• API
• FAQ
• Tools
• Archive
SHARE
TWEET

# Untitled

a guest Mar 19th, 2019 52 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
1. x <- vector(length = 100)
2. x1 <- vector(length = 100)
3. x2 <- vector(length = 100)
4. x3 <- vector(length = 100)
5. x4 <- vector(length = 100)
6. x4 <- vector(length = 100)
7.
8. #нормальное
9. n_mean <- vector (length = 1000)
10. n_mad <- vector (length = 1000)
11. n_med <- vector (length = 1000)
12. n_sd <- vector(length = 1000)
13. n_iqr <- vector(length = 1000)
14. n_uq <- vector(length = 1000)
15. n_lq <- vector(length = 1000)
16. n_count_mean <- 0
17. n_count_med <- 0
18. n_count_tukey <- 0
19. for(i in 1:1000)
20. {
21.   x2<-rnorm(100, mean = 0, sd =1)
22.   x2<-sort(x2)
23.   n_mean[i] <- mean(x2)
24.   n_med[i] <- median(x2)
25.   n_sd[i] <- sd(x2)
26.   n_mad[i] <- mad(x2, center = median(x2))
27.   n_iqr[i] <- IQR(x2)
28.   n_lq[i] <- x2[25]
29.   n_uq[i] <- x2[75]
30.   for (j in 1:100){
31.     if (((abs(x2[j] - n_mean[i]) / n_sd[i]) > 3)){
32.       n_count_mean = n_count_mean + 1
33.     }
34.     if (((abs(x2[j] - n_med[i]) / n_mad[i]) > 3)){
35.       n_count_med = n_count_med + 1
36.     }
37.     if ((x2[j] > (n_uq[i] + 1.5*n_iqr[i])) | (x2[j] < (n_lq[i] - 1.5*n_iqr[i])) ) {
38.       n_count_tukey = n_count_tukey + 1
39.     }
40.   }
41.
42. }
43. boxplot(x2, horizontal = TRUE)
44.
45. #равномерное
46. u_mean <- vector (length = 1000)
47. u_mad <- vector (length = 1000)
48. u_med <- vector (length = 1000)
49. u_sd <- vector(length = 1000)
50. u_iqr <- vector(length = 1000)
51. u_uq <- vector(length = 1000)
52. u_lq <- vector(length = 1000)
53. u_count_mean <- 0
54. u_count_med <- 0
55. u_count_tukey <- 0
56. for(i in 1:1000)
57. {
58.   x5<-runif(100, min = -sqrt(3), max = sqrt(3))
59.   x5<-sort(x)
60.   u_mean[i] <- mean(x5)
61.   u_med[i] <- median(x5)
62.   u_sd[i] <- sd(x5)
63.   u_mad[i] <- mad(x5, center = median(x5))
64.   u_iqr[i] <- IQR(x5)
65.   u_lq[i] <- x5[25]
66.   u_uq[i] <- x5[75]
67.   for (j in 1:100){
68.     if (((abs(x5[j] - u_mean[i]) / u_sd[i]) > 3)){
69.       u_count_mean = u_count_mean + 1
70.     }
71.     if (((abs(x5[j] - u_med[i]) / u_mad[i]) > 3)){
72.       u_count_med = u_count_med + 1
73.     }
74.     if ((x5[j] > (u_uq[i] + 1.5*u_iqr[i])) || (x5[j] < (u_lq[i] - 1.5*u_iqr[i])) ) {
75.       u_count_tukey = u_count_tukey + 1
76.     }
77.   }
78. }
79.
80. #лаплас
81. l_mean <- vector (length = 1000)
82. l_mad <- vector (length = 1000)
83. l_med <- vector (length = 1000)
84. l_sd <- vector(length = 1000)
85. l_iqr <- vector(length = 1000)
86. l_uq <- vector(length = 1000)
87. l_lq <- vector(length = 1000)
88. l_count_mean <- 0
89. l_count_med <- 0
90. l_count_tukey <- 0
91. for(i in 1:1000)
92. {
93.   x4<-rlaplace(100,0,1/sqrt(2))
94.   x4<-sort(x4)
95.   l_mean[i] <- mean(x4)
96.   l_med[i] <- median(x4)
97.   l_sd[i] <- sd(x4)
98.   l_mad[i] <- mad(x4, center = median(x4))
