Comparison of data analysis procedures for real-time nanoparticle sampling data using classical regression and ARIMA models

Seunghon Ham, Sunju Kim, Naroo Lee, Pilje Kim, Igchun Eom, Byoungcheun Lee, Peng-Chi Tsai, Kiyoung Lee, Chungsik Yoon

Research output: Contribution to journalArticle

Abstract

Real-time monitoring is necessary for nanoparticle exposure assessment to characterize the exposure profile, but the data produced are autocorrelated. This study was conducted to compare three statistical methods used to analyze data, which constitute autocorrelated time series, and to investigate the effect of averaging time on the reduction of the autocorrelation using field data. First-order autoregressive (AR(1)) and autoregressive-integrated moving average (ARIMA) models are alternative methods that remove autocorrelation. The classical regression method was compared with AR(1) and ARIMA. Three data sets were used. Scanning mobility particle sizer data were used. We compared the results of regression, AR(1), and ARIMA with averaging times of 1, 5, and 10 min. AR(1) and ARIMA models had similar capacities to adjust autocorrelation of real-time data. Because of the non-stationary of real-time monitoring data, the ARIMA was more appropriate. When using the AR(1), transformation into stationary data was necessary. There was no difference with a longer averaging time. This study suggests that the ARIMA model could be used to process real-time monitoring data especially for non-stationary data, and averaging time setting is flexible depending on the data interval required to capture the effects of processes for occupational and environmental nano measurements.

Original languageEnglish
Pages (from-to)685-699
Number of pages15
JournalJournal of Applied Statistics
Volume44
Issue number4
DOIs
Publication statusPublished - 2017 Mar 12

Fingerprint

Moving Average Model
Integrated Model
Nanoparticles
Data analysis
Regression
Real-time
Averaging
Moving Average
Autocorrelation
Integrated
Moving average
Sampling
Monitoring
Interval Data
Necessary
Process Monitoring
Statistical method
Scanning
Time series
First-order

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Ham, Seunghon ; Kim, Sunju ; Lee, Naroo ; Kim, Pilje ; Eom, Igchun ; Lee, Byoungcheun ; Tsai, Peng-Chi ; Lee, Kiyoung ; Yoon, Chungsik. / Comparison of data analysis procedures for real-time nanoparticle sampling data using classical regression and ARIMA models. In: Journal of Applied Statistics. 2017 ; Vol. 44, No. 4. pp. 685-699.
@article{414d4cf8d34c4dbf98f991c22e84a69b,
title = "Comparison of data analysis procedures for real-time nanoparticle sampling data using classical regression and ARIMA models",
abstract = "Real-time monitoring is necessary for nanoparticle exposure assessment to characterize the exposure profile, but the data produced are autocorrelated. This study was conducted to compare three statistical methods used to analyze data, which constitute autocorrelated time series, and to investigate the effect of averaging time on the reduction of the autocorrelation using field data. First-order autoregressive (AR(1)) and autoregressive-integrated moving average (ARIMA) models are alternative methods that remove autocorrelation. The classical regression method was compared with AR(1) and ARIMA. Three data sets were used. Scanning mobility particle sizer data were used. We compared the results of regression, AR(1), and ARIMA with averaging times of 1, 5, and 10 min. AR(1) and ARIMA models had similar capacities to adjust autocorrelation of real-time data. Because of the non-stationary of real-time monitoring data, the ARIMA was more appropriate. When using the AR(1), transformation into stationary data was necessary. There was no difference with a longer averaging time. This study suggests that the ARIMA model could be used to process real-time monitoring data especially for non-stationary data, and averaging time setting is flexible depending on the data interval required to capture the effects of processes for occupational and environmental nano measurements.",
author = "Seunghon Ham and Sunju Kim and Naroo Lee and Pilje Kim and Igchun Eom and Byoungcheun Lee and Peng-Chi Tsai and Kiyoung Lee and Chungsik Yoon",
year = "2017",
month = "3",
day = "12",
doi = "10.1080/02664763.2016.1182132",
language = "English",
volume = "44",
pages = "685--699",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "4",

}

Comparison of data analysis procedures for real-time nanoparticle sampling data using classical regression and ARIMA models. / Ham, Seunghon; Kim, Sunju; Lee, Naroo; Kim, Pilje; Eom, Igchun; Lee, Byoungcheun; Tsai, Peng-Chi; Lee, Kiyoung; Yoon, Chungsik.

In: Journal of Applied Statistics, Vol. 44, No. 4, 12.03.2017, p. 685-699.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Comparison of data analysis procedures for real-time nanoparticle sampling data using classical regression and ARIMA models

AU - Ham, Seunghon

AU - Kim, Sunju

AU - Lee, Naroo

AU - Kim, Pilje

AU - Eom, Igchun

AU - Lee, Byoungcheun

AU - Tsai, Peng-Chi

AU - Lee, Kiyoung

AU - Yoon, Chungsik

PY - 2017/3/12

Y1 - 2017/3/12

N2 - Real-time monitoring is necessary for nanoparticle exposure assessment to characterize the exposure profile, but the data produced are autocorrelated. This study was conducted to compare three statistical methods used to analyze data, which constitute autocorrelated time series, and to investigate the effect of averaging time on the reduction of the autocorrelation using field data. First-order autoregressive (AR(1)) and autoregressive-integrated moving average (ARIMA) models are alternative methods that remove autocorrelation. The classical regression method was compared with AR(1) and ARIMA. Three data sets were used. Scanning mobility particle sizer data were used. We compared the results of regression, AR(1), and ARIMA with averaging times of 1, 5, and 10 min. AR(1) and ARIMA models had similar capacities to adjust autocorrelation of real-time data. Because of the non-stationary of real-time monitoring data, the ARIMA was more appropriate. When using the AR(1), transformation into stationary data was necessary. There was no difference with a longer averaging time. This study suggests that the ARIMA model could be used to process real-time monitoring data especially for non-stationary data, and averaging time setting is flexible depending on the data interval required to capture the effects of processes for occupational and environmental nano measurements.

AB - Real-time monitoring is necessary for nanoparticle exposure assessment to characterize the exposure profile, but the data produced are autocorrelated. This study was conducted to compare three statistical methods used to analyze data, which constitute autocorrelated time series, and to investigate the effect of averaging time on the reduction of the autocorrelation using field data. First-order autoregressive (AR(1)) and autoregressive-integrated moving average (ARIMA) models are alternative methods that remove autocorrelation. The classical regression method was compared with AR(1) and ARIMA. Three data sets were used. Scanning mobility particle sizer data were used. We compared the results of regression, AR(1), and ARIMA with averaging times of 1, 5, and 10 min. AR(1) and ARIMA models had similar capacities to adjust autocorrelation of real-time data. Because of the non-stationary of real-time monitoring data, the ARIMA was more appropriate. When using the AR(1), transformation into stationary data was necessary. There was no difference with a longer averaging time. This study suggests that the ARIMA model could be used to process real-time monitoring data especially for non-stationary data, and averaging time setting is flexible depending on the data interval required to capture the effects of processes for occupational and environmental nano measurements.

UR - http://www.scopus.com/inward/record.url?scp=84966714424&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966714424&partnerID=8YFLogxK

U2 - 10.1080/02664763.2016.1182132

DO - 10.1080/02664763.2016.1182132

M3 - Article

VL - 44

SP - 685

EP - 699

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 4

ER -