Exploratory data analyses and missing data handling with multiple imputation using MICE package
Kushan De Silva
July 3, 2017
R Markdown
Using the famous Galton data set from the mosaicData package:
library(mosaic)## Loading required package: dplyr## Warning: Installed Rcpp (0.12.10) different from Rcpp used to build dplyr (0.12.11).
## Please reinstall dplyr to avoid random crashes or undefined behavior.##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union## Loading required package: lattice## Loading required package: ggplot2## Loading required package: mosaicData## Loading required package: Matrix##
## The 'mosaic' package masks several functions from core packages in order to add additional features.
## The original behavior of these functions should not be affected by this.##
## Attaching package: 'mosaic'## The following object is masked from 'package:Matrix':
##
## mean## The following objects are masked from 'package:dplyr':
##
## count, do, tally## The following objects are masked from 'package:stats':
##
## binom.test, cor, cov, D, fivenum, IQR, median, prop.test,
## quantile, sd, t.test, var## The following objects are masked from 'package:base':
##
## max, mean, min, prod, range, sample, sumhead(Galton)## family father mother sex height nkids
## 1 1 78.5 67.0 M 73.2 4
## 2 1 78.5 67.0 F 69.2 4
## 3 1 78.5 67.0 F 69.0 4
## 4 1 78.5 67.0 F 69.0 4
## 5 2 75.5 66.5 M 73.5 4
## 6 2 75.5 66.5 M 72.5 4Create a scatterplot of each person’s height against their father’s height
head(Galton)## family father mother sex height nkids
## 1 1 78.5 67.0 M 73.2 4
## 2 1 78.5 67.0 F 69.2 4
## 3 1 78.5 67.0 F 69.0 4
## 4 1 78.5 67.0 F 69.0 4
## 5 2 75.5 66.5 M 73.5 4
## 6 2 75.5 66.5 M 72.5 4g <- ggplot(data = Galton, aes(y = father, x = height))
g + geom_point(size = 3)
g + geom_point(aes(color = height), size = 3)
g <- ggplot(data = Galton, aes(y = father, x = height))
g + geom_point(size = 3)
Separate your plot into facets by sex
g + geom_point(aes(color = height), size = 3)+
facet_wrap(~sex, nrow = 1)+ theme(legend.position = "top")
Add regression lines to all of your facets
g + geom_point(aes(color = sex), size = 3)+
facet_wrap(~sex, nrow = 1)+ theme(legend.position = "top")+ geom_smooth(method = "lm", se = 0) +
xlab("height") +
ylab("father's height")
Using the RailTrail data set from the mosaicData package:
library(mosaic)
head(RailTrail)## hightemp lowtemp avgtemp spring summer fall cloudcover precip volume
## 1 83 50 66.5 0 1 0 7.6 0.00 501
## 2 73 49 61.0 0 1 0 6.3 0.29 419
## 3 74 52 63.0 1 0 0 7.5 0.32 397
## 4 95 61 78.0 0 1 0 2.6 0.00 385
## 5 44 52 48.0 1 0 0 10.0 0.14 200
## 6 69 54 61.5 1 0 0 6.6 0.02 375
## weekday
## 1 1
## 2 1
## 3 1
## 4 0
## 5 1
## 6 1Create a scatterplot of the number of crossings per day volume against the high temperature that day
g <- ggplot(data = RailTrail, aes(y = hightemp, x = volume))
