350.week2b
William Revelle
4/13/20
Using the psych package for descriptive statistics
library(psych) #make it active
library(psychTools) #make it active (necessary for read.file)
#specifiy a file to read (e.g.)
filename <- "http://personality-project.org/r/datasets/simulation.txt"
#read the file
my.data <- read.file(filename)## Data from the .txt file http://personality-project.org/r/datasets/simulation.txt has been loaded.#Get basic descriptives
First, find out how many rows and columns and then, if not too many, show a few
dim(my.data)## [1] 72 7names(my.data)## [1] "Time" "Anxiety" "Impulsivity" "sex" "Arousal" "Tension"
## [7] "Performance"headTail(my.data)## Time Anxiety Impulsivity sex Arousal Tension Performance
## 1 9 4 9 1 50 55 40
## 2 19 8 8 1 70 64 90
## 3 9 5 10 2 50 69 48
## 4 9 4 1 2 57 55 68
## ... ... ... ... ... ... ... ...
## 69 19 6 1 1 66 53 88
## 70 9 5 10 2 48 63 40
## 71 19 6 8 2 69 60 95
## 72 19 10 1 2 66 48 93Then get the basic desriptive statistics
describe(my.data)## vars n mean sd median trimmed mad min max range skew kurtosis se
## Time 1 72 14.28 5.03 19.0 14.34 0.00 9 19 10 -0.11 -2.02 0.59
## Anxiety 2 72 5.24 2.18 5.0 5.24 2.97 0 10 10 -0.04 -0.65 0.26
## Impulsivity 3 72 4.90 3.98 4.5 4.88 5.19 0 10 10 0.02 -1.83 0.47
## sex 4 72 1.50 0.50 1.5 1.50 0.74 1 2 1 0.00 -2.03 0.06
## Arousal 5 72 60.90 8.10 66.0 61.29 5.93 48 70 22 -0.27 -1.67 0.96
## Tension 6 72 56.83 6.29 57.0 57.14 5.93 38 69 31 -0.53 0.42 0.74
## Performance 7 72 72.21 17.41 78.0 73.19 18.53 38 98 60 -0.43 -1.10 2.05#Basic descriptive graphs Box plots and violins
boxplot(my.data[5:7])
violinBy(my.data)
#descriptives by groups
describeBy(my.data,"sex")##
## Descriptive statistics by group
## group: 1
## vars n mean sd median trimmed mad min max range skew kurtosis se
## Time 1 36 14.56 5.04 19 14.67 0.00 9 19 10 -0.21 -2.01 0.84
## Anxiety 2 36 5.50 1.93 5 5.53 1.48 1 9 8 -0.08 -0.68 0.32
## Impulsivity 3 36 4.64 4.06 2 4.57 2.97 0 10 10 0.11 -1.86 0.68
## sex 4 36 1.00 0.00 1 1.00 0.00 1 1 0 NaN NaN 0.00
## Arousal 5 36 61.39 7.97 66 61.83 5.93 48 70 22 -0.39 -1.55 1.33
## Tension 6 36 56.58 6.65 56 56.90 5.19 38 68 30 -0.49 0.42 1.11
## Performance 7 36 72.69 17.30 78 73.57 17.79 40 98 58 -0.48 -1.17 2.88
## ---------------------------------------------------------------------------
## group: 2
## vars n mean sd median trimmed mad min max range skew kurtosis se
## Time 1 36 14.00 5.07 14.0 14.00 7.41 9 19 10 0.00 -2.05 0.85
## Anxiety 2 36 4.97 2.40 5.0 4.90 2.97 0 10 10 0.09 -0.84 0.40
## Impulsivity 3 36 5.17 3.93 7.5 5.20 3.71 0 10 10 -0.07 -1.85 0.66
## sex 4 36 2.00 0.00 2.0 2.00 0.00 2 2 0 NaN NaN 0.00
## Arousal 5 36 60.42 8.32 61.5 60.63 11.12 48 70 22 -0.14 -1.81 1.39
## Tension 6 36 57.08 5.99 58.0 57.40 5.19 41 69 28 -0.53 0.07 1.00
## Performance 7 36 71.72 17.74 75.5 72.53 18.53 38 98 60 -0.37 -1.13 2.96violinBy(my.data,grp="sex")
violinBy(bfi[1:25])