99.   l_iqr[i] <- IQR(x4)
100.   l_lq[i] <- x4[25]
101.   l_uq[i] <- x4[75]
102.   for (j in 1:100){
103.     if (((abs(x4[j] - l_mean[i]) / l_sd[i]) > 3)){
104.       l_count_mean = l_count_mean + 1
105.     }
106.     if (((abs(x4[j] - l_med[i]) / l_mad[i]) > 3)){
107.       l_count_med = l_count_med + 1
108.     }
109.     if ((x4[j] > (l_uq[i] + 1.5*l_iqr[i])) | (x4[j] < (l_lq[i] - 1.5*l_iqr[i])) ) {
110.       l_count_tukey = l_count_tukey + 1
111.     }
112.   }
113.
114. }
115.
116. #коши
117. c_mean <- vector (length = 1000)
118. c_mad <- vector (length = 1000)
119. c_med <- vector (length = 1000)
120. c_sd <- vector(length = 1000)
121. c_iqr <- vector(length = 1000)
122. c_uq <- vector(length = 1000)
123. c_lq <- vector(length = 1000)
124. c_count_mean <- 0
125. c_count_med <- 0
126. c_count_tukey <- 0
127. for(i in 1:1000)
128. {
129.   x3<-rcauchy(100, location = 0, scale = 1)
130.   x3<-sort(x3)
131.   c_mean[i] <- mean(x3)
132.   c_med[i] <- median(x3)
133.   c_sd[i] <- sd(x3)
134.   c_mad[i] <- mad(x3, center = median(x3))
135.   c_iqr[i] <- IQR(x3)
136.   c_lq[i] <- x3[25]
137.   c_uq[i] <- x3[75]
138.   for (j in 1:100){
139.     if (((abs(x3[j] - c_mean[i]) / c_sd[i]) > 3)){
140.       c_count_mean = c_count_mean + 1
141.     }
142.     if (((abs(x3[j] - c_med[i]) / c_mad[i]) > 3)){
143.       c_count_med = c_count_med + 1
144.     }
145.     if ((x3[j] > (c_uq[i] + 1.5*c_iqr[i])) | (x3[j] < (c_lq[i] - 1.5*c_iqr[i])) ) {
146.       c_count_tukey = c_count_tukey + 1
147.     }
148.   }
149. }
150.
151. #gross error model
152. g_mean <- vector (length = 1000)
153. g_mad <- vector (length = 1000)
154. g_med <- vector (length = 1000)
155. g_sd <- vector(length = 1000)
156. g_iqr <- vector(length = 1000)
157. g_uq <- vector(length = 1000)
158. g_lq <- vector(length = 1000)
159. g_count_mean <- 0
160. g_count_med <- 0
161. g_count_tukey <- 0
162. for (i in 1:1000) {
163.   for (j in 1:100) {
164.     alpha <- runif(1,0,1)
165.     if (alpha > 0.1) {
166.       x[j] <- rnorm(1,0,1)
167.     }
168.     else {
169.       x[j] <- rnorm(1,0,10)
170.       x1[j] <- rnorm(1,0,10)
171.     }
172.   }
173.   x<-sort(x)
174.   x1<-sort(x1)
175.   g_mean[i] <- mean(x)
176.   g_med[i] <- median(x)
177.   g_sd[i] <- sd(x)
178.   g_mad[i] <- mad(x, center = median(x))
179.   g_iqr[i] <- IQR(x)
180.   g_lq[i] <- x[25]
181.   g_uq[i] <- x[75]
182.   for (k in 1:100){
183.     if (((abs(x1[k] - g_mean[i]) / g_sd[i]) > 3)){
184.       g_count_mean = g_count_mean + 1
185.     }
186.     if (((abs(x1[k] - g_med[i]) / g_mad[i]) > 3)){
187.       g_count_med = g_count_med + 1
188.     }
189.     if ((x1[k] > (g_uq[i] + 1.5*g_iqr[i])) | (x1[k] < (g_lq[i] - 1.5*g_iqr[i])) ) {
190.       g_count_tukey = g_count_tukey + 1
191.     }
192.   }
193. }
194.
195. boxplot(x, x2, x3, x4, x5, horizontal = TRUE)
RAW Paste Data
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.

Top