g + geom_point(size = 3)
Separate your plot into facets by weekday. Add regression lines to the two facets
g + geom_point(aes(color = weekday), size = 3)+
facet_wrap(~weekday, nrow = 1)+ theme(legend.position = "top")+ geom_smooth(method = "lm", se = 0) +
xlab("volume") +
ylab("high temperature")
library(mosaic)
head(Marriage, 2)## bookpageID appdate ceremonydate delay officialTitle person dob
## 1 B230p539 10/29/96 11/9/96 11 CIRCUIT JUDGE Groom 4/11/64
## 2 B230p677 11/12/96 11/12/96 0 MARRIAGE OFFICIAL Groom 8/6/64
## age race prevcount prevconc hs college dayOfBirth sign
## 1 32.60274 White 0 <NA> 12 7 102 Aries
## 2 32.29041 White 1 Divorce 12 0 219 Leog <- ggplot(data = Marriage, aes(y = delay, x = age))
g + geom_point(size = 3)
g + geom_point(aes(color = person), size = 3)+
facet_wrap(~person, nrow = 1)+ theme(legend.position = "top")+ geom_smooth(method = "lm", se = 0) +
xlab("age") +
ylab("delay")
library(mdsr)
head(MLB_teams, 4)## # A tibble: 4 x 11
## yearID teamID lgID W L WPct attendance normAttend
## <int> <chr> <fctr> <int> <int> <dbl> <int> <dbl>
## 1 2008 ARI NL 82 80 0.5061728 2509924 0.5838859
## 2 2008 ATL NL 72 90 0.4444444 2532834 0.5892155
## 3 2008 BAL AL 68 93 0.4223602 1950075 0.4536477
## 4 2008 BOS AL 95 67 0.5864198 3048250 0.7091172
## # ... with 3 more variables: payroll <int>, metroPop <dbl>, name <chr>str(MLB_teams)## Classes 'tbl_df', 'tbl' and 'data.frame': 210 obs. of 11 variables:
## $ yearID : int 2008 2008 2008 2008 2008 2008 2008 2008 2008 2008 ...
## $ teamID : chr "ARI" "ATL" "BAL" "BOS" ...
## $ lgID : Factor w/ 7 levels "AA","AL","FL",..: 5 5 2 2 2 5 5 2 5 2 ...
## $ W : int 82 72 68 95 89 97 74 81 74 74 ...
## $ L : int 80 90 93 67 74 64 88 81 88 88 ...
## $ WPct : num 0.506 0.444 0.422 0.586 0.546 ...
## $ attendance: int 2509924 2532834 1950075 3048250 2500648 3300200 2058632 2169760 2650218 3202645 ...
## $ normAttend: num 0.584 0.589 0.454 0.709 0.582 ...
## $ payroll : int 66202712 102365683 67196246 133390035 121189332 118345833 74117695 78970066 68655500 137685196 ...
## $ metroPop : num 4489109 5614323 2785874 4732161 9554598 ...
## $ name : chr "Arizona Diamondbacks" "Atlanta Braves" "Baltimore Orioles" "Boston Red Sox" ...p <- ggplot(
data = MLB_teams,
aes(x = reorder(teamID, payroll), y = WPct)) +
geom_bar(fill = "green", stat = "identity") +
ylab("winning percentage") + xlab("payroll") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
p
library(macleish)## Loading required package: etlhead(whately_2015)## # A tibble: 6 x 8
