rm(list = ls()) # Clear environment-remove all files from your workspace
gc() # Clear unused memory used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)
Ncells 609480 32.6 1382550 73.9 NA 717642 38.4
Vcells 1121154 8.6 8388608 64.0 16384 2013586 15.4cat("\f") # Clear the consolegraphics.off() # Clear all graphsThe data was extracted from the 1974 Motor Trend US magazine, and comprises fuel consumption and 10 aspects of automobile design and performance for 32 automobiles (1973–74 models).
A data frame with 32 observations on 11 (numeric) variables.
| [, 1] | mpg |
Miles/(US) gallon |
| [, 2] | cyl |
Number of cylinders |
| [, 3] | disp |
Displacement (cu.in.) |
| [, 4] | hp |
Gross horsepower |
| [, 5] | drat |
Rear axle ratio |
| [, 6] | wt |
Weight (1000 lbs) |
| [, 7] | qsec |
1/4 mile time |
| [, 8] | vs |
Engine (0 = V-shaped, 1 = straight) |
| [, 9] | am |
Transmission (0 = automatic, 1 = manual) |
| [,10] | gear |
Number of forward gears |
| [,11] | carb |
Number of carburetors |
?datasets # Base R datasets
?mtcars
mtcars mpg cyl disp hp drat wt qsec vs am gear carb
Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2df <- mtcars # assignment operatorComment out with # manually
Code -> Uncomment/Comment Lines
Control/hide the code chunk options.
Lets use describe describe() describe describe finction from the psych package.
library(psych)
?describe
describe(x = df) # more readable vars n mean sd median trimmed mad min max range skew
mpg 1 32 20.09 6.03 19.20 19.70 5.41 10.40 33.90 23.50 0.61
cyl 2 32 6.19 1.79 6.00 6.23 2.97 4.00 8.00 4.00 -0.17
disp 3 32 230.72 123.94 196.30 222.52 140.48 71.10 472.00 400.90 0.38
hp 4 32 146.69 68.56 123.00 141.19 77.10 52.00 335.00 283.00 0.73
drat 5 32 3.60 0.53 3.70 3.58 0.70 2.76 4.93 2.17 0.27
wt 6 32 3.22 0.98 3.33 3.15 0.77 1.51 5.42 3.91 0.42
qsec 7 32 17.85 1.79 17.71 17.83 1.42 14.50 22.90 8.40 0.37
vs 8 32 0.44 0.50 0.00 0.42 0.00 0.00 1.00 1.00 0.24
am 9 32 0.41 0.50 0.00 0.38 0.00 0.00 1.00 1.00 0.36
gear 10 32 3.69 0.74 4.00 3.62 1.48 3.00 5.00 2.00 0.53
carb 11 32 2.81 1.62 2.00 2.65 1.48 1.00 8.00 7.00 1.05
kurtosis se
mpg -0.37 1.07
cyl -1.76 0.32
disp -1.21 21.91
hp -0.14 12.12
drat -0.71 0.09
wt -0.02 0.17
qsec 0.34 0.32
vs -2.00 0.09
am -1.92 0.09
gear -1.07 0.13
carb 1.26 0.29describe(df) # less readable vars n mean sd median trimmed mad min max range skew
mpg 1 32 20.09 6.03 19.20 19.70 5.41 10.40 33.90 23.50 0.61
cyl 2 32 6.19 1.79 6.00 6.23 2.97 4.00 8.00 4.00 -0.17
disp 3 32 230.72 123.94 196.30 222.52 140.48 71.10 472.00 400.90 0.38
hp 4 32 146.69 68.56 123.00 141.19 77.10 52.00 335.00 283.00 0.73
drat 5 32 3.60 0.53 3.70 3.58 0.70 2.76 4.93 2.17 0.27
wt 6 32 3.22 0.98 3.33 3.15 0.77 1.51 5.42 3.91 0.42
qsec 7 32 17.85 1.79 17.71 17.83 1.42 14.50 22.90 8.40 0.37
vs 8 32 0.44 0.50 0.00 0.42 0.00 0.00 1.00 1.00 0.24
am 9 32 0.41 0.50 0.00 0.38 0.00 0.00 1.00 1.00 0.36
gear 10 32 3.69 0.74 4.00 3.62 1.48 3.00 5.00 2.00 0.53
carb 11 32 2.81 1.62 2.00 2.65 1.48 1.00 8.00 7.00 1.05
kurtosis se
mpg -0.37 1.07
cyl -1.76 0.32
disp -1.21 21.91
hp -0.14 12.12
drat -0.71 0.09
wt -0.02 0.17
qsec 0.34 0.32
vs -2.00 0.09
am -1.92 0.09
gear -1.07 0.13
carb 1.26 0.29# hist(df$hp)Does the package need to have the same name as the function?
