An Application and Interpretation of the Second Order Response Surface Model
İn this study, three artificial data sets were used to explain the second order response surface model. It was assumed that the data were collected from a 3x3 experiment with two replications. Fitting the second order response surface model showed that 92.51%, 83.93% and 85.41% of the tatei variat...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ankara University
2001-11-01
|
| Series: | Journal of Agricultural Sciences |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/download/article-file/1782482 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | İn this study, three artificial data sets were used to explain the second order response surface model. It was assumed that the data were collected from a 3x3 experiment with two replications. Fitting the second order response surface model showed that 92.51%, 83.93% and 85.41% of the tatei variation in YIELD1, YIELD2 and YIELD3, respectively, accounted for by the fitted model. When the lack of fit test was applied, the results clarif ı ed that the second order model was adequately described the response surface for all the three sets of data. Application of the canonical analysis confı rmed that there was a stationary point of maximum response for YIELD1, a stationary point of minimum response for YIELD2 and a saddle point for YIELD3. After that, the data on the corrected sugar content of sugar beet were analyzed. The results showed that the fitted second order model accounted for 68.9% of the total variation in the sugar content. When the lack of fit test was applied, the results showed that the second order model adequately described the response surface of sugar content. The results of canonical analysis indicated that there was a saddle point for the sugar content. |
|---|---|
| ISSN: | 1300-7580 2148-9297 |