## [1] "1. Leitura dos dados"
## [1] "2. Exploração inicial"
## Rows: 15,395
## Columns: 34
## $ ano <chr> "2016", "2016", "2016", "2016", "2016", "2016", "2016", "20…
## $ ponto <chr> "CF1658277", "CF1658272", "CF1658273", "CF1658274", "CF1658…
## $ x <dbl> -49.18157, -49.18953, -49.18786, -49.18619, -49.18453, -49.…
## $ y <dbl> -21.27265, -21.27243, -21.27241, -21.27239, -21.27237, -21.…
## $ variedade <chr> "CV6654", "CV6654", "CV6654", "CV6654", "CV6654", "CV6654",…
## $ solos <chr> "LVal md", "LVPd md/arg", "LVPd md/arg", "LVPd md/arg", "LV…
## $ tch_real <dbl> 63.54, 63.54, 63.54, 63.54, 63.54, 63.54, 63.54, 63.54, 63.…
## $ atr <dbl> 148.07, 148.07, 148.07, 148.07, 148.07, 148.07, 148.07, 148…
## $ ph_cacl2_1 <dbl> 5.19, 5.18, 4.88, 4.96, 5.05, 5.15, 6.24, 4.50, 5.38, 5.50,…
## $ mo_1 <dbl> 16.2022, 17.0236, 15.6546, 13.7380, 15.6546, 14.0118, 11.82…
## $ p_resina_1 <dbl> 11.538500, 12.526100, 10.880100, 10.715500, 11.044700, 11.2…
## $ s_1 <dbl> 8.84769, 9.92472, 12.07878, 8.96736, 9.56571, 8.01000, 9.80…
## $ ca_1 <dbl> 21.601449, 19.862319, 14.789855, 16.601449, 18.195652, 19.4…
## $ mg_1 <dbl> 11.045207, 15.713952, 5.495713, 9.696804, 10.047545, 10.359…
## $ k_1 <dbl> 1.2805516, 0.9239182, 1.4992867, 1.5563481, 1.6229196, 0.84…
## $ al_1 <dbl> 1.19600, 0.92000, 1.38000, 0.55200, 0.82800, 1.19600, 0.644…
## $ h_al_1 <dbl> 22.96210, 22.01502, 30.19345, 22.72158, 22.01502, 19.40179,…
## $ sb_1 <dbl> 33.92721, 36.50019, 21.78485, 27.85460, 29.86612, 30.63469,…
## $ ctc_1 <dbl> 56.88931, 58.51521, 51.97831, 50.57618, 51.88114, 50.03647,…
## $ v_1 <dbl> 59.63723, 62.37726, 41.91144, 55.07455, 57.56642, 61.22471,…
## $ m_1 <dbl> 3.4051560, 2.4585659, 5.9573004, 1.9432103, 2.6975854, 3.75…
## $ ph_cacl2_2 <dbl> 4.90, 5.38, 5.29, 5.30, 5.16, 5.06, 5.50, 4.50, 4.79, 4.46,…
## $ mo_2 <dbl> 13.7380, 13.4642, 12.3690, 11.5476, 13.7380, 11.5476, 11.82…
## $ p_resina_2 <dbl> 12.032300, 11.703100, 11.703100, 13.513700, 11.867700, 11.8…
## $ s_2 <dbl> 12.43779, 16.86558, 11.00175, 8.12967, 12.19845, 13.27548, …
## $ ca_2 <dbl> 14.210145, 16.021739, 15.514493, 14.427536, 15.224638, 14.5…
## $ mg_2 <dbl> 7.085737, 9.735776, 6.563523, 8.262666, 7.327358, 7.475448,…
## $ k_2 <dbl> 0.8050404, 0.7194484, 0.9429387, 0.5863053, 0.7669995, 0.67…
## $ al_2 <dbl> 3.956000, 1.012000, 1.104000, 0.736000, 2.024000, 2.852000,…
## $ h_al_2 <dbl> 43.19156, 