Wheat relative yield response - replicate normalisation
Jan C Greyling
01/03/2020
Prepare the data
dat <- fread("Output/wheat_data_prepped.csv")
#fix rotation
dat[!is.na(yldb), yld := yldb]
#drop all blank yields and biomass estimates
dat <- dat[!is.na(yld)]
dat[, c("wind","yldb") := NULL]
# Max yield index ---------------------------------------------------------
dat[, yld_max := max(yld,na.rm = T), by = .(year,local,rotation,rep)]
#keep original yield
dat[, yld.OR := yld]
#calculate control normalised yield
dat[, yld := yld/yld_max*100]
fwrite(dat,"Output/data_final.csv")Model results
Langgewens
Canola-Wheat
Langgewens Canola-Wheat results, 2018 was excluded due to wind damage.
| Year | ||||
| Relative yield (Max rep yield = 100) | ||||
| 2016 | 2017 | 2018 | 2019 | |
| (1) | (2) | (3) | (4) | |
| Total Nitrogen Applied | 0.297*** | -0.084 | 0.313*** | 0.117 |
| (0.076) | (0.098) | (0.103) | (0.098) | |
| Total Nitrogen Applied squared | -0.001*** | 0.0002 | -0.001*** | -0.001 |
| (0.0003) | (0.0004) | (0.0004) | (0.0004) | |
| Intercept | 65.924*** | 87.723*** | 62.413*** | 76.679*** |
| (3.843) | (4.888) | (5.198) | (4.547) | |
| Observations | 61 | 62 | 61 | 61 |
| R2 | 0.332 | 0.062 | 0.146 | 0.025 |
| Adjusted R2 | 0.309 | 0.030 | 0.117 | -0.009 |
| Residual Std. Error | 8.168 (df = 58) | 10.850 (df = 59) | 11.006 (df = 58) | 11.700 (df = 58) |
| F Statistic | 14.427*** (df = 2; 58) | 1.933 (df = 2; 59) | 4.969** (df = 2; 58) | 0.739 (df = 2; 58) |
| Note: | p<0.1; p<0.05; p<0.01 | |||
It is evident that only 2016 has a good fit.
grid.arrange(p.seg.2016.Langgewens.CW,p.seg.2018.Langgewens.CW,p.seg.2019.Langgewens.CW, nrow =2)
summary.segmented(m.seg.2016.Langgewens.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 79.203 19.375
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 66.59237 4.46910 14.901 < 2e-16 ***
## N_tot 0.25152 0.09044 2.781 0.00726 **
## U1.N_tot -0.23813 0.09701 -2.455 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.044 on 59 degrees of freedom
## Multiple R-Squared: 0.2931, Adjusted R-squared: 0.2571
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2016.Langgewens.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.251520 0.090443 2.78100 0.070545 0.432500
## slope2 0.013396 0.035073 0.38195 -0.056785 0.083577summary.segmented(m.seg.2018.Langgewens.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 50.613 7.465
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 48.4163 7.7892 6.216 5.34e-08 ***
## N_tot 0.7040 0.2237 3.147 0.00257 **
## U1.N_tot -0.7964 0.2262 -3.521 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.18 on 60 degrees of freedom
## Multiple R-Squared: 0.2465, Adjusted R-squared: 0.2088
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2018.Langgewens.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.704050 0.223690 3.1474 0.25660 1.151500
## slope2 -0.092338 0.033556 -2.7518 -0.15946 -0.025217summary.segmented(m.seg.2019.Langgewens.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 75 28.091
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 72.5325 4.9404 14.682 <2e-16 ***
## N_tot 0.1718 0.1184 1.452 0.152
## U1.N_tot -0.2378 0.1283 -1.854 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 13.18 on 60 degrees of freedom
## Multiple R-Squared: 0.06892, Adjusted R-squared: 0.02237
##
## Convergence attained in 1 iter. (rel. change 2.2691e-09)slope(m.seg.2019.Langgewens.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.171840 0.118380 1.4516 -0.064956 0.408640
## slope2 -0.065937 0.049347 -1.3362 -0.164650 0.032772Medics-Wheat
Langgewens Medics-Wheat results, 2018 was excluded due to wind damage.
| Year | ||||
| Relative yield (Max rep yield = 100) | ||||
| 2016 | 2017 | 2018 | 2019 | |
| (1) | (2) | (3) | (4) | |
| Total Nitrogen Applied | 0.216*** | -0.092 | -0.169* | -0.238** |
| (0.081) | (0.115) | (0.098) | (0.108) | |
| Total Nitrogen Applied squared | -0.001*** | 0.0004 | 0.0004 | 0.001** |
| (0.0003) | (0.0005) | (0.0004) | (0.001) | |
| Intercept | 77.308*** | 82.239*** | 91.842*** | 89.795*** |
| (4.134) | (5.787) | (4.696) | (4.868) | |
| Observations | 60 | 60 | 61 | 61 |
| R2 | 0.119 | 0.011 | 0.155 | 0.077 |
| Adjusted R2 | 0.088 | -0.023 | 0.126 | 0.045 |
| Residual Std. Error | 8.305 (df = 57) | 12.187 (df = 57) | 10.753 (df = 58) | 13.374 (df = 58) |
| F Statistic | 3.835** (df = 2; 57) | 0.328 (df = 2; 57) | 5.315*** (df = 2; 58) | 2.427* (df = 2; 58) |
| Note: | p<0.1; p<0.05; p<0.01 | |||
It is evident that only 2016 has a good fit.
p.seg.2016.Langgewens.MW
summary.segmented(m.seg.2016.Langgewens.MW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 79.405 16.371
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 73.93784 4.72547 15.647 <2e-16 ***
## N_tot 0.22592 0.09563 2.362 0.0214 *
## U1.N_tot -0.29851 0.10248 -2.913 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.563 on 60 degrees of freedom
## Multiple R-Squared: 0.1495, Adjusted R-squared: 0.107
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2016.Langgewens.MW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.225920 0.095632 2.3624 0.03463 0.4172100
## slope2 -0.072583 0.036847 -1.9699 -0.14629 0.0011216Darling
Canola-Wheat
Darling Canola-Wheat results
| Year | |||
| Relative yield (Max rep yield = 100) | |||
| 2016 | 2017 | 2018 | |
| (1) | (2) | (3) | |
| Total Nitrogen Applied | 0.652*** | -0.118 | 0.298*** |
| (0.156) | (0.135) | (0.094) | |
| Total Nitrogen Applied squared | -0.002*** | -0.0002 | -0.001** |
| (0.001) | (0.001) | (0.0004) | |
| Intercept | 22.862*** | 89.759*** | 65.750*** |
| (7.699) | (6.561) | (4.793) | |
| Observations | 62 | 59 | 61 |
| R2 | 0.418 | 0.327 | 0.198 |
| Adjusted R2 | 0.399 | 0.303 | 0.170 |
| Residual Std. Error | 17.671 (df = 59) | 14.335 (df = 56) | 10.068 (df = 58) |
| F Statistic | 21.228*** (df = 2; 59) | 13.591*** (df = 2; 56) | 7.163*** (df = 2; 58) |
| Note: | p<0.1; p<0.05; p<0.01 | ||
It is evident that only 2016 has a good fit.
p.seg.2018.Darling.CW
summary.segmented(m.seg.2018.Darling.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 120.001 28.696
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 69.45336 4.70693 14.756 <2e-16 ***
## N_tot 0.15778 0.07362 2.143 0.0362 *
## U1.N_tot -0.21272 0.09584 -2.220 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.64 on 60 degrees of freedom
## Multiple R-Squared: 0.1648, Adjusted R-squared: 0.1231
##
## Convergence attained in 1 iter. (rel. change 6.7242e-07)slope(m.seg.2018.Darling.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.157780 0.073622 2.14310 0.010513 0.305050
## slope2 -0.054945 0.061352 -0.89557 -0.177670 0.067777Medics-Wheat
Darling Medics-Wheat results
| Year | ||
| Relative yield (Max rep yield = 100) | ||
| 2016 | 2017 | |
| (1) | (2) | |
| Total Nitrogen Applied | 0.702*** | -0.107 |
| (0.101) | (0.185) | |
| Total Nitrogen Applied squared | -0.002*** | 0.0005 |
| (0.0004) | (0.001) | |
| Intercept | 26.950*** | 68.693*** |
| (5.046) | (9.348) | |
| Observations | 63 | 58 |
| R2 | 0.706 | 0.006 |
| Adjusted R2 | 0.696 | -0.030 |
| Residual Std. Error | 11.245 (df = 60) | 18.601 (df = 55) |
| F Statistic | 72.002*** (df = 2; 60) | 0.174 (df = 2; 55) |
| Note: | p<0.1; p<0.05; p<0.01 | |
It is evident that only 2016 has a good fit.