## when temperature wind_speed wind_dir rel_humidity
## <dttm> <dbl> <dbl> <dbl> <dbl>
## 1 2015-01-01 00:00:00 -9.32 1.399 225.4 54.55
## 2 2015-01-01 00:10:00 -9.46 1.506 248.2 55.38
## 3 2015-01-01 00:20:00 -9.44 1.620 258.3 56.18
## 4 2015-01-01 00:30:00 -9.30 1.141 243.8 56.41
## 5 2015-01-01 00:40:00 -9.32 1.223 238.4 56.87
## 6 2015-01-01 00:50:00 -9.34 1.090 241.7 57.25
## # ... with 3 more variables: pressure <int>, solar_radiation <dbl>,
## # rainfall <int>str(whately_2015)## Classes 'tbl_df', 'tbl' and 'data.frame': 52560 obs. of 8 variables:
## $ when : POSIXct, format: "2015-01-01 00:00:00" "2015-01-01 00:10:00" ...
## $ temperature : num -9.32 -9.46 -9.44 -9.3 -9.32 -9.34 -9.3 -9.1 -9.07 -8.99 ...
## $ wind_speed : num 1.4 1.51 1.62 1.14 1.22 ...
## $ wind_dir : num 225 248 258 244 238 ...
## $ rel_humidity : num 54.5 55.4 56.2 56.4 56.9 ...
## $ pressure : int 985 985 985 985 984 984 984 984 984 984 ...
## $ solar_radiation: num 0 0 0 0 0 0 0 0 0 0 ...
## $ rainfall : int 0 0 0 0 0 0 0 0 0 0 ...summary(whately_2015)## when temperature wind_speed
## Min. :2015-01-01 00:00:00 Min. :-22.2800 Min. :0.000
## 1st Qu.:2015-04-02 05:57:30 1st Qu.: 0.9187 1st Qu.:0.951
## Median :2015-07-02 11:55:00 Median : 10.1900 Median :1.453
## Mean :2015-07-02 11:55:00 Mean : 9.3543 Mean :1.633
## 3rd Qu.:2015-10-01 17:52:30 3rd Qu.: 18.6500 3rd Qu.:2.102
## Max. :2015-12-31 23:50:00 Max. : 33.0800 Max. :8.020
## wind_dir rel_humidity pressure solar_radiation
## Min. : 0.0 Min. : 14.26 Min. : 958.0 Min. : 0.000
## 1st Qu.:150.4 1st Qu.: 56.60 1st Qu.: 980.0 1st Qu.: 0.000
## Median :217.3 Median : 76.28 Median : 985.0 Median : 2.884
## Mean :211.8 Mean : 74.30 Mean : 985.2 Mean : 164.494
## 3rd Qu.:305.8 3rd Qu.: 99.90 3rd Qu.: 990.0 3rd Qu.: 259.500
## Max. :360.0 Max. :100.00 Max. :1011.0 Max. :1086.000
## rainfall
## Min. : 0.00000
## 1st Qu.: 0.00000
## Median : 0.00000
## Mean : 0.01073
## 3rd Qu.: 0.00000
## Max. :16.00000library(corrplot)
df.cor = cor(whately_2015[,c(2:8)])
df.cor## temperature wind_speed wind_dir rel_humidity
## temperature 1.00000000 -0.1904743 -0.07286716 0.17109035
## wind_speed -0.19047428 1.0000000 0.15617499 -0.31791291
## wind_dir -0.07286716 0.1561750 1.00000000 -0.18109717
## rel_humidity 0.17109035 -0.3179129 -0.18109717 1.00000000
## pressure -0.09233977 -0.2139012 -0.18553935 -0.12903982
## solar_radiation 0.37066852 0.2379441 -0.09010549 -0.34074567
## rainfall 0.03461170 0.0101804 -0.01998011 0.05827162
## pressure solar_radiation rainfall
## temperature -0.09233977 0.37066852 0.03461170
## wind_speed -0.21390123 0.23794406 0.01018040
## wind_dir -0.18553935 -0.09010549 -0.01998011
## rel_humidity -0.12903982 -0.34074567 0.05827162
## pressure 1.00000000 0.01934476 -0.03732375
## solar_radiation 0.01934476 1.00000000 -0.03142406
## rainfall -0.03732375 -0.03142406 1.00000000corrplot(df.cor, method="ellipse")
data ("BostonHousing", package="mlbench")
original <- BostonHousing
set.seed(123)
BostonHousing[sample(1:nrow(BostonHousing), 100), "ptratio"] <- NA
BostonHousing[sample(1:nrow(BostonHousing), 100), "b"] <- NAlibrary(Rcpp)