26.60941, 24.98024, 21.33044, 24.71858, 26.33069,…
## $ sb_2 <dbl> 22.100922, 26.476963, 23.020954, 23.276507, 23.318995, 22.7…
## $ ctc_2 <dbl> 65.29248, 53.08638, 48.00119, 44.60695, 48.03757, 49.05050,…
## $ v_2 <dbl> 33.84911, 49.87525, 47.95913, 52.18135, 48.54324, 46.31922,…
## $ m_2 <dbl> 15.182146, 3.681478, 4.576174, 3.065069, 7.986428, 11.15290…
## [1] "3. Testes de normalidade"
## [1] "4. Estatística descritiva"
Estatística descritiva das variáveis (2017)
| Min |
30.5000000 |
100.1500000 |
4.0000000 |
6.107800 |
1.299790 |
0.731830 |
3.000000 |
0.5573721 |
0.111964 |
0.000000 |
5.541665 |
5.451818 |
21.073509 |
17.9940737 |
0.0000000 |
| Q1 |
64.6900000 |
125.1800000 |
5.2000000 |
11.369000 |
8.232220 |
4.108258 |
16.115385 |
6.3247223 |
1.274955 |
0.096000 |
12.207434 |
25.072611 |
40.871632 |
61.2126936 |
0.2125567 |
| Med |
86.5900000 |
137.7600000 |
5.5500000 |
13.133200 |
12.376580 |
5.508900 |
21.589431 |
8.6648261 |
1.993912 |
0.288000 |
14.599468 |
32.974015 |
48.463118 |
69.5394902 |
0.7752133 |
| Média |
88.9092373 |
134.8789476 |
5.5307910 |
13.662985 |
16.412581 |
6.809475 |
23.360209 |
9.3435488 |
2.517844 |
0.734965 |
15.345073 |
35.221899 |
50.567020 |
67.6943058 |
2.7774096 |
| Q3 |
111.6600000 |
144.6800000 |
5.8900000 |
15.271200 |
19.777200 |
7.537870 |
28.395770 |
11.3470149 |
3.169131 |
0.768000 |
17.462664 |
42.549554 |
57.509415 |
76.2866930 |
2.2151230 |
| Max |
196.8200000 |
158.1700000 |
7.0400000 |
45.853800 |
159.833880 |
150.317300 |
271.857651 |
39.0179140 |
18.858311 |
35.616000 |
80.392034 |
309.694684 |
323.401252 |
95.7617457 |
69.5969568 |
| DP |
31.6780545 |
11.9622681 |
0.5316525 |
3.508783 |
13.960101 |
6.358454 |
11.525629 |
4.2260972 |
1.884264 |
1.489042 |
4.784460 |
15.263088 |
14.611838 |
11.9740800 |
5.9731258 |
| CV |
35.6296550 |
8.8688919 |
9.6125942 |
25.680942 |
85.057316 |
93.376559 |
49.338723 |
45.2301076 |
74.836408 |
202.600363 |
31.179128 |
43.334086 |
28.895983 |
17.6884597 |
215.0610345 |
| Skn |
0.3742606 |
-0.4124312 |
-0.1709083 |
1.639553 |
3.331065 |
9.672653 |
4.822507 |
1.3798801 |
2.398875 |
7.783490 |
2.177287 |
3.056045 |
3.344003 |
-0.7177730 |
4.2884892 |
| Krt |
-0.5364926 |
-0.9600112 |
-0.1148486 |
7.360341 |
18.288983 |
164.150897 |
75.288765 |
3.5871949 |
9.156951 |
122.720914 |
14.023944 |
35.566484 |
41.356665 |
0.3121032 |
23.2511512 |
