library(readr)
## Warning: package 'readr' was built under R version 3.6.1
ma <- read_csv("~/RPy Analytics/Betty Tigere/ma.csv")
## Parsed with column specification:
## cols(
## var_2 = col_double(),
## var_3 = col_double(),
## var_4 = col_double(),
## var_5 = col_double()
## )
#View(ma)
attach(ma)
### loading the require packages
library(mice)
## Warning: package 'mice' was built under R version 3.6.1
## Loading required package: lattice
##
## Attaching package: 'mice'
## The following objects are masked from 'package:base':
##
## cbind, rbind
library(VIM)
## Warning: package 'VIM' was built under R version 3.6.1
## Loading required package: colorspace
## Warning: package 'colorspace' was built under R version 3.6.1
## Loading required package: grid
## Loading required package: data.table
## Warning: package 'data.table' was built under R version 3.6.1
## Registered S3 methods overwritten by 'car':
## method from
## influence.merMod lme4
## cooks.distance.influence.merMod lme4
## dfbeta.influence.merMod lme4
## dfbetas.influence.merMod lme4
## 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':
##
## sleep
md.pattern(ma)
## var_2 var_3 var_4 var_5
## 34 1 1 1 1 0
## 2 1 0 0 0 3
## 0 2 2 2 6
p<-md.pairs(ma)
p
## $rr
## var_2 var_3 var_4 var_5
## var_2 36 34 34 34
## var_3 34 34 34 34
## var_4 34 34 34 34
## var_5 34 34 34 34
##
## $rm
## var_2 var_3 var_4 var_5
## var_2 0 2 2 2
## var_3 0 0 0 0
## var_4 0 0 0 0
## var_5 0 0 0 0
##
## $mr
## var_2 var_3 var_4 var_5
## var_2 0 0 0 0
## var_3 2 0 0 0
## var_4 2 0 0 0
## var_5 2 0 0 0
##
## $mm
## var_2 var_3 var_4 var_5
## var_2 0 0 0 0
## var_3 0 2 2 2
## var_4 0 2 2 2
## var_5 0 2 2 2
summary(p)
## Length Class Mode
## rr 16 -none- numeric
## rm 16 -none- numeric
## mr 16 -none- numeric
## mm 16 -none- numeric
boxplot(ma[,1:3])
###plot
pbox(var_3,int=FALSE,cex=0.7)
imp<-mice(ma)
##
## iter imp variable
## 1 1 var_3 var_4 var_5
## 1 2 var_3 var_4 var_5
## 1 3 var_3 var_4 var_5
## 1 4 var_3 var_4 var_5
## 1 5 var_3 var_4 var_5
## 2 1 var_3 var_4 var_5
## 2 2 var_3 var_4 var_5
## 2 3 var_3 var_4 var_5
## 2 4 var_3 var_4 var_5
## 2 5 var_3 var_4 var_5
## 3 1 var_3 var_4 var_5
## 3 2 var_3 var_4 var_5
## 3 3 var_3 var_4 var_5
## 3 4 var_3 var_4 var_5
## 3 5 var_3 var_4 var_5
## 4 1 var_3 var_4 var_5
## 4 2 var_3 var_4 var_5
## 4 3 var_3 var_4 var_5
## 4 4 var_3 var_4 var_5
## 4 5 var_3 var_4 var_5
## 5 1 var_3 var_4 var_5
## 5 2 var_3 var_4 var_5
## 5 3 var_3 var_4 var_5
## 5 4 var_3 var_4 var_5
## 5 5 var_3 var_4 var_5
imp$imp$var_3
## 1 2 3 4 5
## 3 0 0 1 0 0
## 35 0 0 1 0 0
head(complete(imp))
## var_2 var_3 var_4 var_5
## 1 8 1 0 95
## 2 16 0 0 96
## 3 9 0 0 96
## 4 7 1 0 96
## 5 1 0 2 96
## 6 4 3 9 96
head(complete(imp,2))
## var_2 var_3 var_4 var_5
## 1 8 1 0 95
## 2 16 0 0 96
## 3 9 0 0 99
## 4 7 1 0 96
## 5 1 0 2 96
## 6 4 3 9 96
summary(lm(var_2~var_3+var_4+var_5,data = ma))
##
## Call:
## lm(formula = var_2 ~ var_3 + var_4 + var_5, data = ma)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8.3532 -3.5811 -0.2992 4.5455 7.5348
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 19.3813 52.2977 0.371 0.7135
## var_3 1.4608 0.8083 1.807 0.0808 .
## var_4 -0.7540 0.2802 -2.691 0.0115 *
## var_5 -0.1013 0.5383 -0.188 0.8520
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.097 on 30 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.1951, Adjusted R-squared: 0.1146
## F-statistic: 2.424 on 3 and 30 DF, p-value: 0.08515
confint(lm(var_2~var_3+var_4+var_5,data = ma))
## 2.5 % 97.5 %
## (Intercept) -87.4249652 126.1874897
## var_3 -0.1899145 3.1115568
## var_4 -1.3261946 -0.1817197
## var_5 -1.2005469 0.9979596
## multiple imputation
fit<-with(imp,lm(var_2~var_3+var_4+var_5,data = ma))
pool(fit)
## Class: mipo m = 5
## estimate ubar b t dfcom df riv lambda
## (Intercept) 19.3812622 2.735053e+03 0 2.735053e+03 30 28.179 0 0
## var_3 1.4608212 6.533226e-01 0 6.533226e-01 30 28.179 0 0
## var_4 -0.7539571 7.851003e-02 0 7.851003e-02 30 28.179 0 0
## var_5 -0.1012936 2.897131e-01 0 2.897131e-01 30 28.179 0 0
## fmi
## (Intercept) 0.06414574
## var_3 0.06414574
## var_4 0.06414574
## var_5 0.06414574
summary(pool(fit))
## estimate std.error statistic df p.value
## (Intercept) 19.3812622 52.2977368 0.3705947 28.179 0.71371079
## var_3 1.4608212 0.8082838 1.8073123 28.179 0.08140177
## var_4 -0.7539571 0.2801964 -2.6908165 28.179 0.01185125
## var_5 -0.1012936 0.5382501 -0.1881907 28.179 0.85207588