BINNING.knit

title: “DESCRIPTIVE STATISTICS IN R-STUDIO” author: “mugo_muiruri_james” date: “2023-09-20” output: html_document: df_print: paged word_document: default

library(psych)
library(sjPlot)
library(table1)

## 
## Attaching package: 'table1'

## The following objects are masked from 'package:base':
## 
##     units, units<-

data("iris")
attach(iris)
summary(iris)

##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
##

describeBy(iris)

## Warning in describeBy(iris): no grouping variable requested

##              vars   n mean   sd median trimmed  mad min max range  skew
## Sepal.Length    1 150 5.84 0.83   5.80    5.81 1.04 4.3 7.9   3.6  0.31
## Sepal.Width     2 150 3.06 0.44   3.00    3.04 0.44 2.0 4.4   2.4  0.31
## Petal.Length    3 150 3.76 1.77   4.35    3.76 1.85 1.0 6.9   5.9 -0.27
## Petal.Width     4 150 1.20 0.76   1.30    1.18 1.04 0.1 2.5   2.4 -0.10
## Species*        5 150 2.00 0.82   2.00    2.00 1.48 1.0 3.0   2.0  0.00
##              kurtosis   se
## Sepal.Length    -0.61 0.07
## Sepal.Width      0.14 0.04
## Petal.Length    -1.42 0.14
## Petal.Width     -1.36 0.06
## Species*        -1.52 0.07

kableExtra:: kable_styling(kableExtra::kable(describeBy(iris), digits = 2), bootstrap_options=c("bordered", "responsive", "striped"), full_width = FALSE)

## Warning in describeBy(iris): no grouping variable requested

	vars	n	mean	sd	median	trimmed	mad	min	max	range	skew	kurtosis	se
Sepal.Length	1	150	5.84	0.83	5.80	5.81	1.04	4.3	7.9	3.6	0.31	-0.61	0.07
Sepal.Width	2	150	3.06	0.44	3.00	3.04	0.44	2.0	4.4	2.4	0.31	0.14	0.04
Petal.Length	3	150	3.76	1.77	4.35	3.76	1.85	1.0	6.9	5.9	-0.27	-1.42	0.14
Petal.Width	4	150	1.20	0.76	1.30	1.18	1.04	0.1	2.5	2.4	-0.10	-1.36	0.06
Species*	5	150	2.00	0.82	2.00	2.00	1.48	1.0	3.0	2.0	0.00	-1.52	0.07

table1(~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width | Species, data = iris)

	setosa (N=50)	versicolor (N=50)	virginica (N=50)	Overall (N=150)
Sepal.Length
Mean (SD)	5.01 (0.352)	5.94 (0.516)	6.59 (0.636)	5.84 (0.828)
Median [Min, Max]	5.00 [4.30, 5.80]	5.90 [4.90, 7.00]	6.50 [4.90, 7.90]	5.80 [4.30, 7.90]
Sepal.Width
Mean (SD)	3.43 (0.379)	2.77 (0.314)	2.97 (0.322)	3.06 (0.436)
Median [Min, Max]	3.40 [2.30, 4.40]	2.80 [2.00, 3.40]	3.00 [2.20, 3.80]	3.00 [2.00, 4.40]
Petal.Length
Mean (SD)	1.46 (0.174)	4.26 (0.470)	5.55 (0.552)	3.76 (1.77)
Median [Min, Max]	1.50 [1.00, 1.90]	4.35 [3.00, 5.10]	5.55 [4.50, 6.90]	4.35 [1.00, 6.90]
Petal.Width
Mean (SD)	0.246 (0.105)	1.33 (0.198)	2.03 (0.275)	1.20 (0.762)
Median [Min, Max]	0.200 [0.100, 0.600]	1.30 [1.00, 1.80]	2.00 [1.40, 2.50]	1.30 [0.100, 2.50]

mod1 <- lm(Sepal.Length ~ Petal.Length, data = iris)
summary(mod1)

## 
## Call:
## lm(formula = Sepal.Length ~ Petal.Length, data = iris)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1.24675 -0.29657 -0.01515  0.27676  1.00269 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   4.30660    0.07839   54.94   <2e-16 ***
## Petal.Length  0.40892    0.01889   21.65   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.4071 on 148 degrees of freedom
## Multiple R-squared:   0.76,  Adjusted R-squared:  0.7583 
## F-statistic: 468.6 on 1 and 148 DF,  p-value: < 2.2e-16

mod2 <- lm(Sepal.Length ~ Petal.Length + Petal.Width, data = iris)
summary(mod2)

## 
## Call:
## lm(formula = Sepal.Length ~ Petal.Length + Petal.Width, data = iris)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1.18534 -0.29838 -0.02763  0.28925  1.02320 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   4.19058    0.09705  43.181  < 2e-16 ***
## Petal.Length  0.54178    0.06928   7.820 9.41e-13 ***
## Petal.Width  -0.31955    0.16045  -1.992   0.0483 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.4031 on 147 degrees of freedom
## Multiple R-squared:  0.7663, Adjusted R-squared:  0.7631 
## F-statistic:   241 on 2 and 147 DF,  p-value: < 2.2e-16

tab_model(mod1, mod2)

	Sepal Length			Sepal Length
Predictors	Estimates	CI	p	Estimates	CI	p
(Intercept)	4.31	4.15 – 4.46	<0.001	4.19	4.00 – 4.38	<0.001
Petal Length	0.41	0.37 – 0.45	<0.001	0.54	0.40 – 0.68	<0.001
Petal Width				-0.32	-0.64 – -0.00	0.048
Observations	150			150
R² / R² adjusted	0.760 / 0.758			0.766 / 0.763

correlation tables

tab_corr(iris[ , 1:4])

	Sepal.Length	Sepal.Width	Petal.Length	Petal.Width
Sepal.Length		-0.118	0.872***	0.818***
Sepal.Width	-0.118		-0.428***	-0.366***
Petal.Length	0.872***	-0.428***		0.963***
Petal.Width	0.818***	-0.366***	0.963***
Computed correlation used pearson-method with listwise-deletion.