Air quality monitoring is essential for evaluating environmental
conditions and protecting public health.
This analysis compares nitrogen dioxide (NO₂) concentrations recorded at
the Regina monitoring station with measurements from the National Air
Pollution Surveillance (NAPS) network.
The objective is to determine whether the two monitoring systems demonstrate sufficient agreement to be considered comparable.
The figure below illustrates monthly averaged NO₂ concentrations for both monitoring stations, enabling visual comparison of long-term patterns.
A scatter plot was generated to evaluate the relationship between the
two monitors.
Points clustering near the 1:1 line indicate strong agreement.
Key statistical metrics were calculated to quantify monitor agreement.
| Metric | Value |
|---|---|
| Correlation | 0.459 |
| Bias | 0.004 |
| RMSE | 8.115 |
| Nash–Sutcliffe Efficiency | -0.071 |
Linear regression was used to further assess the strength of the relationship between measurements.
##
## Call:
## lm(formula = Regina ~ NAPS, data = paired)
##
## Residuals:
## Min 1Q Median 3Q Max
## -45.956 -4.124 -1.605 2.510 107.967
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.577342 0.025704 217.0 <2e-16 ***
## NAPS 0.454676 0.001995 227.9 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.897 on 194314 degrees of freedom
## Multiple R-squared: 0.2109, Adjusted R-squared: 0.2109
## F-statistic: 5.192e+04 on 1 and 194314 DF, p-value: < 2.2e-16
The Bland–Altman plot provides insight into measurement bias and limits of agreement between monitors.
This analysis evaluated agreement between the Regina and NAPS
monitoring stations using graphical and statistical techniques.
Correlation, bias, RMSE, regression, and Bland–Altman analysis
collectively provide a comprehensive assessment of monitor
comparability.