#Now lets try some bivariate descriptives – The correlation
cor(my.data) #the traditional output## Time Anxiety Impulsivity sex Arousal Tension Performance
## Time 1.00000000 0.013216858 0.06121135 -0.05564149 0.956608901 0.05050668 0.87406181
## Anxiety 0.01321686 1.000000000 0.15052463 -0.12197796 0.002116381 0.34330479 0.04696584
## Impulsivity 0.06121135 0.150524635 1.00000000 0.06677940 -0.065812947 0.08773475 -0.15565556
## sex -0.05564149 -0.121977956 0.06677940 1.00000000 -0.060408880 0.04004630 -0.02812176
## Arousal 0.95660890 0.002116381 -0.06581295 -0.06040888 1.000000000 0.05358998 0.91904738
## Tension 0.05050668 0.343304791 0.08773475 0.04004630 0.053589983 1.00000000 0.02194427
## Performance 0.87406181 0.046965844 -0.15565556 -0.02812176 0.919047382 0.02194427 1.00000000lowerCor(my.data) #just find the correlations but show them as a lower off diagonal output## Time Anxty Impls sex Arosl Tensn Prfrm
## Time 1.00
## Anxiety 0.01 1.00
## Impulsivity 0.06 0.15 1.00
## sex -0.06 -0.12 0.07 1.00
## Arousal 0.96 0.00 -0.07 -0.06 1.00
## Tension 0.05 0.34 0.09 0.04 0.05 1.00
## Performance 0.87 0.05 -0.16 -0.03 0.92 0.02 1.00corPlot(my.data,numbers=FALSE) #show them in a heat map without showing values
corPlot(my.data) #with the values
corPlot(my.data, numbers = TRUE, stars=TRUE) # with magic astericks
corPlot(my.data,numbers=TRUE,upper=FALSE,diag=FALSE)
# Lets try some more conventional ways of showing it
cor.test(my.data[,1],my.data[,2])##
## Pearson's product-moment correlation
##
## data: my.data[, 1] and my.data[, 2]
## t = 0.11059, df = 70, p-value = 0.9123
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.2191226 0.2441379
## sample estimates:
## cor
## 0.01321686corr.test(my.data)## Call:corr.test(x = my.data)
## Correlation matrix
## Time Anxiety Impulsivity sex Arousal Tension Performance
## Time 1.00 0.01 0.06 -0.06 0.96 0.05 0.87
## Anxiety 0.01 1.00 0.15 -0.12 0.00 0.34 0.05
## Impulsivity 0.06 0.15 1.00 0.07 -0.07 0.09 -0.16
## sex -0.06 -0.12 0.07 1.00 -0.06 0.04 -0.03
## Arousal 0.96 0.00 -0.07 -0.06 1.00 0.05 0.92
## Tension 0.05 0.34 0.09 0.04 0.05 1.00 0.02
## Performance 0.87 0.05 -0.16 -0.03 0.92 0.02 1.00
## Sample Size
## [1] 72
## Probability values (Entries above the diagonal are adjusted for multiple tests.)
## Time Anxiety Impulsivity sex Arousal Tension Performance
## Time 0.00 1.00 1.00 1.00 0.00 1.00 0
## Anxiety 0.91 0.00 1.00 1.00 1.00 0.06 1
## Impulsivity 0.61 0.21 0.00 1.00 1.00 1.00 1
## sex 0.64 0.31 0.58 0.00 1.00 1.00 1
## Arousal 0.00 0.99 0.58 0.61 0.00 1.00 0
## Tension 0.67 0.00 0.46 0.74 0.65 0.00 1
## Performance 0.00 0.70 0.19 0.81 0.00 0.85 0
##
## To see confidence intervals of the correlations, print with the short=FALSE option#What about bootstrap resampling?
ci <- corCi(my.data)
cor.plot.upperLowerCi(ci) #with the confidence intervals