/* NIST/ITL StRD Dataset Name: BoxBOD (BoxBOD.dat) File Format: ASCII Starting Values (lines 41 to 42) Certified Values (lines 41 to 47) Data (lines 61 to 66) Procedure: Nonlinear Least Squares Regression Description: These data are described in detail in Box, Hunter and Hunter (1978). The response variable is biochemical oxygen demand (BOD) in mg/l, and the predictor variable is incubation time in days. Reference: Box, G. P., W. G. Hunter, and J. S. Hunter (1978). Statistics for Experimenters. New York, NY: Wiley, pp. 483-487. Data: 1 Response (y = biochemical oxygen demand) 1 Predictor (x = incubation time) 6 Observations Higher Level of Difficulty Observed Data Model: Exponential Class 2 Parameters (b1 and b2) y = b1*(1-exp[-b2*x]) + e Starting values Certified Values Start 1 Start 2 Parameter Standard Deviation b1 = 1 100 2.1380940889E+02 1.2354515176E+01 b2 = 1 0.75 5.4723748542E-01 1.0455993237E-01 Residual Sum of Squares: 1.1680088766E+03 Residual Standard Deviation: 1.7088072423E+01 Degrees of Freedom: 4 Number of Observations: 6 */ clear scalar N = 6 scalar df_r = 4 scalar df_m = 2 scalar rss = 1.1680088766E+03 scalar rmse = 1.7088072423E+01 scalar b1 = 2.1380940889E+02 scalar seb1 = 1.2354515176E+01 scalar b2 = 5.4723748542E-01 scalar seb2 = 1.0455993237E-01 qui input double(y x) 109 1 149 2 149 3 191 5 213 7 224 10 end nl ( y = {b1}*(1-exp(-{b2}*x)) ), init(b1 1 b2 1) eps(1e-10) assert N == e(N) assert df_r == e(df_r) assert df_m == e(df_m) lrecomp [b1]_b[_cons] b1 [b2]_b[_cons] b2 () /* */ [b1]_se[_cons] seb1 [b2]_se[_cons] seb2 () /* */ e(rmse) rmse e(rss) rss