas that of D3 and the rest members was achieved by using the coordinates of the 2nd component. Spatial allocation of each of the 28 SS was represented multidimensionally, and could not be reduced to a few dimensional By using 28 signs and symptoms(SS)commonly used in traditional Chinese medicine, specialists in Chinese medicine classified 377 cases of chronic epigastralgia(wei won tong)into 3 disease categories, that is D1, D2 and D3. The data collected in this study were analysed by correspondence analysis. Both 377 cases and 28 SS were arranged according to the similarity and were assigned on multidimensional coordinates. On the 2 dimensional plane spanned by the first 2 components, 377 cases were plotted and were examined whether the members of the same category could make an isolated cluster and did not mix with those of the different categories. The examination revealed that the members of D1 and those of D2 occupied the left half and the right half of one unseparable group, respectively. On the other hand, those of D3 were scattered below the combined group of D1 and D2. As a result, it was concluded that the separation of D1 and D2 was considerably difficult from the standpoint of the numerical taxonomy alone, whereas that of D3 and the rest members was achieved by using the coordinates of the 2nd component. Spatial allocation of each of the 28 SS was represented multidimensionally, and could not be reduced to a few dimensional space.

View full abstract

Automated Rorschach system was developed for Klopfer-Kataguchi technique. Programs were written in BASIC, the total size is about190KB, and run on a personal computer system of NEC's PC-9801series. The Rorschach scores were written by line-editor in the traditional manner. The automated interpretation was based on the standard scores cut off by mean± 1σ and mean± 2σ . Two hundred and fifty five if-then rule based system were constructed on the quantitative relationships included with contents, and the sequence of the record. Fifty four meta-rules regulate the contradictory rules. The outputs for screen, printer, and disk, were consisted of scoring list, tables of location, determinant, contents, psychogram, summary scor ings, record of clients, and the automated interpretation. The automated interpretation was printed in the ordinary style of Japanese containing about1500-2000letters. The system performance was evaluted for concordance of the automated diagnoses to the seventy-five clinical cases and to the thirty-three normal subjects. The result of analyses revealed that our system was in full clinical validity. The automated interpretation of the Rorschach record of the methamphetamine psychotic was compared to the report by the clinician.

View full abstract

In order to prevent cardiovascular disease, a new questionnaire, called“ LPC(life planning center)questionnaire on life habits”, was constructed. The procedure and result were summar ized as follows. 1)Preliminary questionnaire was used in164house wives. By means of statistical analy sis of the obtained data, we made the questionnaire consisting of23scales with195items concerning food habits, behavior patterns, health condition, personality and value system. 2)A main survey was carried out in seven different regions(five for female and two for male respectively), in which5894adult females and914adult males were chosen. 3)Reliability coefficients were obtained from the result of principal component analysis based on items for each scale. The values of reliability coefficients ranged from0. 486to0. 845. Some scales with lower values should be necessary to be modified to some extent in the near future. 4)For evaluating life habits, the mean values of the23scales were calculated separately for each sex. Significant differences are found among some scales stratified with respect to ages, sexes and medical histories. 5)Six factors were extracted by means of varimax rotated factor analysis, which were useful for grasping life habits for both sexes

View full abstract

Statistics has retained steady relationships with the graphics for a long time, but we will not mention about the past, In this paper, we will evaluate and consider the present state of work in the field of statistical graphics including graphical methods used in the process of statistical data analysis, graphical communication of information, recent research and dissemination of statistical graphics, and reflect on the future. Paying attention to the development of recent statistical graphics, we especially review on following themes, namely, (1)cooperation between formal methods and graphical methods, (2)computer-oriented approaches, (3)advances in exploratory data analysis and dinamic graphics, (4)development of philosophical basis of graphical methods. Many methods that are called statistical graphics are proposed and available. Although, in order that these methods can be accepted and play useful roles, it seems that various conditions such as the celebrity of the proponent(his achievement, thought and background), fashion of the times, and maturity(adaptability of the surroundings). The main points we wish to emphasize in this paper are summarized as follows. First, to compare to the formal methods, graphical methods have many advantages as well as some shortages. Thus, it is necessary to understand the properties of each graphical method and to use it properly in the process of statistical data analysis. Second, we must take into considerations the “philosophical context of visual perception”, namely a series of process which starts from “outward apperance” and attains to inner looking. It is necessary to pay great attention to the aspects of “ conception” or“ discovery” for graphical methods to play the creative role that bring forth the productive findings. Third, many and various graphical methods have been developed keeping step with the development and evolution of computer and computing environ ment. Thus, it is urgently needed to standardize and systematize these graphical methods and gain experiences of applying them so that users of them can utilize the right method in the right place.

View full abstract