p.seg.2016.Darling.MW
summary.segmented(m.seg.2016.Darling.MW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 74.838 9.258
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 21.1046 5.5718 3.788 0.000354 ***
## N_tot 0.7274 0.1128 6.451 2.15e-08 ***
## U1.N_tot -0.5989 0.1208 -4.956 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11.28 on 60 degrees of freedom
## Multiple R-Squared: 0.736, Adjusted R-squared: 0.7228
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2016.Darling.MW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.72736 0.112760 6.4505 0.50181 0.95291
## slope2 0.12846 0.043446 2.9566 0.04155 0.21536Porterville
Canola-Wheat
Porterville Canola-Wheat results
| Year | ||||
| Relative yield (Max rep yield = 100) | ||||
| 2016 | 2017 | 2018 | 2019 | |
| (1) | (2) | (3) | (4) | |
| Total Nitrogen Applied | 0.599*** | -0.145 | 0.373*** | 0.268** |
| (0.202) | (0.159) | (0.075) | (0.114) | |
| Total Nitrogen Applied squared | -0.002* | 0.0004 | -0.001*** | -0.001 |
| (0.001) | (0.001) | (0.0003) | (0.001) | |
| Intercept | 16.172 | 75.633*** | 53.334*** | 61.358*** |
| (9.738) | (7.810) | (3.774) | (5.168) | |
| Observations | 61 | 63 | 60 | 62 |
| R2 | 0.321 | 0.042 | 0.659 | 0.185 |
| Adjusted R2 | 0.297 | 0.010 | 0.647 | 0.157 |
| Residual Std. Error | 22.298 (df = 58) | 18.085 (df = 60) | 8.261 (df = 57) | 14.214 (df = 59) |
| F Statistic | 13.699*** (df = 2; 58) | 1.324 (df = 2; 60) | 55.053*** (df = 2; 57) | 6.687*** (df = 2; 59) |
| Note: | p<0.1; p<0.05; p<0.01 | |||
It is evident that only 2016 has a good fit.
grid.arrange(p.seg.2016.Porterville.CW, p.seg.2018.Porterville.CW,p.seg.2019.Porterville.CW, nrow =2)## Warning: Removed 4 rows containing missing values (geom_point).## Warning: Removed 8 rows containing missing values (geom_point).## Warning: Removed 3 rows containing missing values (geom_point).
summary.segmented(m.seg.2016.Porterville.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 148.883 18.363
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 21.8759 8.3233 2.628 0.01088 *
## N_tot 0.3670 0.1061 3.458 0.00101 **
## U1.N_tot -0.6569 0.2245 -2.927 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 23.73 on 60 degrees of freedom
## Multiple R-Squared: 0.2914, Adjusted R-squared: 0.256
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2016.Porterville.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.36698 0.10614 3.4576 0.15468 0.57928
## slope2 -0.28996 0.19777 -1.4661 -0.68556 0.10564summary.segmented(m.seg.2018.Porterville.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 47.841 10.612
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 46.0989 6.8541 6.726 7.33e-09 ***
## N_tot 0.5884 0.1968 2.989 0.00405 **
## U1.N_tot -0.4635 0.1990 -2.329 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 9.842 on 60 degrees of freedom
## Multiple R-Squared: 0.5636, Adjusted R-squared: 0.5418
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2018.Porterville.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.58842 0.196840 2.9893 0.194680 0.98216
## slope2 0.12487 0.029527 4.2291 0.065809 0.18394summary.segmented(m.seg.2019.Porterville.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 90.772 23.417
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 56.6834 5.3683 10.559 2.62e-15 ***
## N_tot 0.2964 0.1120 2.646 0.0104 *
## U1.N_tot -0.3308 0.1299 -2.547 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 14.98 on 60 degrees of freedom
## Multiple R-Squared: 0.2393, Adjusted R-squared: 0.2013
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2019.Porterville.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.296390 0.112020 2.64580 0.072314 0.520470
## slope2 -0.034385 0.065699 -0.52338 -0.165800 0.097033Medics-Wheat
Porterville Medics-Wheat results
| Year | |||
| Relative yield (Max rep yield = 100) | |||
| 2016 | 2017 | 2018 | |
| (1) | (2) | (3) | |
| Total Nitrogen Applied | 0.304*** | -0.276* | -0.116 |
| (0.087) | (0.151) | (0.107) | |
| Total Nitrogen Applied squared | -0.001*** | 0.001 | 0.0004 |
| (0.0004) | (0.001) | (0.0004) | |
| Intercept | 63.944*** | 88.406*** | 90.273*** |
| (4.300) | (7.682) | (5.514) | |
| Observations | 60 | 62 | 61 |
| R2 | 0.239 | 0.088 | 0.021 |
| Adjusted R2 | 0.213 | 0.057 | -0.013 |
| Residual Std. Error | 9.493 (df = 57) | 16.335 (df = 59) | 11.129 (df = 58) |
| F Statistic | 8.961*** (df = 2; 57) | 2.855* (df = 2; 59) | 0.613 (df = 2; 58) |
| Note: | p<0.1; p<0.05; p<0.01 | ||
It is evident that only 2016 has a good fit.