## [1] "5. Transformações"
Estatística descritiva após transformações (2017)
| Min |
30.5000000 |
100.1500000 |
4.0000000 |
6.107800 |
0.8328178 |
-0.3122070 |
1.0986123 |
0.5573721 |
0.111964 |
0.000000 |
5.541665 |
1.6959492 |
3.0480167 |
17.9940737 |
0.0000000 |
| Q1 |
64.6900000 |
125.1800000 |
5.2000000 |
11.369000 |
2.2226995 |
1.4129991 |
2.7797744 |
6.3247223 |
1.274955 |
0.096000 |
12.207434 |
3.2217760 |
3.7104362 |
61.2126936 |
0.1927311 |
| Med |
86.5900000 |
137.7600000 |
5.5500000 |
13.133200 |
2.5935054 |
1.7063650 |
3.0722039 |
8.6648261 |
1.993912 |
0.288000 |
14.599468 |
3.4957198 |
3.8808031 |
69.5394902 |
0.5739206 |
| Média |
88.9092373 |
134.8789476 |
5.5307910 |
13.662985 |
2.6443932 |
1.7416995 |
3.0550922 |
9.3435488 |
2.517844 |
0.734965 |
15.345073 |
3.4805820 |
3.8889056 |
67.6943058 |
0.8180992 |
| Q3 |
111.6600000 |
144.6800000 |
5.8900000 |
15.271200 |
3.0338562 |
2.0199396 |
3.3462402 |
11.3470149 |
3.169131 |
0.768000 |
17.462664 |
3.7506694 |
4.0519487 |
76.2866930 |
1.1678656 |
| Max |
196.8200000 |
158.1700000 |
7.0400000 |
45.853800 |
5.0803720 |
5.0127484 |
5.6052786 |
39.0179140 |
18.858311 |
35.616000 |
80.392034 |
5.7355869 |
5.7788938 |
95.7617457 |
4.2569870 |
| DP |
31.6780545 |
11.9622681 |
0.5316525 |
3.508783 |
0.6252337 |
0.5423803 |
0.4379050 |
4.2260972 |
1.884264 |
1.489042 |
4.784460 |
0.4038201 |
0.2561310 |
11.9740800 |
0.8518108 |
| CV |
35.6296550 |
8.8688919 |
9.6125942 |
25.680942 |
23.6437484 |
31.1408672 |
14.3336112 |
45.2301076 |
74.836408 |
202.600363 |
31.179128 |
11.6020852 |
6.5861968 |
17.6884597 |
104.1207197 |
| Skn |
0.3742606 |
-0.4124312 |
-0.1709083 |
1.639553 |
0.3860856 |
0.6699677 |
-0.1051319 |
1.3798801 |
2.398875 |
7.783490 |
2.177287 |
-0.1071827 |
0.4566969 |
-0.7177730 |
1.3477142 |
| Krt |
-0.5364926 |
-0.9600112 |
-0.1148486 |
7.360341 |
0.3224830 |
2.3977005 |
0.7312156 |
3.5871949 |
9.156951 |
122.720914 |
14.023944 |
0.4865845 |
1.3136648 |
0.3121032 |
1.3620381 |
## [1] "6. Seleção de ano/variável"
## Rows: 4,197
## Columns: 3
## $ x <dbl> -49.30086, -49.29970, -49.29900, -49.29814, -49.29813, -49.29792, -4…
## $ y <dbl> -20.87622, -20.87756, -20.87855, -20.88096, -20.87652, -20.87957, -2…
## $ z <dbl> 67.87, 67.87, 67.87, 102.85, 68.39, 67.87, 68.39, 102.85, 68.39, 102…
## [1] "7. Boxplot / histograma / normalidade"
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 30.50 64.69 86.59 88.91 111.66 196.82
##
## Shapiro-Wilk normality test
##
## data: y_vals
## W = 0.97738, p-value < 2.2e-16
##
## Cramer-von Mises normality test
##
## data: y_vals
## W = 4.0125, p-value = 7.37e-10
##
## Lilliefors (Kolmogorov-Smirnov) normality test
##
## data: y_vals
## D = 0.065602, p-value < 2.2e-16
##
## Anderson-Darling normality test
##
## data: y_vals
## A = 24.862, p-value < 2.2e-16
## [1] "8. Colinearidade"
## tch_real atr ph_cacl2_1 mo_1 p_resina_1 s_1 ca_1 mg_1 k_1
## tch_real 1.00 0.01 0.01 0.02 0.17 -0.02 0.16 0.20 0.09
## atr 0.01 1.00 -0.20 -0.01 -0.05 -0.02 -0.25 -0.19 -0.07
## ph_cacl2_1 0.01 -0.20 1.00 0.15 0.33 0.08 0.56 0.46 0.29
## mo_1 0.02 -0.01 0.15 1.00 0.24 0.01 0.26 0.23 0.17
## p_resina_1 0.17 -0.05 0.33 0.24 1.00 0.05 0.34 0.22 0.26
## s_1 -0.02 -0.02 0.08 0.01 0.05 1.00 0.04 0.06 0.23
## ca_1 0.16 -0.25 0.56 0.26 0.34 0.04 1.00 0.69 0.27
## mg_1 0.20 -0.19 0.46 0.23 0.22 0.06 0.69 1.00 0.28
## k_1 0.09 -0.07 0.29 0.17 0.26 0.23 0.27 0.28 1.00
## al_1 -0.03 -0.02 -0.48 -0.07 -0.16 0.05 -0.36 -0.22 -0.10
## h_al_1 -0.09 0.04 -0.59 0.05 -0.17 0.02 -0.33 -0.27 -0.14
## sb_1 0.18 -0.25 0.59 0.28 0.34 0.08 0.97 0.81 0.41
## ctc_1 0.17 -0.24 0.36 0.32 0.30 0.10 0.88 0.77 0.38
## v_1 0.17 -0.19 0.74 0.16 0.33 0.05 0.85 0.69 0.36
## m_1 -0.04 0.00 -0.64 -0.14 -0.25 0.03 -0.54 -0.36 -0.24
## al_1 h_al_1 sb_1 ctc_1 v_1 m_1
## tch_real -0.03 -0.09 0.18 0.17 0.17 -0.04
## atr -0.02 0.04 -0.25 -0.24 -0.19 0.00
## ph_cacl2_1 -0.48 -0.59 0.59 0.36 0.74 -0.64
## mo_1 -0.07 0.05 0.28 0.32 0.16 -0.14
## p_resina_1 -0.16 -0.17 0.34 0.30 0.33 -0.25
## s_1 0.05 0.02 0.08 0.10 0.05 0.03
## ca_1 -0.36 -0.33 0.97 0.88 0.85 -0.54
## mg_1 -0.22 -0.27 0.81 0.77 0.69 -0.36
## k_1 -0.10 -0.14 0.41 0.38 0.36 -0.24
## al_1 1.00 0.50 -0.36 -0.13 -0.50 0.79
## h_al_1 0.50 1.00 -0.34 0.04 -0.73 0.49
## sb_1 -0.36 -0.34 1.00 0.91 0.88 -0.55
## ctc_1 -0.13 0.04 0.91 1.00 0.61 -0.32
## v_1 -0.50 -0.73 0.88 0.61 1.00 -0.67
## m_1 0.79 0.49 -0.55 -0.32 -0.67 1.00
## ca_1 mg_1 h_al_1 sb_1 ctc_1 v_1
## 84.29664 12.12042 17.02421 410.57600 120.32423 148.96923
## [1] "9. Regressão múltipla e Stepwise"
##
## Call:
## lm(formula = form_reg, data = df_aux)
##
## Residuals:
## Min 1Q Median 3Q Max
## -78.910 -23.011 -3.245 21.196 130.169
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 91.21440 16.16013 5.644 1.77e-08 ***
