24小时热门版块排行榜

返回列表

yuying.sw

新虫 (初入文坛)

应助: 1 (幼儿园)
金币: 113.9
帖子: 32
在线: 14小时
虫号: 1221431
注册: 2011-03-04
专业: 食品科学基础

[求助] 响应面实验结果，麻烦哪位大神帮我分析一下，谢谢！

本人刚接触响应面试验，对于响应面的分析确实是个门外汉，现在将试验结果附上，请大神帮我分析一下，谢谢，在线等啊~~~

      ANOVA for Response Surface Quadratic Model
Analysis of variance table [Partial sum of squares - Type III]
Sum of Mean F p-value
Source Squares df Square Value Prob > F
Block 103.43 2 51.72
Model 995.35 14 71.10 2.14 0.1151 not significant
A-SPI:MD 8.10 1 8.10 0.24 0.6321
B-芯材含量 385.56 1 385.56 11.60 0.0067
C-乳化剂含量 0.62 1 0.62 0.019 0.8943
D-固形物含量 0.090 1 0.090 2.713E-003 0.9595
AB 140.19 1 140.19 4.22 0.0670
AC 0.058 1 0.058 1.734E-003 0.9676
AD 0.23 1 0.23 6.935E-003 0.9353
BC 65.37 1 65.37 1.97 0.1910
BD 37.27 1 37.27 1.12 0.3144
CD 7.48 1 7.48 0.23 0.6453
A^2 56.00 1 56.00 1.69 0.2233
B^2 85.96 1 85.96 2.59 0.1388
C^2 3.48 1 3.48 0.10 0.7528
D^2 106.11 1 106.11 3.19 0.1042
Residual 332.25 10 33.23
Cor Total 1431.03 26

The "Model F-value" of 2.14 implies the model is not significant relative to the noise.  There is a
11.51 % chance that a "Model F-value" this large could occur due to noise.

Values of "Prob > F" less than 0.0500 indicate model terms are significant.
In this case B are significant model terms.
Values greater than 0.1000 indicate the model terms are not significant.
If there are many insignificant model terms (not counting those required to support hierarchy),
model reduction may improve your model.

Std. Dev. 5.76 R-Squared 0.7497
Mean 76.06 Adj R-Squared 0.3994
C.V. % 7.58 Pred R-Squared -0.8626
PRESS 2472.73 Adeq Precision 5.986

A negative "Pred R-Squared" implies that the overall mean is a better predictor of your
response than the current model.

"Adeq Precision" measures the signal to noise ratio.  A ratio greater than 4 is desirable.  Your
ratio of 5.986 indicates an adequate signal.  This model can be used to navigate the design space.

Coefficient Standard 95% CI 95% CI
Factor Estimate df Error Low High VIF
Intercept 74.06 1 3.33 66.64 81.48
Block 1 2.63 2
Block 2 -2.07
Block 3 -0.56
A-SPI:MD 0.82 1 1.66 -2.89 4.53 1.00
B-芯材含量 -5.67 1 1.66 -9.38 -1.96 1.00
C-乳化剂含量 0.23 1 1.66 -3.48 3.93 1.00
D-固形物含量 -0.087 1 1.66 -3.79 3.62 1.00
AB 5.92 1 2.88 -0.50 12.34 1.00
AC 0.12 1 2.88 -6.30 6.54 1.00
AD 0.24 1 2.88 -6.18 6.66 1.00
BC -4.04 1 2.88 -10.46 2.38 1.00
BD -3.05 1 2.88 -9.47 3.37 1.00
CD -1.37 1 2.88 -7.79 5.05 1.00
A^2 3.24 1 2.50 -2.32 8.80 1.25
B^2 -4.01 1 2.50 -9.58 1.55 1.25
C^2 0.81 1 2.50 -4.75 6.37 1.25
D^2 4.46 1 2.50 -1.10 10.02 1.25

Final Equation in Terms of Coded Factors:

微胶囊包埋率    =
+74.06
+0.82    * A
-5.67    * B
+0.23    * C
-0.087    * D
+5.92    * A * B
+0.12    * A * C
+0.24    * A * D
-4.04    * B * C
-3.05    * B * D
-1.37    * C * D
+3.24    * A^2
-4.01    * B^2
+0.81    * C^2
+4.46    * D^2

Final Equation in Terms of Actual Factors:

微胶囊包埋率    =
+74.06000
+0.82167    * SPI:MD
-5.66833    * 芯材含量
+0.22667    * 乳化剂含量
-0.086667    * 固形物含量
+5.92000    * SPI:MD * 芯材含量
+0.12000    * SPI:MD * 乳化剂含量
+0.24000    * SPI:MD * 固形物含量
-4.04250    * 芯材含量 * 乳化剂含量
-3.05250    * 芯材含量 * 固形物含量
-1.36750    * 乳化剂含量 * 固形物含量
+3.24042    * SPI:MD^2
-4.01458    * 芯材含量^2
+0.80792    * 乳化剂含量^2
+4.46042    * 固形物含量^2

The Diagnostics Case Statistics Report has been moved to the Diagnostics Node.
In the Diagnostics Node, Select Case Statistics from the View Menu.

Proceed to Diagnostic Plots (the next icon in progression).  Be sure to look at the:
1) Normal probability plot of the studentized residuals to check for normality of residuals.
2) Studentized residuals versus predicted values to check for constant error.
3) Externally Studentized Residuals to look for outliers, i.e., influential values.
4) Box-Cox plot for power transformations.

If all the model statistics and diagnostic plots are OK, finish up with the Model Graphs icon.

回复此楼