Alternative adjustment for seasonality and long-term time-trend in time-series analysis for long-term environmental exposures and disease counts

Table 1 Residual variance of one-year moving average of PM₁₀ concentration in Seoul, South Korea, 2002–2013

Adjustment method for seasonality and long-term time-trend	Residual variance	R² (%)
Not adjusted	71.080
NCS(t,10df/year)	0.185	99.7
NCS(t,4df/year)	0.505	99.3
NCS(t,1.5df/year)	1.029	98.6
NCS(doy,10df)+I(year)+NCS(week,20df)+NCS(month,20df)	0.675	99.1
NCS(doy,10df)+I(year)+NCS(week,5df)+NCS(month,5df)	2.088	97.1
NCS(doy,10df)+I(year)	2.417	96.6

Abbreviations: df degrees of freedom, doy day of the year, I(year) an indicator function of year throughout the study period, NCS natural cubic spline, NCS(doy,pdf) NCS of doy with pdf, NCS(month,pdf) NCS of the order of month throughout the study period with pdf, NCS(t,pdf/year) NCS of time throughout the study period with pdf per year, NCS(week,pdf) NCS of the order of week throughout the study period with pdf, PM₁₀ particulate matter with aerodynamic diameter ≤10 μm

ISSN: 1471-2288