2014
DOI: 10.7763/lnse.2014.v2.92
|View full text |Cite
|
Sign up to set email alerts
|

Statistical Software and Regression Diagnostic Reporting with Fuzzy-AHP Intelligent Zax (FAIZ)

Abstract: Abstract-Most statistical Software do efficient regression reporting. This reporting is based on multiple criteria and uses multiple fragmented diagnostic tables. In this study Fuzzy AHP Intelligent Zax (FAIZ) has been proposed which can be incorporated in statistical software as a scoring technique for ranking the simple linear regressions (SLR) based on fuzzy Analytical Hierarchy Process (AHP) logic to push 'Further Evolution' in Software Engineering Evolution process for Statistical Software. This approach … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
4
2

Relationship

3
3

Authors

Journals

citations
Cited by 6 publications
(2 citation statements)
references
References 10 publications
0
2
0
Order By: Relevance
“…The study has shown that for any prediction problem, it is always a wise strategy to use attribute selection algorithms before using the dataset in prediction, classification or forecasting algorithms or in regressions because of its demonstrated potential in saving time and efforts spent which may have otherwise been wasted either on plotting hundreds of variables against each other or on doing unnecessary juggling with running regressions in a traditional trial and error fashion in order to arrive at the best selection of variables and/or results. All this in turn reduces the excuses for regressioneering (Anjum 2014a) or regressgineering 2014c) and thus makes the completely analytical or experimental exercise more scientific as well as legitimate one.…”
Section: Discussionmentioning
confidence: 99%
“…The study has shown that for any prediction problem, it is always a wise strategy to use attribute selection algorithms before using the dataset in prediction, classification or forecasting algorithms or in regressions because of its demonstrated potential in saving time and efforts spent which may have otherwise been wasted either on plotting hundreds of variables against each other or on doing unnecessary juggling with running regressions in a traditional trial and error fashion in order to arrive at the best selection of variables and/or results. All this in turn reduces the excuses for regressioneering (Anjum 2014a) or regressgineering 2014c) and thus makes the completely analytical or experimental exercise more scientific as well as legitimate one.…”
Section: Discussionmentioning
confidence: 99%
“…Whereas, for the econometric analysis, multiple linear regression models has been used to analyse the data. The selection of these techniques have been made after reviewing vast variety of techniques from literature including stepwise linear function technique [5], logistic regression [8][9], variables ranking methodologies [10][11][12][13], mathematical rationale for regulatory variables [14], multi-criteria decision making methodologies [15], advanced econometric analysis [6,16] data mining based logic [17][18] and fuzzy based multi-criteria decision making methodologies [15,19] Cronbach's alpha is used to measure reliability. A reliability coefficient of .70 or higher is considered acceptable and a high level for alpha means that items in the test are highly correlated [20].…”
Section: Methods Of Data Analysismentioning
confidence: 99%