require(Amelia)## Loading required package: Amelia## ##
## ## Amelia II: Multiple Imputation
## ## (Version 1.7.4, built: 2015-12-05)
## ## Copyright (C) 2005-2017 James Honaker, Gary King and Matthew Blackwell
## ## Refer to http://gking.harvard.edu/amelia/ for more information
## ##missmap(BostonHousing, main="Missing Map")
#missing data proportions
sapply(BostonHousing, function(df) {
+ sum(is.na(df)==TRUE)/ length(df)
})## crim zn indus chas nox rm age
## 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000
## dis rad tax ptratio b lstat medv
## 0.0000000 0.0000000 0.0000000 0.1976285 0.1976285 0.0000000 0.0000000#missing data in numbers
sapply(BostonHousing, function(x) sum(is.na(x)))## crim zn indus chas nox rm age dis rad
## 0 0 0 0 0 0 0 0 0
## tax ptratio b lstat medv
## 0 100 100 0 0#missing data imputation
pMiss <- function(x){sum(is.na(x))/length(x)*100}
apply(BostonHousing,2,pMiss)## crim zn indus chas nox rm age dis
## 0.00000 0.00000 0.00000 0.00000 0.00000 0.00000 0.00000 0.00000
## rad tax ptratio b lstat medv
## 0.00000 0.00000 19.76285 19.76285 0.00000 0.00000apply(BostonHousing,1,pMiss)## 1 2 3 4 5 6 7
## 7.142857 0.000000 0.000000 0.000000 7.142857 0.000000 0.000000
## 8 9 10 11 12 13 14
## 0.000000 0.000000 0.000000 0.000000 7.142857 0.000000 0.000000
## 15 16 17 18 19 20 21
## 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 7.142857
## 22 23 24 25 26 27 28
## 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000
## 29 30 31 32 33 34 35
## 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000
## 36 37 38 39 40 41 42
## 7.142857 0.000000 0.000000 7.142857 0.000000 0.000000 0.000000
## 43 44 45 46 47 48 49
## 7.142857 14.285714 0.000000 0.000000 0.000000 7.142857 0.000000
## 50 51 52 53 54 55 56
## 0.000000 14.285714 0.000000 0.000000 0.000000 7.142857 7.142857
## 57 58 59 60 61 62 63
## 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000 7.142857
## 64 65 66 67 68 69 70
## 7.142857 0.000000 0.000000 7.142857 7.142857 0.000000 7.142857
## 71 72 73 74 75 76 77
## 7.142857 0.000000 7.142857 7.142857 7.142857 0.000000 0.000000
## 78 79 80 81 82 83 84
## 7.142857 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000
## 85 86 87 88 89 90 91
## 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000
## 92 93 94 95 96 97 98
## 0.000000 0.000000 7.142857 7.142857 0.000000 0.000000 7.142857
## 99 100 101 102 103 104 105
## 0.000000 0.000000 0.000000 7.142857 0.000000 7.142857 0.000000
## 106 107 108 109 110 111 112
## 0.000000 7.142857 7.142857 7.142857 7.142857 0.000000 7.142857
## 113 114 115 116 117 118 119
## 7.142857 0.000000 7.142857 0.000000 7.142857 0.000000 0.000000
## 120 121 122 123 124 125 126
## 0.000000 7.142857 7.142857 0.000000 0.000000 0.000000 0.000000
## 127 128 129 130 131 132 133
## 0.000000 0.000000 0.000000 0.000000 0.000000 7.142857 7.142857
## 134 135 136 137 138 139 140
## 7.142857 0.000000 0.000000 0.000000 0.000000 7.142857 0.000000
## 141 142 143 144 145 146 147
## 0.000000 0.000000 7.142857 0.000000 0.000000 14.285714 0.000000
## 148 149 150 151 152 153 154
## 0.000000 