Correlation matrix plot

Reading data

# data are available at https://github.com/tuanvnguyen/Regression-Book/blob/master/Osteo%20data.csv 
df = read.csv("~/Dropbox/_Books and websites/Regression analysis (sach Viet)/Datasets for book/Osteo data.csv")
head(df)

##   id lean.mass fat.mass pcfat age height weight  bmi osta osteo  osteo.group
## 1  1     27.98    16.49 37.09  76  156.0   45.0 18.5  6.2     2 Osteoporosis
## 2  8     29.02    27.54 48.70  54  153.0   56.0 23.9 -0.4     1   Osteopenia
## 3 21     31.72    20.65 39.43  56  158.2   51.5 20.6  0.9     1   Osteopenia
## 4 38     35.96    21.96 37.92  54  154.0   51.0 21.5  0.6     1   Osteopenia
## 5 39     35.00    26.29 42.89  60  159.5   60.0 23.6  0.0     1   Osteopenia
## 6 53     32.58    19.82 37.82  53  156.0   51.0 21.0  0.4     1   Osteopenia

# Select only continuous variables from df 
df1 = df[, c("age", "height", "weight",  "bmi", "lean.mass", "fat.mass", "pcfat")]

Simple correlation matrix plot using package ‘psych’

# Using function pairs.panels on df1 
pairs.panels(df1)

Using package ‘corrplot’

# Calculate correlations
cor.matrix = cor(df1)
corrplot(cor.matrix, method = "circle")

corrplot(cor.matrix, method = "ellipse")

corrplot(cor.matrix, method = "pie")

corrplot.mixed(cor.matrix, lower.col = "black", number.cex = 0.7)

Using ggpairs from package GGally

# can be used on df1, no need to calculate correlation coeff
ggpairs(df1) 

# can be used for grouped data 
df2 = df[, c("osteo.group", "age", "height", "weight",  "bmi", "lean.mass", "fat.mass", "pcfat")]
ggpairs(df2, ggplot2::aes(colour=osteo.group)) 

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.