Optimal trimming proportion in regression analysis for non-normal distributions

2021 ◽  
pp. 1-12
Author(s):  
Amitava Mitra ◽  
Pankush Kalgotra
Keyword(s):  
Regression Analysis ◽  
Normal Distributions

Generalized Linear Models

2021 ◽  
pp. 195-208
Author(s):  
Andy Hector
Keyword(s):  
Regression Analysis ◽  
Maximum Likelihood ◽  
Generalized Linear Models ◽  
Linear Models ◽  
Square Root ◽  
Link Function ◽  
Data Transformations ◽  
Normal Distributions ◽  
Equal Variance ◽  
The Mean

This chapter revisits a regression analysis to explore the normal least squares assumption of approximately equal variance. It also considers some of the data transformations that can be used to achieve this. A linear regression of transformed data is compared with a generalized linear-model equivalent that avoids transformation by using a link function and non-normal distributions. Generalized linear models based on maximum likelihood use a link function to model the mean (in this case a square-root link) and a variance function to model the variability (in this case the gamma distribution, where the variance increases as the square of the mean). The Box–Cox family of transformations is explained in detail.

Regression Analysis of Count Data

1998 ◽  
Author(s):  
A. Colin Cameron ◽  
Pravin K. Trivedi
Keyword(s):  
Regression Analysis ◽  
Count Data

Poor Acceptance of the Past is Related to Depressive Symptoms in Older Adults

GeroPsych ◽  
2020 ◽  
Vol 33 (4) ◽  
pp. 246-251
Author(s):  
Gozde Cetinkol ◽  
Gulbahar Bastug ◽  
E. Tugba Ozel Kizil
Keyword(s):  
Older Adults ◽  
Regression Analysis ◽  
Depressive Symptoms ◽  
Death Anxiety ◽  
Geriatric Depression ◽  
Ego Integrity ◽  
The Past ◽  
Depressed Group ◽  
Total Death ◽  
The Relationship

Abstract. Depression in older adults can be explained by Erikson’s theory on the conflict of ego integrity versus hopelessness. The study investigated the relationship between past acceptance, hopelessness, death anxiety, and depressive symptoms in 100 older (≥50 years) adults. The total Beck Hopelessness (BHS), Geriatric Depression (GDS), and Accepting the Past (ACPAST) subscale scores of the depressed group were higher, while the total Death Anxiety (DAS) and Reminiscing the Past (REM) subscale scores of both groups were similar. A regression analysis revealed that the BHS, DAS, and ACPAST predicted the GDS. Past acceptance seems to be important for ego integrity in older adults.

Measures of RSA Suppression, Attentional Control, and Negative Affect Predict Self-Ratings of Executive Functions

2011 ◽  
Vol 25 (4) ◽  
pp. 164-173 ◽  
Author(s):  
Brian Healy ◽  
Aaron Treadwell ◽  
Mandy Reagan
Keyword(s):  
College Students ◽  
Heart Rate ◽  
Regression Analysis ◽  
Individual Differences ◽  
Negative Affect ◽  
Respiratory Sinus Arrhythmia ◽  
Attentional Control ◽  
Executive Processes ◽  
Sinus Arrhythmia ◽  
Low Levels

The current study was an attempt to determine the degree to which the suppression of respiratory sinus arrhythmia (RSA) and attentional control were influential in the ability to engage various executive processes under high and low levels of negative affect. Ninety-four college students completed the Stroop Test while heart rate was being recorded. Estimates of the suppression of RSA were calculated from each participant in response to this test. The participants then completed self-ratings of attentional control, negative affect, and executive functioning. Regression analysis indicated that individual differences in estimates of the suppression of RSA, and ratings of attentional control were associated with the ability to employ executive processes but only when self-ratings of negative affect were low. An increase in negative affect compromised the ability to employ these strategies in the majority of participants. The data also suggest that high attentional control in conjunction with attenuated estimates of RSA suppression may increase the ability to use executive processes as negative affect increases.

Power, Conflict, and Effectiveness

2000 ◽  
Vol 5 (1) ◽  
pp. 28-33 ◽  
Author(s):  
M. Afzalur Rahim ◽  
David Antonioni ◽  
Krum Krumov ◽  
Snejana Ilieva
Keyword(s):  
United States ◽  
Regression Analysis ◽  
Interpersonal Conflict ◽  
The United States ◽  
Hierarchical Regression ◽  
Hierarchical Regression Analysis ◽  
Referent Power ◽  
Legitimate Power ◽  
Power Base ◽  
Effectiveness Data

This study investigated the relationships of bases of leader power (coercive, reward, legitimate, expert, and referent) and styles of handling interpersonal conflict (integrating, obliging, dominating, avoiding, and compromising) to subordinates' effectiveness. Data for this study were collected with questionnaires from the United States and Bulgaria and analyzed with hierarchical regression analysis for each country. Results indicated that in the United States referent power base of supervisors and integrating style of handling conflict of subordinates were positively associated with effectiveness. In Bulgaria, legitimate power base of supervisors was positively associated with effectiveness, but the subordinates' conflict styles were not associated with effectiveness.

Normal Distributions

1989 ◽  
Author(s):  
Teresa M. Amabile
Keyword(s):  
Normal Distributions

Plasma Levels of Protein S, Protein C, and Factor X: Effects of Sex, Hormonal State and Age

1995 ◽  
Vol 74 (05) ◽  
pp. 1271-1275 ◽  
Author(s):  
C M A Henkens ◽  
V J J Bom ◽  
W van der Schaaf ◽  
P M Pelsma ◽  
C Th Smit Sibinga ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Postmenopausal Women ◽  
Protein C ◽  
Blood Donors ◽  
Premenopausal Women ◽  
Protein S ◽  
The Other ◽  
Factor X ◽  
Normal Ranges

SummaryWe measured total and free protein S (PS), protein C (PC) and factor X (FX) in 393 healthy blood donors to assess differences in relation to sex, hormonal state and age. All measured proteins were lower in women as compared to men, as were levels in premenopausal women as compared to postmenopausal women. Multiple regression analysis showed that both age and subgroup (men, pre- and postmenopausal women) were of significance for the levels of total and free PS and PC, the subgroup effect being caused by the differences between the premenopausal women and the other groups. This indicates a role of sex-hormones, most likely estrogens, in the regulation of levels of pro- and anticoagulant factors under physiologic conditions. These differences should be taken into account in daily clinical practice and may necessitate different normal ranges for men, pre- and postmenopausal women.

Sign in / Sign up

Export Citation Format

Share Document