Compensating for Type-I Errors in Video Quality Assessment

Kjell Brunnström; Samira Tavakoli; Jacob Søgaard

doi:10.1109/QoMEX.2015.7148080

Compensating for Type-I Errors in Video Quality Assessment

Kjell Brunnström
, Samira Tavakoli
, Jacob Søgaard

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

This paper analyzes the impact on compensating for Type-I errors in video quality assessment. A Type-I error is to incorrectly conclude that there is an effect. The risk increases with the number of comparisons that are performed in statistical tests. Type-I errors are an issue often neglected in Quality of Experience and video quality assessment analysis. Examples are given for the analysis of subjective experiments and the evaluation of objective metrics by correlation.

Original language	English
Title of host publication	Proceedings of IEEE QoMEX 2015.
Number of pages	2
Publisher	IEEE
Publication date	2015
DOIs	https://doi.org/10.1109/QoMEX.2015.7148080
Publication status	Published - 2015
Event	7th International Workshop on Quality of Multimedia Experience - Costa Navarino, Messinia, Greece Duration: 26 May 2015 → 29 May 2015

Conference

Conference	7th International Workshop on Quality of Multimedia Experience
Location	Costa Navarino
Country/Territory	Greece
City	Messinia
Period	26/05/2015 → 29/05/2015

Keywords

Type-I error
Video quality
Statistical significance
Student T-test
Bonferroni

Access to Document

10.1109/QoMEX.2015.7148080

OpenUrl availability

Full text

Cite this

@inproceedings{82baf85c1b3e4e68bb7db5f0e9c8f733,

title = "Compensating for Type-I Errors in Video Quality Assessment",

abstract = "This paper analyzes the impact on compensating for Type-I errors in video quality assessment. A Type-I error is to incorrectly conclude that there is an effect. The risk increases with the number of comparisons that are performed in statistical tests. Type-I errors are an issue often neglected in Quality of Experience and video quality assessment analysis. Examples are given for the analysis of subjective experiments and the evaluation of objective metrics by correlation.",

keywords = "Type-I error, Video quality, Statistical significance, Student T-test, Bonferroni",

author = "Kjell Brunnstr{\"o}m and Samira Tavakoli and Jacob S{\o}gaard",

year = "2015",

doi = "10.1109/QoMEX.2015.7148080",

language = "English",

booktitle = "Proceedings of IEEE QoMEX 2015.",

publisher = "IEEE",

address = "United States",

note = "7th International Workshop on Quality of Multimedia Experience, QoMEX 2015 ; Conference date: 26-05-2015 Through 29-05-2015",

}

TY - GEN

T1 - Compensating for Type-I Errors in Video Quality Assessment

AU - Brunnström, Kjell

AU - Tavakoli, Samira

AU - Søgaard, Jacob

PY - 2015

Y1 - 2015

N2 - This paper analyzes the impact on compensating for Type-I errors in video quality assessment. A Type-I error is to incorrectly conclude that there is an effect. The risk increases with the number of comparisons that are performed in statistical tests. Type-I errors are an issue often neglected in Quality of Experience and video quality assessment analysis. Examples are given for the analysis of subjective experiments and the evaluation of objective metrics by correlation.

AB - This paper analyzes the impact on compensating for Type-I errors in video quality assessment. A Type-I error is to incorrectly conclude that there is an effect. The risk increases with the number of comparisons that are performed in statistical tests. Type-I errors are an issue often neglected in Quality of Experience and video quality assessment analysis. Examples are given for the analysis of subjective experiments and the evaluation of objective metrics by correlation.

KW - Type-I error

KW - Video quality

KW - Statistical significance

KW - Student T-test

KW - Bonferroni

U2 - 10.1109/QoMEX.2015.7148080

DO - 10.1109/QoMEX.2015.7148080

M3 - Article in proceedings

BT - Proceedings of IEEE QoMEX 2015.

PB - IEEE

T2 - 7th International Workshop on Quality of Multimedia Experience

Y2 - 26 May 2015 through 29 May 2015

ER -

Compensating for Type-I Errors in Video Quality Assessment

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this