p.seg.2016.Porterville.MW## Warning: Removed 6 rows containing missing values (geom_point).
summary.segmented(m.seg.2016.Porterville.MW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 150 19.447
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 70.47646 3.85718 18.272 <2e-16 ***
## N_tot 0.11745 0.04918 2.388 0.0201 *
## U1.N_tot -0.28679 0.10401 -2.757 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11 on 60 degrees of freedom
## Multiple R-Squared: 0.16, Adjusted R-squared: 0.118
##
## Convergence attained in 1 iter. (rel. change 1.2057e-07)slope(m.seg.2016.Porterville.MW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.11745 0.049185 2.3880 0.019067 0.215840
## slope2 -0.16934 0.091651 -1.8477 -0.352670 0.013989Caledon
Not one of the models has a good fit, there is no response to fertiliser.
| Year | |||
| Relative yield (Max rep yield = 100) | |||
| 2016 | 2017 | 2018 | |
| (1) | (2) | (3) | |
| Total Nitrogen Applied | 0.111 | 0.039 | -0.030 |
| (0.113) | (0.087) | (0.104) | |
| Total Nitrogen Applied squared | -0.0004 | -0.0001 | 0.00005 |
| (0.0005) | (0.0004) | (0.0004) | |
| Intercept | 72.883*** | 81.544*** | 79.684*** |
| (5.661) | (4.335) | (5.439) | |
| Observations | 60 | 59 | 59 |
| R2 | 0.017 | 0.016 | 0.012 |
| Adjusted R2 | -0.018 | -0.019 | -0.024 |
| Residual Std. Error | 11.923 (df = 57) | 9.070 (df = 56) | 10.301 (df = 56) |
| F Statistic | 0.489 (df = 2; 57) | 0.452 (df = 2; 56) | 0.329 (df = 2; 56) |
| Note: | p<0.1; p<0.05; p<0.01 | ||
Tygerhoek
All years show a good fit except for 2017
| Year | ||||
| Relative yield (Max rep yield = 100) | ||||
| 2016 | 2017 | 2018 | 2019 | |
| (1) | (2) | (3) | (4) | |
| Total Nitrogen Applied | 0.492*** | 0.021 | 0.530*** | 0.285*** |
| (0.095) | (0.068) | (0.098) | (0.104) | |
| Total Nitrogen Applied squared | -0.002*** | 0.00003 | -0.002*** | -0.001** |
| (0.0004) | (0.0003) | (0.0004) | (0.0005) | |
| Intercept | 50.672*** | 84.986*** | 52.171*** | 71.580*** |
| (4.807) | (3.423) | (4.782) | (4.682) | |
| Observations | 61 | 60 | 59 | 59 |
| R2 | 0.491 | 0.055 | 0.387 | 0.125 |
| Adjusted R2 | 0.474 | 0.022 | 0.365 | 0.094 |
| Residual Std. Error | 10.177 (df = 58) | 7.221 (df = 57) | 10.488 (df = 56) | 11.876 (df = 56) |
| F Statistic | 27.986*** (df = 2; 58) | 1.650 (df = 2; 57) | 17.688*** (df = 2; 56) | 4.016** (df = 2; 56) |
| Note: | p<0.1; p<0.05; p<0.01 | |||
grid.arrange(p.seg.2016.Tygerhoek.CW, p.seg.2018.Tygerhoek.CW,p.seg.2019.Tygerhoek.CW, nrow =2)
summary.segmented(m.seg.2016.Tygerhoek.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 50.648 7.837
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 36.6240 8.3941 4.363 5.13e-05 ***
## N_tot 0.8684 0.2411 3.602 0.000641 ***
## U1.N_tot -0.8181 0.2438 -3.356 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 12.05 on 60 degrees of freedom
## Multiple R-Squared: 0.4463, Adjusted R-squared: 0.4186
##
## Convergence attained in 2 iter. (rel. change 0)slope(m.seg.2016.Tygerhoek.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.868380 0.241060 3.6023 0.386180 1.3506
## slope2 0.050267 0.036161 1.3901 -0.022067 0.1226summary.segmented(m.seg.2018.Tygerhoek.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 52.116 5.722
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 33.4139 7.2908 4.583 2.43e-05 ***
