Correspondence analysis used complementary to loglinear analysis

Loglinear analysis and correspondence analysis provide us with two different methods for the decomposition of contingency tables. In this paper we will show that there are cases in which these two techniques can be used complementary to each other. More specifically, we will show that often correspondence analysis can be viewed as providing a decomposition of the difference between two matrices, each following a specific loglinear model. Therefore, in these cases the correspondence analysis solution can be interpreted in terms of the difference between these loglinear models. A generalization of correspondence analysis, recently proposed by Escofier, will also be discussed. With this decomposition, which includes classical correspondence analysis as a special case, it is possible to use correspondence analysis complementary to loglinear analysis in more instances than those described for classical correspondence analysis. In this context correspondence analysis is used for the decomposition of the residuals of specific restricted loglinear models.     

Iterative least squares estimates of communality: Initial estimate need not affect stabilized value

A common criticism of iterative least squares estimates of communality is that method of initial estimation may influence stabilized values. As little systematic research on this topic has been performed, the criticism appears to be based on cumulated experience with empirical data sets. In the present paper, two studies are reported in which four types of initial estimate (unities, squared multiple correlations, highestr, and zeroes) and four levels of convergence criterion were employed using four widely available computer packages (BMDP, SAS, SPSS, and SOUPAC). The results suggest that initial estimates have no effect on stabilized communality estimates when a stringent criterion for convergence is used, whereas initial estimates appear to affect stabilized values employing rather gross convergence criteria. There were no differences among the four computer packages for matrices without Heywood cases.     

Statistical consistency and hypothesis testing for nonmetric multidimensional scaling

The properties of nonmetric multidimensional scaling (NMDS) are explored by specifying statistical models, proving statistical consistency, and developing hypothesis testing procedures. Statistical models with errors in the dependent and independent variables are described for quantitative and qualitative data. For these models, statistical consistency often depends crucially upon how error enters the model and how data are collected and summarized (e.g., by means, medians, or rank statistics). A maximum likelihood estimator for NMDS is developed, and its relationship to the standard Shepard-Kruskal estimation method is described. This maximum likelihood framework is used to develop a method for testing the overall fit of the model.     

Symmetry and transitivity of conditional relations in monkeys (Cebus apella) and pigeons (Columba livia)

In Experiment 1 six monkeys were tested with discriminative relations that were backward relative to their training in a 0-second conditional (“symbolic”) matching procedure. Although there was some indication of backward associations, the evidence was generally weak, and statistical evaluations did not reach conventional significance levels. Unlike children, who show backward associations to the point of symmetry, monkeys and pigeons display at best only weak and transient backward associations. In Experiment 2 associative transitivity was assessed across two sets of conditional matching tasks. All four monkeys tested demonstrated strong transitivity. In contrast, in Experiment 3 there was no evidence of transitivity in three pigeons tested under conditions closely comparable to those of Experiment 2. These results may identify some key features of interspecies differences and contribute to analyses of serial learning in animals.     

Flicker fusion frequency and organic syndrome in alcoholics

Flicker fusion frequencies of 48 healthy controls and of 35 alcoholics were measured to detect possible associations between flicker fusion and signs of nonspecific brain damage, the aim of the study. FFF was statistically significantly lower in patients addicted to alcohol than in healthy subjects. Lower flicker fusion frequencies were associated with the severeness of organic psychosis as rated psychopathologically. The hypothesis that addiction to alcohol is a sign of diffuse, nonspecific, organic brain damage was discussed.     

Temporal lobe signs and reports of subjective paranormal experiences in a normal population: a replication

Correlations (r = 0.50) were found between the numbers of different psi (paranormal) experiences and the numbers of temporal lobe signs within a population of university students (n = 99). The strongest correlation of 0.60 occurred with a cluster of signs that are similar to symptoms reported by patients who show chronic foci in the mesiobasal temporal lobe. However, there were no significant correlations between numbers of different psi experiences and clusters of control items or a lie scale. Specific analyses of the 140 items of the inventory indicated only 23 reached statistical criterion (p less than .001). Of these 17 were direct temporal lobe signs that implied deepened affect, auditory-vestibular experiences (vibrations, hearing one's name called), olfactory auras, perseveration ("forced" thinking), depersonalization, and sense of the personal. Five items involved beliefs about exotic phenomena or philosophical ideas. Only one item was from a control cluster. These results support the hypothesis that mystical or paranormal experiences are associated with transient electrical foci within the temporal lobe of the human brain. The repeated occurrence of these experiences within normal individuals may be embedded within a more complex symptomatology of temporal lobe signs.     

Interactive effects of noise with illumination and age on activity of rats

Locomotor activity of male, albino rats (25, 90, and 200 days old at the start of the experiment) was measured in conditions of light and dark. Continuous and pulsed noises of 50, 60, 70, 80 and 90 dB were presented under each illumination condition. While noise intensity altered activity of all age groups, it interacted with illumination and age, resulting in different sensory-dependent patterns of activity in each age group. The results are interpreted in terms of arousal theory and potential functional development of CNS structures regulating the effects of ambient sensory input on behavior.     

Physical training and personality factors as predictors of marathon time and training injury

On the basis of surveys completed by 105 male participants in a popular marathon, a multiple regression analysis was conducted to identify the variables contributing significantly to the prediction of final time. Overall prediction was successful, with R = .896, and training pace was the most important factor in the equation, speedier workouts being associated with faster marathon times. Final time was also related positively to best 10-km race time in the previous 12 mo. and repression-sensitization (faster runners being more sensitized), and negatively to maximum number of training miles in a single week, number of previous marathons completed, and number of days of training lost through illness or injury. Contrary to expectations, locus of control was not related to final time. Only 27% of the runners had lost training time through injury, but a discriminant analysis showed that, compared to those who had avoided this problem, the injured were younger, rested less, ran less in the week prior to the marathon, ran a slightly longer long run but ran it earlier before the race, and ran fewer runs of 20 miles or more. It is suggested that researchers should study the repression-sensitization variable and investigate injury in runners preparing for a marathon.     

Antidepressant treatment of children: clinical relapse is unrelated to tricyclic plasma concentrations

Plasma concentrations of imipramine and amitriptyline and their desmethylated metabolites were measured in 20 children being treated for major depressive illness 2 wk. and 5 to 10 wk. after achieving drug dosages of 2.25 mg/kg body weight. At 2 wk. all children had exhibited clinical improvement, but by 10 wk. 4 of the 10 children treated with imipramine and 5 of the 10 children treated with amitriptyline had experienced clinical relapse of depressive symptoms. Tricyclic antidepressant plasma concentrations and ratios were comparable in the subgroups of children who maintained their clinical improvement and those who relapsed. There was no evidence of a systematic decline in plasma tricyclic antidepressant concentrations in those children who relapsed.