Optimized segmented regression models for the transition period of intervention effects

Table 1 \(L\) selected results for four distribution patterns of intervention effect

Method	L	MSE	R²	F	P	EEV
CSR	0	498.4159	0.8015	140.0032	< 0.001	517.5858
OSR-UD	8	408.5852	0.8373	178.4058	< 0.001	424.3000
OSR-ND	5	425.0226	0.8308	170.1654	< 0.001	441.3696
OSR-LND	10	421.5121	0.8322	171.8713	< 0.001	437.7241
OSR-LNFD	3	423.4491	0.8314	170.9266	< 0.001	439.7356

UD: uniform distribution; ND: normal distribution; LND: log-normal distribution; LNFD: log-normal flip distribution. MSE: mean square error. \({R}^{2}\), \(F\), \(P\), and EEV are the model statistics. \({R}^{2}\) is the coefficient of determination and indicates the model's goodness of fit. The \(F\) is the test statistic of the F-test in the regression model, and \(P\) is the corresponding p-value. EEV: estimate of error variance

ISSN: 2397-0642