1990
DOI: 10.1007/978-3-662-25092-1
|View full text |Cite
|
Sign up to set email alerts
|

Regression Analysis

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
92
1
2

Year Published

2001
2001
2022
2022

Publication Types

Select...
10

Relationship

0
10

Authors

Journals

citations
Cited by 114 publications
(95 citation statements)
references
References 47 publications
0
92
1
2
Order By: Relevance
“…See Sen & Srivastava (1990) and Christensen (1996). To avoid the problem, two things can help us, first by taking into account the bound intervals for the parameters which causes the model to converge quickly.…”
Section: Nonlinear Regression Of the Radial Velocity-acceleration Curvementioning
confidence: 99%
“…See Sen & Srivastava (1990) and Christensen (1996). To avoid the problem, two things can help us, first by taking into account the bound intervals for the parameters which causes the model to converge quickly.…”
Section: Nonlinear Regression Of the Radial Velocity-acceleration Curvementioning
confidence: 99%
“…Furthermore, the correlation coefficients were used to identify pairs of chemical constituents that were strongly associated with one another such that only one of the pairs of variables would be used in regression modeling; this analysis was done to avoid the problem of multicollinearity (i.e., independent variables that are closely related to each other) because this may bias estimates of regression parameters. 48 The contribution of various sources of personal exposure to PM 2.5 was investigated with univariate regression models and a mixed-effects model. Univariate regression models, with personal exposures modeled as the dependent variable and outdoor measurements as the independent variable, were constructed for each individual to separate the contribution of outdoor and nonoutdoor sources to total PM 2.5 exposures.…”
Section: Quality Assurancementioning
confidence: 99%
“…The F statistic is then used to compute the probability value p 1 that the regression coefficient β 1 (the slope of the regression line) is equal to zero: if p 1 is less than the selected level of significance α 1 , the null hypothesis of no correlation (H 0 : β 1 = 0) is rejected and we accept that there is a significant linear relationship between the two variables; conversely, if p 1 > α 1 the null hypothesis cannot be rejected and we conclude that the two variables are not linearly correlated. Obviously, the absence of a linear correlation does not imply that the displacements are randomly distributed with time because the time series could be described by a higher order model (Draper and Smith, 1981;Sen and Srivastava, 1990). Based on our experience, however, a time series with an average slope close to zero (β 1 ≈ 0) typically indicates a stable PS with no appreciable movements.…”
Section: (A) Linear Regressionmentioning
confidence: 95%