14.285714 7.142857 7.142857 0.000000 0.000000 0.000000
## 155 156 157 158 159 160 161
## 0.000000 7.142857 0.000000 7.142857 0.000000 0.000000 14.285714
## 162 163 164 165 166 167 168
## 0.000000 0.000000 7.142857 0.000000 7.142857 7.142857 7.142857
## 169 170 171 172 173 174 175
## 7.142857 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000
## 176 177 178 179 180 181 182
## 7.142857 7.142857 7.142857 7.142857 0.000000 7.142857 0.000000
## 183 184 185 186 187 188 189
## 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000
## 190 191 192 193 194 195 196
## 0.000000 14.285714 14.285714 7.142857 0.000000 0.000000 0.000000
## 197 198 199 200 201 202 203
## 7.142857 7.142857 0.000000 7.142857 0.000000 7.142857 7.142857
## 204 205 206 207 208 209 210
## 0.000000 7.142857 14.285714 7.142857 0.000000 7.142857 0.000000
## 211 212 213 214 215 216 217
## 0.000000 0.000000 0.000000 7.142857 0.000000 0.000000 0.000000
## 218 219 220 221 222 223 224
## 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
## 225 226 227 228 229 230 231
## 14.285714 7.142857 14.285714 7.142857 0.000000 0.000000 0.000000
## 232 233 234 235 236 237 238
## 0.000000 0.000000 7.142857 0.000000 7.142857 7.142857 0.000000
## 239 240 241 242 243 244 245
## 0.000000 0.000000 0.000000 0.000000 7.142857 0.000000 0.000000
## 246 247 248 249 250 251 252
## 7.142857 7.142857 0.000000 7.142857 0.000000 7.142857 0.000000
## 253 254 255 256 257 258 259
## 0.000000 7.142857 0.000000 0.000000 7.142857 7.142857 0.000000
## 260 261 262 263 264 265 266
## 0.000000 0.000000 7.142857 7.142857 0.000000 7.142857 0.000000
## 267 268 269 270 271 272 273
## 7.142857 0.000000 0.000000 7.142857 0.000000 7.142857 0.000000
## 274 275 276 277 278 279 280
## 7.142857 14.285714 0.000000 0.000000 0.000000 0.000000 0.000000
## 281 282 283 284 285 286 287
## 0.000000 0.000000 7.142857 7.142857 7.142857 7.142857 0.000000
## 288 289 290 291 292 293 294
## 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000
## 295 296 297 298 299 300 301
## 7.142857 0.000000 7.142857 0.000000 0.000000 0.000000 7.142857
## 302 303 304 305 306 307 308
## 0.000000 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000
## 309 310 311 312 313 314 315
## 7.142857 0.000000 14.285714 0.000000 0.000000 0.000000 7.142857
## 316 317 318 319 320 321 322
## 0.000000 7.142857 0.000000 0.000000 7.142857 7.142857 0.000000
## 323 324 325 326 327 328 329
## 0.000000 7.142857 0.000000 7.142857 0.000000 7.142857 7.142857
## 330 331 332 333 334 335 336
## 7.142857 0.000000 0.000000 0.000000 7.142857 14.285714 0.000000
## 337 338 339 340 341 342 343
## 7.142857 0.000000 7.142857 0.000000 7.142857 0.000000 0.000000
## 344 345 346 347 348 349 350
## 0.000000 0.000000 0.000000 0.000000 7.142857 7.142857 0.000000
## 351 352 353 354 355 356 357
## 0.000000 0.000000 0.000000 0.000000 7.142857 0.000000 7.142857
## 358 359 360 361 362 363 364
## 7.142857 0.000000 0.000000 7.142857 0.000000 7.142857 0.000000
## 365 366 367 368 369 370 371
## 0.000000 0.000000 0.000000 0.000000 7.142857 0.000000 7.142857
## 372 373 374 375 376 377 378
## 0.000000 