Comparison of Selected Methods of Transformations of Proportions

1983 ◽  
Vol 57 (2) ◽  
pp. 423-426 ◽  
Author(s):  
Joseph C. Bledsoe

44 female white teachers were observed for six separate 20-min. periods for a total of 88 hr. The frequency of approving and disapproving behaviors toward boys and girls were obtained and two indices consisting of proportions of approving to total behaviors of boys and girls were derived. After observation, the Bern Sex-role Inventory was administered to the teachers, and four groups of 11 teachers each were classified by a median-split procedure as androgynous, masculine, feminine, and undifferentiated. The two proportions were then transformed to arc sine (angit), probit, and logit scales and compared to the results of the analysis of the nontransformed proportions. Differences in all analyses showed girls were more favorably perceived than boys; feminine teachers showed greatest differences and masculine teachers showed the smallest differences. All differences between approving behaviors of boys and girls were significant except for those of masculine teachers. The three transformations gave essentially similar results with approximately 4% greater non-error variance. The transformations eliminated a gross heterogeneity of variance in the proportions and the logit analysis was most sensitive to differences among types of teacher and pupil-sex groups. Implications were briefly discussed.

1983 ◽  
Vol 53 (3) ◽  
pp. 711-714 ◽  
Author(s):  
Joseph C. Bledsoe

44 white female teachers were observed by two observers for six separate 20-min. periods for a total of 88 hr. The frequencies of approval and disapproval behaviors toward boys and girls were obtained. After observation, the Bem Sex-role Inventory was administered to the teachers, and four groups of 11 teachers each were classified by a median split-procedure as androgynous, masculine, feminine, and undifferentiated. As predicted, masculine teachers were more approving of boys' behavior, feminine teachers were more approving of girls' behavior and less approving of boys' behavior. In total observations, types of teacher did not differ, but when approval or disapproval was considered, there were significant differences according to pupils' sex and type of observation. Teachers' self-definition of sex-role type is likely to influence significantly their behavior toward middle-school boys and girls.


1983 ◽  
Vol 52 (3) ◽  
pp. 993-994
Author(s):  
Joseph C. Bledsoe

44 female teachers in Grades 7 and 8 were observed by two observers for 6 separate 20-min. periods, from which 2 measures of teachers' interaction were derived, proportion of approval to total behavior in interactions with boys and proportion of approval to total behaviors with girls. Teachers then completed the Bem Sex-role Inventory and 11 teachers each were categorized as Androgynous (+,+), Masculine (+, −), Feminine (−, +), and Undifferentiated (−, −) by a median-split procedure. The two measures of classroom behavior were then used as predictor variables in a discriminant analysis to predict sex-role type. Of 44, 23 or 53% were correctly classified, 17 of whom were self-defined as “Masculine” or “Feminine.”


1986 ◽  
Vol 10 (3) ◽  
pp. 263-273 ◽  
Author(s):  
Michael Windle

Bem's Sex Role Inventory (Bem, 1974) was employed to categorize 101 older adults into masculine, feminine, androgynous, and undifferentiated sex role orientations. Relationships among these sex role orientations and cognitive flexibility and life satisfaction were explored. Additionally, hierarchical multiple regression analyses were performed to assess the contributions of masculinity, femininity, and the interaction term (masculinity x femininity) in the prediction of cognitive flexibility and life satisfaction. These older adults did not vary significantly in either their cognitive flexibility or their life satisfaction as a function of their sex role categorization, nor was an appreciable percentage of variance accounted for by the predictor variables in the regression analyses. Issues are raised regarding the validity of the typological (median-split based) approaches used by researchers to assess expectations of the differentiation of masculine and feminine components in older adults. An alternative structural developmental approach, based on a factor-analytic methodology, is proposed.


2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Md. Bokhtiar Hasan Aarif ◽  
Muhammad Rafiqul Islam Rafiq ◽  
Abu N.M. Wahid

