1983
DOI: 10.1016/s0003-2670(00)85492-6
|View full text |Cite
|
Sign up to set email alerts
|

Non-linear transformation of factors in the design of experiments

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

1985
1985
2023
2023

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(4 citation statements)
references
References 7 publications
0
4
0
Order By: Relevance
“…Possible reasons for this are the presence of irrelevant model terms (i.e., overfitting) [ 78 ], model biases due to factor level errors [ 79 ] and the possibility that a second-order model does not adequately describe the relationship between the response and factors [ 80 ]. Broad design regions—e.g., by ±α-values in the CCC design—can also contribute to this issue [ 81 ]. Interestingly, the similarity of the multiple R 2 , RMSE and MAE for the confirmatory run replicates of the two designs indicated that they had equal predictive power based on statistical metrics, even though the BBD-based models had a considerable advantage in the first adequacy check.…”
Section: Discussionmentioning
confidence: 99%
“…Possible reasons for this are the presence of irrelevant model terms (i.e., overfitting) [ 78 ], model biases due to factor level errors [ 79 ] and the possibility that a second-order model does not adequately describe the relationship between the response and factors [ 80 ]. Broad design regions—e.g., by ±α-values in the CCC design—can also contribute to this issue [ 81 ]. Interestingly, the similarity of the multiple R 2 , RMSE and MAE for the confirmatory run replicates of the two designs indicated that they had equal predictive power based on statistical metrics, even though the BBD-based models had a considerable advantage in the first adequacy check.…”
Section: Discussionmentioning
confidence: 99%
“…(4) becomes A,/A =0.986 (iv) In order to calculate M the valuef,=0.04 (equivalent to a 25-fold dilution) extrapolated in eqn. ( 5 ) produces adequate results. This value off,,, which was not achieved experimentally, corresponds to a sufficiently high dilution and is comparable to an infinite dilution in which interferent effects would disappear.…”
Section: (I)mentioning
confidence: 93%
“…With these measurements and using eqns. (7), (5) and (8) successively a value of the corrected absorbance, A(corr), of the undiluted sample was produced. The same treatment was applied to a solution of known concentration without interferents in order to calibrate the result obtained using the solution of unknown concentration.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation