TRABALHO FINAL
Filipi Nero Magalhaes de Paula
library(ggplot2)
library(emmeans)
library(knitr)1 Criação do Banco de Dados
semente<-130 #Nr_da_residencia
nr_mat<-1525#Numero de Matricula
idade<-19 # Idade
set.seed(2)
Y1 <- matrix(rnorm(180,nr_mat/2,nr_mat *(20/100)),nrow=180,ncol=1)
Y2 <- matrix(rnorm(20,nr_mat,nr_mat*(28/100)),nrow=20,ncol=1)
Y <- rbind(Y1,Y2)
X1 <- matrix(rnorm(180,idade,idade/4),nrow=180,ncol=1)
X2 <- matrix(rnorm(20,idade,idade*(75/100)),nrow=20,ncol=1)
X <-rbind(X1,X2)
rho <- (01/100)
Y = Y
X = rho*Y+sqrt(1-rho^2)*X
cor(X,Y)## [,1]
## [1,] 0.5757991plot(X,Y)
dados <-data.frame(1:200, coll1=c(X), coll2=c(Y))
str(dados)## 'data.frame': 200 obs. of 3 variables:
## $ X1.200: int 1 2 3 4 5 6 7 8 9 10 ...
## $ coll1 : num 25.3 22.3 45.1 24.2 21.8 ...
## $ coll2 : num 489 819 1247 418 738 ...dados## X1.200 coll1 coll2
## 1 1 25.30381 488.94106
## 2 2 22.34521 818.87900
## 3 3 45.10306 1246.79283
## 4 4 24.21522 417.73542
## 5 5 21.78838 738.02321
## 6 6 28.85107 802.88819
## 7 7 28.20433 978.42619
## 8 8 24.22795 689.39210
## 9 9 35.52401 1367.76455
## 10 10 27.29925 720.16996
## 11 11 32.77231 889.88348
## 12 12 27.12739 1061.93460
## 13 13 33.95788 642.72792
## 14 14 16.64097 445.40096
## 15 15 32.71857 1306.07983
## 16 16 21.71963 57.62393
## 17 17 35.07368 1030.47440
## 18 18 20.44229 773.42105
## 19 19 24.30022 1071.41275
## 20 20 35.90139 894.34087
## 21 21 34.89215 1400.19986
## 22 22 26.36282 396.52263
## 23 23 27.70496 1247.33965
## 24 24 41.72358 1358.66875
## 25 25 26.97368 764.00602
## 26 26 21.37531 14.72955
## 27 27 27.65285 908.05738
## 28 28 29.05156 580.54976
## 29 29 27.26524 1004.12200
## 30 30 38.23360 850.83920
## 31 31 36.34967 987.87627
## 32 32 18.31432 859.78292
## 33 33 26.96472 1090.73013
## 34 34 25.61512 675.83190
## 35 35 16.07772 525.61404
## 36 36 19.80362 580.82355
## 37 37 18.64930 236.07617
## 38 38 26.16395 487.21173
## 39 39 25.37453 591.98612
## 40 40 23.08009 687.31367
## 41 41 25.06568 645.50620
## 42 42 34.36809 164.97353
## 43 43 29.62749 505.77996
## 44 44 35.04054 1343.08198
## 45 45 32.22322 952.36065
## 46 46 30.01212 1369.73073
## 47 47 26.18133 669.32746
## 48 48 27.68414 734.79251
## 49 49 23.80892 706.33076
## 50 50 20.79240 396.87583
## 51 51 26.44949 506.82242
## 52 52 31.00200 1392.72191
## 53 53 24.06666 591.01465
## 54 54 28.99722 1151.59323
## 55 55 27.43514 442.99035
## 56 56 22.92538 162.90714
## 57 57 24.19663 663.99382
## 58 58 28.12429 1047.93807
## 59 59 34.75554 1109.96509
## 60 60 30.90876 1272.34372
## 61 61 27.54890 217.08613
## 62 62 32.35216 1382.02897
## 63 63 22.95006 548.04098
## 64 64 18.01192 810.74025
## 65 65 25.09477 916.90161
## 66 66 17.47607 512.40149
## 67 67 29.70019 152.85167
## 68 68 27.35457 616.31576
## 69 69 29.38601 788.17487
## 70 70 23.71854 489.37658
## 71 71 10.89401 481.51092
## 72 72 27.40809 863.28710
## 73 73 26.21448 719.29345
## 74 74 22.13043 895.12857
## 75 75 27.65203 746.11460
## 76 76 31.48168 485.83134
## 77 77 30.43105 1160.07123
## 78 78 33.86750 997.89588
## 79 79 27.93414 1083.52031
## 80 80 22.64282 332.43831
## 81 81 39.33141 1066.27530
## 82 82 24.53703 245.29170
## 83 83 31.07388 599.82150
## 84 84 19.45483 343.95782
## 85 85 26.30365 89.08447
## 86 86 40.12593 1318.24737
## 87 87 30.20139 563.21501
## 88 88 25.78512 675.67223
## 89 89 31.64473 644.48037
## 90 90 27.36180 880.44197
## 91 91 26.14395 1250.61921
## 92 92 34.54133 1275.25226
## 93 93 23.43756 401.50005
## 94 94 21.37423 348.17054
## 95 95 29.07699 301.13541
## 96 96 21.12022 380.30301
## 97 97 34.58857 1360.10391
## 98 98 16.68505 764.83199
## 99 99 17.54462 505.50236
## 100 100 21.53948 579.14617
## 101 101 28.39016 1090.21012
## 102 102 25.92037 841.98234
## 103 103 29.86584 666.64705
## 104 104 15.38237 533.86282
## 105 105 27.47202 499.52951
## 106 106 36.62547 1387.15229
## 107 107 30.41631 1049.17562
## 108 108 37.12592 1375.14957
## 109 109 31.23548 633.98106
## 110 110 22.31861 655.49550
## 111 111 25.93824 449.14892
## 112 112 23.63608 686.09167
## 113 113 25.67857 906.41714
## 114 114 21.39282 1176.97665
## 115 115 25.64003 934.57142
## 116 116 30.27250 901.57393
## 117 117 36.15995 1137.94087
## 118 118 30.68181 1112.37674
## 119 119 27.36889 795.01240
## 120 120 23.28205 523.58842
## 121 121 28.04156 1141.06595
## 122 122 32.22323 804.85182
## 123 123 36.21900 1284.24263
## 124 124 27.04214 631.15450
## 125 125 24.84103 444.00998
## 126 126 30.78080 926.46175
## 127 127 29.18333 558.27627
## 128 128 37.63783 957.33571
## 129 129 28.50379 236.68310
## 130 130 19.82853 231.05883
## 131 131 33.23082 972.89027
## 132 132 27.21706 863.44377
## 133 133 28.36065 1028.17565
## 134 134 23.93822 147.54510
## 135 135 35.20710 1132.33663
## 136 136 28.82648 1128.65088
## 137 137 33.40895 1077.28084
## 138 138 28.92072 1002.35513
## 139 139 40.14893 1406.07242
## 140 140 24.31629 319.08800
## 141 141 25.67668 584.65333
## 142 142 29.71301 887.46581
## 143 143 18.04081 516.37060
## 144 144 27.98458 788.59288
## 145 145 32.32062 990.10417
## 146 146 23.43611 563.12972
## 147 147 27.11307 962.91732
## 148 148 32.97240 930.22232
## 149 149 28.09747 516.44755
## 150 150 25.40022 458.29919
## 151 151 36.51455 1060.14664
## 152 152 29.27284 710.82593
## 153 153 27.06929 982.76849
## 154 154 31.40240 504.95232
## 155 155 41.58325 1152.07457
## 156 156 29.17450 352.85128
## 157 157 24.48764 995.92890
## 158 158 31.99785 904.08178
## 159 159 30.93197 844.23795
## 160 160 29.24525 966.09442
## 161 161 35.22698 884.03252
## 162 162 31.43807 567.88834
## 163 163 24.10351 680.84756
## 164 164 25.35752 872.26327
## 165 165 13.66656 362.07584
## 166 166 18.51499 492.88927
## 167 167 30.78983 1396.01391
## 168 168 25.79447 122.23618
## 169 169 21.32579 384.75568
## 170 170 29.84281 1064.58209
## 171 