Evaluation of cancer patients comfort with and interest in interacting with various social robot configurations in a clinical environment.

e14112 Background: Our group is interested in designing and programming social robots that augment our staff capabilities in performing different cognitive tasks in the clinic. This study examined patients' interest and comfort with various robot form factors, when screened for distress as part of a routine patient evaluation. Methods: 199 Patients (N) (Power > .80) were presented 7 commercially available robot forms and rated their comfort and interest in interacting with each one on a 5-point Likert scale (1 = Strongly Agree, 3 = Neutral, 5 = Strongly disagree).One sample t-tests compared the difference between the overall mean ratings and neutral point for comfort and interest. Independent samples t-test examined sex differences in overall ratings. Robust ANOVAs and post-hoc tests compared ratings across forms. Results: Results indicated significant interest and comfort in interacting with any robot tested, with men more interested and comfortable (see Table). Robust ANOVA indicated significant main effects for robot type ( Qcomfort = 31 .12; Qinteraction = 26 .52 , ps < .005) and sex ( Qcomfort = 21 .74; Qinteraction = 19 .35 , ps < .005) on comfort and interest. Post-hoc tests indicated that taller and narrower robots were least favored; however, there was no clear preferred form. Conclusions: Our findings suggest that patients are comfortable and interested in interacting with a robot, with men more comfortable and interested. Across robot forms, the taller and narrower forms were less favorable to patients. Future implementations of robotic interfaces may wish to avoid taller and narrower form factors. These data have informed the current model being tested in our clinics, which will be available for display. [Table: see text]

Evaluating the Efficacy of Conditional Analysis of Variance under Heterogeneity and Non-Normality

A simulation study was conducted to examine the efficacy of conditional analysis of variance (ANOVA) methods where the initial homogeneity of variance screening leads to the choice between the ANOVA F test and robust ANOVA methods. Type I error control and statistical power were investigated under various conditions.

Experimental methods of evaluating measurement uncertainty resulting from sample collection and preparation for analysis in chemical laboratories / Niepewność pomiaru wynikająca z poboru i przygotowania próbek do badań w laboratorium chemicznym oszacowana metodą doświadczalną

A measurement result should be presented with its measurement uncertainty determined according to the evaluation method. The paper presents an experimental method used to evaluate measurement uncertainty resulting from the collection and preparation of samples for analysis in chemical labs. Evaluation of measurement uncertainty of the content of particular elements in actual samples has been conducted with the method of precision determination using ROBUST ANOVA analysis of variance. Analyses of soil samples were made in the Laboratory of the Institute of Environmental Protection - National Research Institute. The experimental method of evaluating measurement uncertainty allows a fast and relatively simple evaluation of all sources of uncertainty resulting from sample collection and preparation for analysis in chemical labs

The Kruskal-Wallis Test and Stochastic Homogeneity

For the comparison of more than two independent samples the Kruskal-Wallis H test is a preferred procedure in many situations. However, the exact null and alternative hypotheses, as well as the assumptions of this test, do not seem to be very clear among behavioral scientists. This article attempts to bring some order to the inconsistent, sometimes controversial treatments of the Kruskal-Wallis test. First we clarify that the H test cannot detect with consistently increasing power any alternative hypothesis other than exceptions to stochastic homogeneity. It is then shown by a mathematical derivation that stochastic homogeneity is equivalent to the equality of the expected values of the rank sample means. This finding implies that the null hypothesis of stochastic homogeneity can be tested by an ANOVA performed on the rank transforms, which is essentially equivalent to doing a Kruskal-Wallis H test. If the variance homogeneity condition does not hold then it is suggested that robust ANOVA alternatives performed on ranks be used for testing stochastic homogeneity. Generalizations are also made with respect to Friedman’s G test.