## atr 0.09931 0.04187 2.372 0.01775 *
## ph_cacl2_1 -9.09302 1.28885 -7.055 2.01e-12 ***
## mo_1 -0.60032 0.14334 -4.188 2.87e-05 ***
## p_resina_1 8.83592 0.82787 10.673 < 2e-16 ***
## s_1 -2.68713 0.89555 -3.001 0.00271 **
## mg_1 1.75772 0.18399 9.553 < 2e-16 ***
## k_1 0.78239 0.28255 2.769 0.00565 **
## al_1 -1.01424 0.52722 -1.924 0.05445 .
## ctc_1 1.39301 3.20283 0.435 0.66364
## m_1 1.37525 1.07965 1.274 0.20281
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 30.41 on 4211 degrees of freedom
## Multiple R-squared: 0.0812, Adjusted R-squared: 0.07902
## F-statistic: 37.22 on 10 and 4211 DF, p-value: < 2.2e-16
##
## studentized Breusch-Pagan test
##
## data: modelo_final
## BP = 110.02, df = 10, p-value < 2.2e-16
##
## Durbin-Watson test
##
## data: modelo_final
## DW = 1.504, p-value < 2.2e-16
## alternative hypothesis: true autocorrelation is greater than 0
## Start: AIC=29183.76
## tch_real ~ 1
##
## Df Sum of Sq RSS AIC
## + mg_1 1 163667 4075587 29020
## + p_resina_1 1 124301 4114953 29060
## + ctc_1 1 115784 4123471 29069
## + k_1 1 32900 4206355 29153
## + m_1 1 6602 4232652 29179
## + al_1 1 3636 4235619 29182
## + s_1 1 2575 4236680 29183
## <none> 4239254 29184
## + mo_1 1 1013 4238241 29185
## + atr 1 627 4238628 29185
## + ph_cacl2_1 1 266 4238988 29186
##
## Step: AIC=29019.53
## tch_real ~ mg_1
##
## Df Sum of Sq RSS AIC
## + p_resina_1 1 72144 4003443 28946
## + ph_cacl2_1 1 36673 4038914 28983
## + atr 1 10712 4064875 29010
## + s_1 1 5937 4069650 29015
## + k_1 1 5230 4070357 29016
## + m_1 1 5043 4070544 29016
## + mo_1 1 4091 4071496 29017
## + ctc_1 1 2024 4073563 29019
## <none> 4075587 29020
## + al_1 1 759 4074828 29021
##
## Step: AIC=28946.13
## tch_real ~ mg_1 + p_resina_1
##
## Df Sum of Sq RSS AIC
## + ph_cacl2_1 1 72545 3930898 28871
## + m_1 1 15375 3988067 28932
## + mo_1 1 13971 3989472 28933
## + atr 1 11000 3992443 28937
## + s_1 1 7785 3995658 28940
## + al_1 1 3701 3999741 28944
## <none> 4003443 28946
## + k_1 1 293 4003150 28948
## + ctc_1 1 98 4003344 28948
##
## Step: AIC=28870.92
## tch_real ~ mg_1 + p_resina_1 + ph_cacl2_1
##
## Df Sum of Sq RSS AIC
## + mo_1 1 14156.6 3916741 28858
## + s_1 1 5613.0 3925285 28867
## + atr 1 4699.6 3926198 28868
## + al_1 1 3460.1 3927438 28869
## + k_1 1 3300.6 3927597 28869
## <none> 3930898 28871
## + m_1 1 911.2 3929987 28872
## + ctc_1 1 388.2 3930510 28873
##
## Step: AIC=28857.69
## tch_real ~ mg_1 + p_resina_1 + ph_cacl2_1 + mo_1
##
## Df Sum of Sq RSS AIC
## + s_1 1 5801.7 3910940 28853
## + atr 1 5326.1 3911415 28854
## + k_1 1 4447.7 3912294 28855
## + al_1 1 3408.4 3913333 28856
## <none> 3916741 28858
## + m_1 1 1123.1 3915618 28859
## + ctc_1 1 20.1 3916721 28860
##
## Step: AIC=28853.43
## tch_real ~ mg_1 + p_resina_1 + ph_cacl2_1 + mo_1 + s_1
##
## Df Sum of Sq RSS AIC
## + k_1 1 7153.2 3903786 28848
## + atr 1 5360.5 3905579 28850
## + al_1 1 2616.2 3908323 28853
## <none> 3910940 28853
## + m_1 1 638.4 3910301 28855
## + ctc_1 1 111.3 3910828 28855
##
## Step: AIC=28847.7
## tch_real ~ mg_1 + p_resina_1 + ph_cacl2_1 + mo_1 + s_1 + k_1
##
## Df Sum of Sq RSS AIC
## + atr 1 5309.6 3898477 28844
## + al_1 1 2831.6 3900955 28847
## <none> 3903786 28848
## + m_1 1 377.4 3903409 28849
## + ctc_1 1 92.6 3903694 28850
##
## Step: AIC=28843.95
## tch_real ~ mg_1 + p_resina_1 + ph_cacl2_1 + mo_1 + s_1 + k_1 +
## atr
##
## Df Sum of Sq RSS AIC
## + al_1 1 1926.93 3896550 28844
## <none> 3898477 28844
## + m_1 1 29.72 3898447 28846
## + ctc_1 1 14.23 3898463 28846
##
## Step: AIC=28843.86
## tch_real ~ mg_1 + p_resina_1 + ph_cacl2_1 + mo_1 + s_1 + k_1 +
## atr + al_1
##
## Df Sum of Sq RSS AIC
## <none> 3896550 28844
## + m_1 1 1361.54 3895188 28844
## + ctc_1 1 35.73 3896514 28846
##
## Call:
## lm(formula = tch_real ~ mg_1 + p_resina_1 + ph_cacl2_1 + mo_1 +
## s_1 + k_1 + atr + al_1, data = variaveis_validas)
##
## Residuals:
## Min 1Q Median 3Q Max
## -79.253 -22.991 -3.063 21.138 129.649
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 102.09497 9.11699 11.198 < 2e-16 ***
## mg_1 1.79254 0.12922 13.872 < 2e-16 ***
## p_resina_1 8.85091 0.81922 10.804 < 2e-16 ***
## ph_cacl2_1 -9.79276 1.16887 -8.378 < 2e-16 ***
## mo_1 -0.59283 0.14044 -4.221 2.48e-05 ***
## s_1 -2.57818 0.89147 -2.892 0.00385 **
## k_1 0.76759 0.27352 2.806 0.00503 **
## atr 0.08859 0.04059 2.182 0.02914 *
## al_1 -0.52544 0.36403 -1.443 0.14898
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 30.41 on 4213 degrees of freedom
## Multiple R-squared: 0.08084, Adjusted R-squared: 0.0791
## F-statistic: 46.32 on 8 and 4213 DF, p-value: < 2.2e-16
## [1] "10. PCA e biplot"
## [1] 6.029222247 1.932043179 1.160895993 1.107306680 1.031001656 0.882891625
## [7] 0.692941754 0.664321056 0.650014256 0.337896731 0.319804673 0.160221886
## [13] 0.022864303 0.006919797 0.001654164
## [1] 0.4019481498 0.1288028786 0.0773930662 0.0738204453 0.0687334437
## [6] 0.0588594417 0.0461961169 0.0442880704 0.0433342838 0.0225264487
## [11] 0.0213203115 0.0106814591 0.0015242869 0.0004613198 0.0001102776
## [1] 40.19481 53.07510 60.81441 68.19645 75.06980 80.95574 85.57535
## [8] 90.00416 94.33759 96.59023 98.72227 99.79041 99.94284 99.98897
## [15] 100.00000
## [1] "11. Semivariograma e krigagem"
## [using ordinary kriging]
## 0% done 1% done 4% done 7% done 11% done 14% done 17% done 20% done 23% done 27% done 30% done 33% done 36% done 40% done 43% done 46% done 49% done 53% done 56% done 58% done 62% done 65% done 68% done 71% done 75% done 78% done 81% done 84% done 87% done 90% done 93% done 97% done100% done