No !
psych package has describe function.
stargazer package has stargazer function.
# install.packages("stargazer")
??stargazer # global search
library(stargazer)
Please cite as: Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables. R package version 5.2.3. https://CRAN.R-project.org/package=stargazer ?stargazer # local search
stargazer(df, type = "text", title = "Summary Statistics Table")
Summary Statistics Table
============================================
Statistic N Mean St. Dev. Min Max
--------------------------------------------
mpg 32 20.091 6.027 10.400 33.900
cyl 32 6.188 1.786 4 8
disp 32 230.722 123.939 71.100 472.000
hp 32 146.688 68.563 52 335
drat 32 3.597 0.535 2.760 4.930
wt 32 3.217 0.978 1.513 5.424
qsec 32 17.849 1.787 14.500 22.900
vs 32 0.438 0.504 0 1
am 32 0.406 0.499 0 1
gear 32 3.688 0.738 3 5
carb 32 2.812 1.615 1 8
--------------------------------------------I am not printing the output of the following 3 commands.
stargazer(df,
type = "text",
title = "Summary Statistics Table"
)
stargazer(df,
type = "text",
title = "Summary Statistics Table"
)
stargazer(df, # dataframe/raw data
type = "text", # output
title = "Summary Statistics Table" # title
)More readable code gives arguments for each input into the function, is well alligned, and has comments.
stargazer(... = df, # dataframe/raw data
type = "text", # output
title = "Summary Statistics Table" # title
)
Summary Statistics Table
============================================
Statistic N Mean St. Dev. Min Max
--------------------------------------------
mpg 32 20.091 6.027 10.400 33.900
cyl 32 6.188 1.786 4 8
disp 32 230.722 123.939 71.100 472.000
hp 32 146.688 68.563 52 335
drat 32 3.597 0.535 2.760 4.930
wt 32 3.217 0.978 1.513 5.424
qsec 32 17.849 1.787 14.500 22.900
vs 32 0.438 0.504 0 1
am 32 0.406 0.499 0 1
gear 32 3.688 0.738 3 5
carb 32 2.812 1.615 1 8
--------------------------------------------stargazer(... = df, # dataframe/raw data
type = "text", # output
title = "Summary Statistics Table", # title
digits = 1, # control decimal places
covariate.labels = c("Miles per Gallon", # label variables
"# of Cylinders"
)
)
Summary Statistics Table
=============================================
Statistic N Mean St. Dev. Min Max
---------------------------------------------
Miles per Gallon 32 20.1 6.0 10.4 33.9
# of Cylinders 32 6.2 1.8 4 8
disp 32 230.7 123.9 71.1 472.0
hp 32 146.7 68.6 52 335
drat 32 3.6 0.5 2.8 4.9
wt 32 3.2 1.0 1.5 5.4
qsec 32 17.8 1.8 14.5 22.9
vs 32 0.4 0.5 0 1
am 32 0.4 0.5 0 1
gear 32 3.7 0.7 3 5
carb 32 2.8 1.6 1 8
---------------------------------------------?datasets
#library(help = "datasets")
df <- beaver2
psych::describe(beaver2) vars n mean sd median trimmed mad min max range
day 1 100 307.13 0.34 307.00 307.04 0.00 307.00 308.00 1.00
time 2 100 1446.20 658.97 1535.00 1514.00 607.87 0.00 2350.00 2350.00
temp 3 100 37.60 0.45 37.74 37.61 0.48 36.58 38.35 1.77
activ 4 100 0.62 0.49 1.00 0.65 0.00 0.00 1.00 1.00
skew kurtosis se
day 2.17 2.73 0.03
time -0.80 -0.14 65.90
temp -0.31 -1.22 0.04
activ -0.49 -1.78 0.05plot(df$time, df$temp,
main = "Beaver Body Temperatue Over Time",
xlab = "Time of Day",
ylab = "Temperature (Celsius)",
col = "darkgreen"
)
This data is longitudinal as it measures various different values from different subjects and varying times.