0.000000 0.000000 14.285714 0.000000 14.285714 0.000000
## 379 380 381 382 383 384 385
## 0.000000 0.000000 0.000000 7.142857 0.000000 0.000000 0.000000
## 386 387 388 389 390 391 392
## 0.000000 7.142857 0.000000 0.000000 7.142857 0.000000 0.000000
## 393 394 395 396 397 398 399
## 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000 7.142857
## 400 401 402 403 404 405 406
## 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000
## 407 408 409 410 411 412 413
## 0.000000 0.000000 7.142857 0.000000 0.000000 0.000000 0.000000
## 414 415 416 417 418 419 420
## 7.142857 7.142857 0.000000 0.000000 0.000000 0.000000 0.000000
## 421 422 423 424 425 426 427
## 0.000000 0.000000 0.000000 7.142857 0.000000 0.000000 0.000000
## 428 429 430 431 432 433 434
## 0.000000 7.142857 0.000000 0.000000 0.000000 7.142857 7.142857
## 435 436 437 438 439 440 441
## 0.000000 0.000000 0.000000 0.000000 0.000000 7.142857 0.000000
## 442 443 444 445 446 447 448
## 7.142857 0.000000 7.142857 14.285714 7.142857 7.142857 0.000000
## 449 450 451 452 453 454 455
## 7.142857 0.000000 0.000000 0.000000 7.142857 0.000000 0.000000
## 456 457 458 459 460 461 462
## 7.142857 0.000000 14.285714 14.285714 0.000000 0.000000 0.000000
## 463 464 465 466 467 468 469
## 7.142857 7.142857 7.142857 0.000000 7.142857 7.142857 0.000000
## 470 471 472 473 474 475 476
## 14.285714 0.000000 0.000000 7.142857 7.142857 7.142857 0.000000
## 477 478 479 480 481 482 483
## 7.142857 0.000000 0.000000 0.000000 14.285714 0.000000 7.142857
## 484 485 486 487 488 489 490
## 0.000000 0.000000 0.000000 7.142857 0.000000 7.142857 7.142857
## 491 492 493 494 495 496 497
## 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
## 498 499 500 501 502 503 504
## 0.000000 0.000000 7.142857 7.142857 0.000000 0.000000 0.000000
## 505 506
## 0.000000 7.142857library(mice)
md.pattern(BostonHousing)## crim zn indus chas nox rm age dis rad tax lstat medv ptratio b
## 326 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0
## 80 1 1 1 1 1 1 1 1 1 1 1 1 0 1 1
## 80 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1
## 20 1 1 1 1 1 1 1 1 1 1 1 1 0 0 2
## 0 0 0 0 0 0 0 0 0 0 0 0 100 100 200library(VIM)## Loading required package: colorspace## Loading required package: grid## Loading required package: data.table##
## Attaching package: 'data.table'## The following objects are masked from 'package:dplyr':
##
## between, first, last## VIM is ready to use.
## Since version 4.0.0 the GUI is in its own package VIMGUI.
##
## Please use the package to use the new (and old) GUI.## Suggestions and bug-reports can be submitted at: https://github.com/alexkowa/VIM/issues##
## Attaching package: 'VIM'## The following object is masked from 'package:datasets':
##
## sleepaggr_plot <- aggr(BostonHousing, col=c('navyblue','red'),
numbers=TRUE,
sortVars=TRUE,
labels=names(BostonHousing),
cex.axis=.7,
gap=3,
ylab=c("Histogram of missing data","Pattern"))