## N_tot 0.9948 0.2094 4.751 1.34e-05 ***
## U1.N_tot -1.0162 0.2118 -4.797 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 10.47 on 59 degrees of freedom
## Multiple R-Squared: 0.4912, Adjusted R-squared: 0.4653
##
## Convergence attained in 2 iter. (rel. change 2.813e-16)slope(m.seg.2018.Tygerhoek.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.994780 0.209380 4.75110 0.575820 1.413800
## slope2 -0.021436 0.032088 -0.66804 -0.085643 0.042771summary.segmented(m.seg.2019.Tygerhoek.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 86.615 17.731
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 68.6425 5.0592 13.568 <2e-16 ***
## N_tot 0.2733 0.1056 2.589 0.0121 *
## U1.N_tot -0.4017 0.1224 -3.283 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 14.12 on 60 degrees of freedom
## Multiple R-Squared: 0.1746, Adjusted R-squared: 0.1333
##
## Convergence attained in 2 iter. (rel. change 1.5208e-16)slope(m.seg.2019.Tygerhoek.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.27333 0.105570 2.5890 0.062153 0.4845100
## slope2 -0.12842 0.061916 -2.0741 -0.252270 -0.0045672Riversdale
| Year | ||||
| Relative yield (Max rep yield = 100) | ||||
| 2016 | 2017 | 2018 | 2019 | |
| (1) | (2) | (3) | (4) | |
| Total Nitrogen Applied | 0.278*** | 0.285* | -0.138 | 0.064 |
| (0.087) | (0.153) | (0.288) | (0.131) | |
| Total Nitrogen Applied squared | -0.001* | -0.001* | 0.001 | -0.0004 |
| (0.0004) | (0.001) | (0.001) | (0.001) | |
| Intercept | 59.735*** | 67.827*** | 68.709*** | 78.166*** |
| (4.324) | (8.022) | (14.655) | (5.875) | |
| Observations | 54 | 46 | 47 | 44 |
| R2 | 0.563 | 0.078 | 0.061 | 0.019 |
| Adjusted R2 | 0.546 | 0.035 | 0.018 | -0.029 |
| Residual Std. Error | 6.943 (df = 51) | 12.048 (df = 43) | 23.903 (df = 44) | 14.449 (df = 41) |
| F Statistic | 32.862*** (df = 2; 51) | 1.817 (df = 2; 43) | 1.419 (df = 2; 44) | 0.396 (df = 2; 41) |
| Note: | p<0.1; p<0.05; p<0.01 | |||
## Warning: Removed 6 rows containing missing values (geom_point).## Warning: Removed 1 rows containing missing values (geom_vline).## Warning: Removed 1 rows containing missing values (geom_text).## Warning: Removed 6 rows containing missing values (geom_point).## Warning: Removed 5 rows containing missing values (geom_point).## Warning: Removed 2 rows containing missing values (geom_point).
p.seg.2017.Riversdale.CW## Warning: Removed 6 rows containing missing values (geom_point).## Warning: Removed 1 rows containing missing values (geom_text).
summary.segmented(m.seg.2017.Riversdale.CW)##
## ***Regression Model with Segmented Relationship(s)***
##
## Call:
## segmented.lm(obj = model, seg.Z = ~N_tot)
##
## Estimated Break-Point(s):
## Est. St.Err
## psi1.N_tot 120 39.261
##
## Meaningful coefficients of the linear terms:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 73.2131 7.4669 9.805 1.22e-12 ***
## N_tot 0.1071 0.1131 0.947 0.349
## U1.N_tot -0.2139 0.1382 -1.547 NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 13.06 on 44 degrees of freedom
## Multiple R-Squared: 0.06081, Adjusted R-squared: -0.003226
##
## Convergence attained in 1 iter. (rel. change 1.7283e-06)slope(m.seg.2017.Riversdale.CW)## $N_tot
## Est. St.Err. t value CI(95%).l CI(95%).u
## slope1 0.10711 0.113100 0.94697 -0.12084 0.335050
## slope2 -0.10681 0.079482 -1.34390 -0.26700 0.053373