Statistical modelling / Fitting Wood's curve
Having set the new spread sheet as the active worksheet we can now do a
multiple regression analysis for the first cow by applying Stats → Regression Analysis →
Linear Models…
. We can also use the 'Save' button to store values for the
three estimates in the vector Est[1]. The analysis is shown below.
***** Regression Analysis *****
Response variate: logmilk_1[1]
Fitted terms: Constant, logday_1[1], day_1[1]
*** Summary of analysis ***
|
d.f.
|
s.s.
|
m.s.
|
v.r.
|
Regression
|
2
|
0.6661
|
0.33307
|
18.18
|
Residual
|
23
|
0.4215
|
0.01832
|
|
Total
|
25
|
1.0876
|
0.04350
|
|
Percentage variance accounted for 57.9
Standard error of observations is estimated to be 0.135
*** Estimates of parameters ***
|
estimate
|
s.e.
|
t(23)
|
t pr.
|
Constant
|
2.162
|
0.227
|
9.51
|
<.001
|
logday_1[1]
|
0.0342
|
0.0712
|
0.48
|
0.636
|
day_1[1]
|
-0.002681
|
0.000915
|
-2.93
|
0.008
|
|
  
|
|