2015
DOI: 10.12983/ijsrk-2015-p0220-0226
|View full text |Cite
|
Sign up to set email alerts
|

Outlier Detection and Missing Value in Time Series Ozone Data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
2
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(5 citation statements)
references
References 14 publications
0
2
0
Order By: Relevance
“…First, the data were screened to detect any multivariate outliers; here, we calculated the Mahalanobis distance, the leverage, and the Cook's distance of the predicted variables (Kaliyaperumal & Kuppusamy, 2015;Rousseeuw & Zomeren, 1990). Next, we tested our data for the normality distribution assumptions and found that these were consistent.…”
Section: Discussionmentioning
confidence: 99%
“…First, the data were screened to detect any multivariate outliers; here, we calculated the Mahalanobis distance, the leverage, and the Cook's distance of the predicted variables (Kaliyaperumal & Kuppusamy, 2015;Rousseeuw & Zomeren, 1990). Next, we tested our data for the normality distribution assumptions and found that these were consistent.…”
Section: Discussionmentioning
confidence: 99%
“…Eliminating outliers and data control techniques applied in this study: Turkish Method (boxplot) is used to visually show the distribution of numerical data and variability by displaying data quartiles (or percentiles) and means. A value may be considered as an outlier if it was higher than the upper fence (Uf) or lower than the lower fence (Lf) (Kaliyaperumal et al, 2015).…”
Section: Methodsmentioning
confidence: 99%
“…In the second stage, total and standardised Z scores were calculated according to the scales. According to the z score, participants who were outside the [-3,+3] range were determined as outliers (Kaliyaperumal et al, 2015). According to the Z scores, 519 observations outside this range were identified as outliers and deleted from the data.…”
Section: Th Grade Levelmentioning
confidence: 99%
“…In this data, 685 participants who responded carelessly were identified and removed from the sample (Kam & Meyer, 2015). Since there was no value outside the range of [-3,+3] according to Z scores, it was decided that there was no outlier (Kaliyaperumal et al , 2015). The fact that the kurtosis and skewness coefficients are in the range of [-1.5,+1.5] indicates that the data are normally distributed (Tabachnick & Fidell, 2013).…”
Section: Th Grade Levelmentioning
confidence: 99%