171 29.10384 1094.54187
## 172 172 40.03756 1018.65494
## 173 173 22.98051 779.84188
## 174 174 33.45710 861.28281
## 175 175 23.70121 486.57606
## 176 176 21.48845 563.58393
## 177 177 24.63802 682.45134
## 178 178 35.80502 477.42783
## 179 179 29.87962 1012.95417
## 180 180 25.24207 267.10095
## 181 181 23.75446 1085.01763
## 182 182 18.33397 986.15618
## 183 183 37.97055 1692.46284
## 184 184 19.22926 1041.87586
## 185 185 55.33153 1757.34969
## 186 186 16.84098 2027.41202
## 187 187 35.01454 1535.77260
## 188 188 36.04194 1744.96186
## 189 189 51.59208 1245.69513
## 190 190 48.21501 1740.05513
## 191 191 31.42974 981.80509
## 192 192 53.00897 1492.21872
## 193 193 45.63687 950.54863
## 194 194 45.53491 1411.28240
## 195 195 37.23394 1989.38940
## 196 196 42.12554 1824.14245
## 197 197 18.31620 1335.94169
## 198 198 46.95115 1188.30197
## 199 199 33.86553 1159.15677
## 200 200 44.15082 1206.27908summary(dados)## X1.200 coll1 coll2
## Min. : 1.00 Min. :10.89 Min. : 14.73
## 1st Qu.: 50.75 1st Qu.:24.17 1st Qu.: 531.80
## Median :100.50 Median :27.69 Median : 843.11
## Mean :100.50 Mean :28.70 Mean : 835.52
## 3rd Qu.:150.25 3rd Qu.:32.33 3rd Qu.:1078.84
## Max. :200.00 Max. :55.33 Max. :2027.41head(dados)## X1.200 coll1 coll2
## 1 1 25.30381 488.9411
## 2 2 22.34521 818.8790
## 3 3 45.10306 1246.7928
## 4 4 24.21522 417.7354
## 5 5 21.78838 738.0232
## 6 6 28.85107 802.88821.1 Analise Grafica: com Outlyers
ggplot(dados)+
aes(x= coll1)+
geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
2 Outlyers
2.1 Analise Outlyers
out1<-boxplot.stats(dados$coll1)$out
out2<-boxplot.stats(dados$coll2)$out
View(out1)
View(out2)3 Retirar Outlyers
dados$coll2[dados$coll2 == "out2"] <- mean(dados$coll2)
dados$coll1[dados$coll1 == "out1"] <- mean(dados$coll1)
boxplot(dados$coll1)
boxplot(dados$coll2)
## Analise Grafica: sem Outlyers
ggplot(dados)+
aes(x= coll1)+
geom_histogram()## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
4 Grafico de Dispersão
ggplot(dados)+ aes(x= coll1, y= coll2)+ geom_point()
## Valor da Correlação
dados$X1.200 <- NULL
cor(dados, method = "pearson", use = "complete.obs")## coll1 coll2
## coll1 1.0000000 0.5757991
## coll2 0.5757991 1.00000004.1 Ajustar Modelo de Regreção
regres = lm(coll1 ~ coll2, data = dados)
summary(regres)##
## Call:
## lm(formula = coll1 ~ coll2, data = dados)
##
## Residuals:
## Min 1Q Median 3Q Max
## -24.6979 -3.1851 -0.4478 3.0673 18.4769
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 19.691589 1.001280 19.67 <2e-16 ***
## coll2 0.010776 0.001087 9.91 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.952 on 198 degrees of freedom
## Multiple R-squared: 0.3315, Adjusted R-squared: 0.3282
## F-statistic: 98.21 on 1 and 198 DF, p-value: < 2.2e-164.2 Analise de Residuos
ggplot(dados, aes(x = coll1, y = coll2)) +
geom_point() +
geom_hline(yintercept = 0) +
labs(x = "Índice", y = "Resíduos")