##
## Variables sorted by number of missings:
## Variable Count
## ptratio 0.1976285
## b 0.1976285
## crim 0.0000000
## zn 0.0000000
## indus 0.0000000
## chas 0.0000000
## nox 0.0000000
## rm 0.0000000
## age 0.0000000
## dis 0.0000000
## rad 0.0000000
## tax 0.0000000
## lstat 0.0000000
## medv 0.0000000imputed <- mice(BostonHousing,m=5,maxit=50,meth='pmm',seed=500)##
## iter imp variable
## 1 1 ptratio b
## 1 2 ptratio b
## 1 3 ptratio b
## 1 4 ptratio b
## 1 5 ptratio b
## 2 1 ptratio b
## 2 2 ptratio b
## 2 3 ptratio b
## 2 4 ptratio b
## 2 5 ptratio b
## 3 1 ptratio b
## 3 2 ptratio b
## 3 3 ptratio b
## 3 4 ptratio b
## 3 5 ptratio b
## 4 1 ptratio b
## 4 2 ptratio b
## 4 3 ptratio b
## 4 4 ptratio b
## 4 5 ptratio b
## 5 1 ptratio b
## 5 2 ptratio b
## 5 3 ptratio b
## 5 4 ptratio b
## 5 5 ptratio b
## 6 1 ptratio b
## 6 2 ptratio b
## 6 3 ptratio b
## 6 4 ptratio b
## 6 5 ptratio b
## 7 1 ptratio b
## 7 2 ptratio b
## 7 3 ptratio b
## 7 4 ptratio b
## 7 5 ptratio b
## 8 1 ptratio b
## 8 2 ptratio b
## 8 3 ptratio b
## 8 4 ptratio b
## 8 5 ptratio b
## 9 1 ptratio b
## 9 2 ptratio b
## 9 3 ptratio b
## 9 4 ptratio b
## 9 5 ptratio b
## 10 1 ptratio b
## 10 2 ptratio b
## 10 3 ptratio b
## 10 4 ptratio b
## 10 5 ptratio b
## 11 1 ptratio b
## 11 2 ptratio b
## 11 3 ptratio b
## 11 4 ptratio b
## 11 5 ptratio b
## 12 1 ptratio b
## 12 2 ptratio b
## 12 3 ptratio b
## 12 4 ptratio b
## 12 5 ptratio b
## 13 1 ptratio b
## 13 2 ptratio b
## 13 3 ptratio b
## 13 4 ptratio b
## 13 5 ptratio b
## 14 1 ptratio b
## 14 2 ptratio b
## 14 3 ptratio b
## 14 4 ptratio b
## 14 5 ptratio b
## 15 1 ptratio b
## 15 2 ptratio b
## 15 3 ptratio b
## 15 4 ptratio b
## 15 5 ptratio b
## 16 1 ptratio b
## 16 2 ptratio b
## 16 3 ptratio b
## 16 4 ptratio b
## 16 5 ptratio b
## 17 1 ptratio b
## 17 2 ptratio b
## 17 3 ptratio b
## 17 4 ptratio b
## 17 5 ptratio b
## 18 1 ptratio b
## 18 2 ptratio b
## 18 3 ptratio b
## 18 4 ptratio b
## 18 5 ptratio b
## 19 1 ptratio b
## 19 2 ptratio b
## 19 3 ptratio b
## 19 4 ptratio b
## 19 5 ptratio b
## 20 1 ptratio b
## 20 2 ptratio b
## 20 3 ptratio b
## 20 4 ptratio b
## 20 5 ptratio b
## 21 1 ptratio b
## 21 2 ptratio b
## 21 3 ptratio b
## 21 4 ptratio b
## 21 5 ptratio b
## 22 1 ptratio b
## 22 2 ptratio b
## 22 3 ptratio b
## 22 4 ptratio b
## 22 5 ptratio b
## 23 1 ptratio b
## 23 2 ptratio b
## 23 3 ptratio b
## 23 4 ptratio b
## 23 5 ptratio b
## 24 1 ptratio b
## 24 2 ptratio b
## 24 3 ptratio b
## 24 4 ptratio b
## 24 5 ptratio b
## 25 1 ptratio b
## 25 2 ptratio b
## 25 3 ptratio b
## 25 4 ptratio b
## 25 5 ptratio b
## 26 1 ptratio b
## 26 2 ptratio b
## 26 3 ptratio b
## 26 4 ptratio b
## 26 5 ptratio b
## 27 1 ptratio b
## 27 2 ptratio b
## 27 3 ptratio b
## 27 4 ptratio b
## 27 5 ptratio b
## 28 1 ptratio b
## 28 2 ptratio b
## 28 3 ptratio b
## 28 4 ptratio b
## 28 5 ptratio b
## 29 1 ptratio b
## 29 2 ptratio b
## 29 3 ptratio b
## 29 4 ptratio b
## 29 5 ptratio b
## 30 1 ptratio b
## 30 2 ptratio b
## 30 3 ptratio b
## 30 4 ptratio b
## 30 5 ptratio b
## 31 1 ptratio b
## 31 2 ptratio b
## 31 3 ptratio b
## 31 4 ptratio b
## 31 5 ptratio b
## 32 1 ptratio b
## 32 2 ptratio b
## 32 3 ptratio b
## 32 4 ptratio b
## 32 5 ptratio b
## 33 1 ptratio b
## 33 2 ptratio b
## 33 3 ptratio b