Purpose This paper aims to examine whether the Sharīʿah indices outperform the conventional indices as evident from Dhaka Stock Exchange (DSE). To achieve the objective, the study, first, assesses the risk adjusted returns of the Sharīʿah and conventional indices and compares the same between the two indices. Second, it examines the short-run and long-run associations between the two indices. Design/methodology/approach The DSEX Sharīʿah index and DSE broad index of the DSE are used as representatives of the Sharīʿah and conventional indices, respectively. The study uses monthly data for the period 2014–2018 and applies a number of techniques such as risk adjusted returns, Johansen’s cointegration test, vector error correction model, Granger causality test, forecast error variance decomposition and impulse response functions techniques. Findings The study reveals that albeit there is no significant difference in simple mean between the two indices, the Sharīʿah index outperforms its conventional counterpart based on the risk adjusted returns. The two indices are associated only in the long-run, while no causal relationship is spotted between them. The overall results show that the Sharīʿah index has dominance over the conventional index in Bangladesh. Research limitations/implications The study could use more pairs of indices, including additional variables such as financial crisis and macroeconomic variables. Practical implications The study has important implications to investors, especially the religious Muslims and ethical ones, who are suggested to invest their funds in the Sharīʿah index without sacrificing returns, rather be monetarily more benefited. Moreover, the other investors can generate diversification benefits by adding both Sharīʿah and conventional indices in their portfolios in the short-run. Originality/value Unlike previous studies, this study endeavors to use a comprehensive methodology to conduct its analysis. Moreover, this is supposedly the first ever effort to conduct such a study in the context of Bangladesh.


Blood ◽  
1957 ◽  
Vol 12 (7) ◽  
pp. 649-656 ◽  
Author(s):  
G. J. MOGENSON ◽  
L. B. JAQUES

Abstract Forced jumping in the Lashley jumping apparatus, maintenance in cages with an electrified water source, transportation, sound-induced seizures, and electroconvulsive treatment were used in studying the effects of psychological stress on the prothrombin time of the albino rat. An increased prothrombin time occurred at certain times following forced jumping, sound-induced seizures, and electroshock. Frequently the altered coagulability was reflected in a greater heterogeneity of variance due to some animals having a longer prothrombin time and others shorter. The changes in the prothrombin time following stress were more pronounced when the prothrombopenic drug, Dicumarol, was administered. This was evident from two indices, prothrombin time and mortality.


1980 ◽  
Vol 47 (1) ◽  
pp. 143-146 ◽  
Author(s):  
Elizabeth C. Penick ◽  
Barbara J. Powell ◽  
Marsha R. Read ◽  
David Mahoney

Contemporary measures of sex-role affiliation, which emphasize the relative independence of masculine and feminine attributes, typically rely upon a median-split procedure to generate a four-fold typology, e.g., masculine, feminine, indeterminant, and androgynous types. Methodological problems created by this classification technique are illustrated for one combined male/female sample and three male samples given the PRF ANDRO. The number in each standardization sample was Combined, 772; Males, 386; Alcoholics, 123; Veterans of Foreign Wars, 73. Sex-role typing was markedly influenced by the sample from which median cutting scores were derived.


1983 ◽  
Vol 52 (1) ◽  
pp. 69-70 ◽  
Author(s):  
Barbara A. Wech

Correlations among sex-role orientation, stress, and health were examined. Masculine sex-typed subjects reported significantly fewer health problems than feminine subjects. Discussed are two scoring methods for Bem's scale, the original method and the difference/median split.


1978 ◽  
Vol 43 (2) ◽  
pp. 415-418 ◽  
Author(s):  
George D. Yonge ◽  
Mary C. Regan

38 male and 38 female university students were classified by a median split on the Autonomy scale from the Omnibus Personality Inventory as authoritarian and non-authoritarian. Subjects also completed a modified version of a questionnaire developed by Hawley (1971) dealing with traditional versus androgynous female sex-role expectations. The five scores derived from this questionnaire are: Woman as Partner, Woman as Ingenue, Woman as Homemaker, Woman as Competitor, and Woman as Knower. As anticipated, authoritarian subjects held more traditional expectations. Men were significantly more traditional than women on two of the five scores, Woman as Homemaker and Woman as Competitor.


1996 ◽  
Vol 5 (1) ◽  
pp. 90-96 ◽  
Author(s):  
Frank E. Musiek ◽  
Cynthia A. McCormick ◽  
Raymond M. Hurley

We performed a retrospective study of 26 patients with acoustic tumors and 26 patients with otologically diagnosed cochlear pathology to determine the sensitivity (hit rate), specificity (false-alarm rate), and efficiency of six auditory brainstem response indices. In addition, a utility value was determined for each of these six indices. The I–V interwave interval, the interaural latency difference, and the absolute latency of wave V provided the highest hit rates, the best A’ values and good utility. The V/I amplitude ratio index provided high specificity but low sensitivity scores. In regard to sensitivity and specificity, using the combination of two indices provided little overall improvement over the best one-index measures.


Sign in / Sign up

Export Citation Format

Share Document