## 33 4 ptratio b
## 33 5 ptratio b
## 34 1 ptratio b
## 34 2 ptratio b
## 34 3 ptratio b
## 34 4 ptratio b
## 34 5 ptratio b
## 35 1 ptratio b
## 35 2 ptratio b
## 35 3 ptratio b
## 35 4 ptratio b
## 35 5 ptratio b
## 36 1 ptratio b
## 36 2 ptratio b
## 36 3 ptratio b
## 36 4 ptratio b
## 36 5 ptratio b
## 37 1 ptratio b
## 37 2 ptratio b
## 37 3 ptratio b
## 37 4 ptratio b
## 37 5 ptratio b
## 38 1 ptratio b
## 38 2 ptratio b
## 38 3 ptratio b
## 38 4 ptratio b
## 38 5 ptratio b
## 39 1 ptratio b
## 39 2 ptratio b
## 39 3 ptratio b
## 39 4 ptratio b
## 39 5 ptratio b
## 40 1 ptratio b
## 40 2 ptratio b
## 40 3 ptratio b
## 40 4 ptratio b
## 40 5 ptratio b
## 41 1 ptratio b
## 41 2 ptratio b
## 41 3 ptratio b
## 41 4 ptratio b
## 41 5 ptratio b
## 42 1 ptratio b
## 42 2 ptratio b
## 42 3 ptratio b
## 42 4 ptratio b
## 42 5 ptratio b
## 43 1 ptratio b
## 43 2 ptratio b
## 43 3 ptratio b
## 43 4 ptratio b
## 43 5 ptratio b
## 44 1 ptratio b
## 44 2 ptratio b
## 44 3 ptratio b
## 44 4 ptratio b
## 44 5 ptratio b
## 45 1 ptratio b
## 45 2 ptratio b
## 45 3 ptratio b
## 45 4 ptratio b
## 45 5 ptratio b
## 46 1 ptratio b
## 46 2 ptratio b
## 46 3 ptratio b
## 46 4 ptratio b
## 46 5 ptratio b
## 47 1 ptratio b
## 47 2 ptratio b
## 47 3 ptratio b
## 47 4 ptratio b
## 47 5 ptratio b
## 48 1 ptratio b
## 48 2 ptratio b
## 48 3 ptratio b
## 48 4 ptratio b
## 48 5 ptratio b
## 49 1 ptratio b
## 49 2 ptratio b
## 49 3 ptratio b
## 49 4 ptratio b
## 49 5 ptratio b
## 50 1 ptratio b
## 50 2 ptratio b
## 50 3 ptratio b
## 50 4 ptratio b
## 50 5 ptratio bsummary(imputed)## Multiply imputed data set
## Call:
## mice(data = BostonHousing, m = 5, method = "pmm", maxit = 50,
## seed = 500)
## Number of multiple imputations: 5
## Missing cells per column:
## crim zn indus chas nox rm age dis rad
## 0 0 0 0 0 0 0 0 0
## tax ptratio b lstat medv
## 0 100 100 0 0
## Imputation methods:
## crim zn indus chas nox rm age dis rad
## "pmm" "pmm" "pmm" "pmm" "pmm" "pmm" "pmm" "pmm" "pmm"
## tax ptratio b lstat medv
## "pmm" "pmm" "pmm" "pmm" "pmm"
## VisitSequence:
## ptratio b
## 11 12
## PredictorMatrix:
## crim zn indus chas nox rm age dis rad tax ptratio b lstat medv
## crim 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## zn 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## indus 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## chas 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## nox 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## rm 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## age 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## dis 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## rad 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## tax 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## ptratio 1 1 1 1 1 1 1 1 1 1 0 1 1 1
## b 1 1 1 1 1 1 1 1 1 1 1 0 1 1
## lstat 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## medv 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## Random generator seed value: 500completed <- complete(imputed,1)
library(lattice)
xyplot(imputed, b ~ ptratio,pch=18,cex=1)