Bevezetés az R-be 2.0 - Feladatgyűjtemény

Mutatók

Ebben a fejezetben a statisztikai mutatók kiszámítását mutatjuk be. Az R rendkívül sok függvényt kínál, melyek egyfajta csoportosítása a következő lehet:

Egy numerikus változóból
- egy mutató
- több mutató
- csoportonként egy-egy mutató
- csoportonként több mutató
Több numerikus változóból
- egy-egy mutató
- több mutató
- csoportonként egy-egy mutató
- csoportonként több mutató
A teljes adattáblára vonatkozó mutatók

1. feladat. Mutatók
Határozzuk meg a MASS csomag survey adattáblájában a numerikus változók mutatóit a fenti csoportosítás figyelembe vételével!

Adattábla beolvasása

data(survey, package = "MASS") # a survey beolvasása
str(survey)                    # numerikus oszlopok keresése

'data.frame':    237 obs. of  12 variables:
 $ Sex   : Factor w/ 2 levels "Female","Male": 1 2 2 2 2 1 2 1 2 2 ...
 $ Wr.Hnd: num  18.5 19.5 18 18.8 20 18 17.7 17 20 18.5 ...
 $ NW.Hnd: num  18 20.5 13.3 18.9 20 17.7 17.7 17.3 19.5 18.5 ...
 $ W.Hnd : Factor w/ 2 levels "Left","Right": 2 1 2 2 2 2 2 2 2 2 ...
 $ Fold  : Factor w/ 3 levels "L on R","Neither",..: 3 3 1 3 2 1 1 3 3 3 ...
 $ Pulse : int  92 104 87 NA 35 64 83 74 72 90 ...
 $ Clap  : Factor w/ 3 levels "Left","Neither",..: 1 1 2 2 3 3 3 3 3 3 ...
 $ Exer  : Factor w/ 3 levels "Freq","None",..: 3 2 2 2 3 3 1 1 3 3 ...
 $ Smoke : Factor w/ 4 levels "Heavy","Never",..: 2 4 3 2 2 2 2 2 2 2 ...
 $ Height: num  173 178 NA 160 165 ...
 $ M.I   : Factor w/ 2 levels "Imperial","Metric": 2 1 NA 2 2 1 1 2 2 2 ...
 $ Age   : num  18.2 17.6 16.9 20.3 23.7 ...

Egy numerikus változó, egy mutató

mean(survey$Height, na.rm=T)        # átlag

[1] 172.3809

median(survey$Height, na.rm=T)      # medián

[1] 171

sd(survey$Height, na.rm=T)          # szórás

[1] 9.847528

var(survey$Height, na.rm=T)         # szórásnégyzet (variancia)

[1] 96.9738

diff(range(survey$Height, na.rm=T)) # a minta terjedelme

[1] 50

IQR(survey$Height, na.rm=T)         # interkvartilis eltérés

[1] 15

min(survey$Height, na.rm=T)         # minimum

[1] 150

max(survey$Height, na.rm=T)         # maximum

[1] 200

quantile(survey$Height, na.rm=T)    # minimum, kvartilisek és a maximum

  0%  25%  50%  75% 100% 
 150  165  171  180  200

quantile(survey$Height, prob=c(0.33, 0.66), na.rm=T) # a 33 és 66%-os kvantilisek

   33%    66% 
167.64 176.14

mad(survey$Height, na.rm=T)         # mediántól való abszolút eltérés mediánja

[1] 10.08168

library(e1071)
skewness(survey$Height, na.rm=T)    # ferdeségi együttható

[1] 0.2158388

kurtosis(survey$Height, na.rm=T)    # csúcsossági együttható

[1] -0.4374444

Egy numerikus változó, több mutató

A beépített lehetőség: a `summary()` függvény

A summary() outputjában megjelenő mutatók:

Név az outputban	Jelentés
`Min.`	minimum
`1st Qu.`	alsó kvartilis
`Median`	medián
`Mean`	átlag
`3rd Qu.`	felső kvartilis
`Max.`	maximum
`NA's`	hiányzó értékek száma

summary(survey$Height)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  150.0   165.0   171.0   172.4   180.0   200.0      28

Mutatók a `psych` csomagokkal `describe()` függvényével

A psych::describe() outputjában megjelenő mutatók:

Név az outputban	Jelentés
`vars`	a változó sorszáma
`n`	érvényes (nem hiányzó) mintaelemszám
`mean`	átlag
`sd`	szórás
`median`	medián
`trimmed`	trimmelt átlag
`mad`	mediántól való abszolút eltérés mediánja
`min`	minimum
`max`	maximum
`range`	terjedelem
`skew`	ferdeség
`kurtosis`	csúcsosság
`se`	standard hiba

library(psych)
psych::describe(survey$Height)

  vars   n   mean   sd median trimmed   mad min max range skew kurtosis   se
1    1 209 172.38 9.85    171  172.19 10.08 150 200    50 0.22    -0.44 0.68

Mutatók a `pastecs` csomag `stat.desc()` függvényével

A pastecs::stat.desc() outputjában megjelenő mutatók:

Név az outputban	Jelentés
`nbr.val`	érvényes (nem hiányzó) mintaelemszám
`nbr.null`	a nulla értékek száma
`nbr.na`	a hiányzó értékek száma
`min`	minimum
`max`	maximum
`range`	terjedelem
`sum`	az értékek összege
`median`	medián
`mean`	átlag
`SE.mean`	standard hiba
`CI.mean.0.95`	a 95%-os konfidencia intervallum félterjedelme
`var`	variancia
`std.dev`	szórás
`coef.var`	relatív gyakoriság
`skewness`	ferdeségi együttható
`skew.2SE`	szignifikancia kritérium a ferdeségre
`kurtosis`	csúcsossági együttható
`kurt.2SE`	szignifikancia kritérium a csúcsosságra
`normtest.W`	Shapiro-Wilk-próba próbastatisztika értéke
`normtest.p`	Shapiro-Wilk-próba p értéke

library(pastecs)
round(stat.desc(survey$Height, norm = T), digits=3)

     nbr.val     nbr.null       nbr.na          min          max        range          sum 
     209.000        0.000       28.000      150.000      200.000       50.000    36027.600 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     171.000      172.381        0.681        1.343       96.974        9.848        0.057 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
       0.216        0.641       -0.437       -0.653        0.988        0.088

Mutatók a `DescTools` csomag `Desc` függvényével

A DescTools::Desc() outputjában megjelenő mutatók:

Név az outputban	Jelentés
`length`	a vektor elemszáma
`n`	érvényes (nem hiányzó) mintaelemszám
`NAs`	hiányzó értékek száma
`unique`	egyedi értékek száma
`0s`	a nulla értékek száma
`mean`	átlag
`meanSE`	standard hiba
`.05`, `.10`, `.25`, `median`, `.75`, `.90`, `.95`	kvantilisek táblázata
`sd`	szórás
`vcoef`	relatív szórás
`mad`	mediántól való abszolút eltérés mediánja
`IQR`	interkvartilis eltérés
`skew`	ferdeségi együttható
`kurt`	csúcsossági együttható
`lowest`	a legkisebb értékek, zárójelben a gyakoriság
`highest`	a legnagyobb értékek, zárójelben a gyakoriság
`Shapiro-Wilks ...`	Shapiro-Wilk-próba p értéke

library(DescTools)
Desc(survey$Height)

-------------------------------------------------------------------------------------------------- 
survey$Height (numeric)

   length       n     NAs  unique      0s    mean  meanSE
      237     209      28      67       0 172.381   0.681

      .05     .10     .25  median     .75     .90     .95
      157     160     165     171     180 185.420 189.600

      rng      sd   vcoef     mad     IQR    skew    kurt
       50   9.848   0.057  10.082      15   0.216  -0.437

lowest : 150, 152, 152.4, 153.5, 154.94 (2)
highest: 191.8, 193.04, 195, 196, 200

Shapiro-Wilks normality test  p.value : 0.088436

Mutatók az `Rcmdr` csomag `numSummary()` függvényével

Az Rcmdr::numSummary() outputjában megjelenő mutatók:

Név az outputban	Jelentés
`mean`	átlag
`sd`	szórás
`se(mean)`	standard hiba
`IQR`	interkvratilis eltérés
`cv`	relatív szórás
`skewness`	ferdeségi együttható
`kurtosis`	csúcsossági együttható
`0%`, `25%`, `50%`, `75%`, `100%`	kvantilisek
`n`	érvényes (nem hiányzó) értékek száma
`NA`	hiányzó értékek száma

library(Rcmdr)
numSummary(survey$Height)

     mean       sd IQR  0% 25% 50% 75% 100%   n NA
 172.3809 9.847528  15 150 165 171 180  200 209 28

# még több mutató a numSummary() függvénnyel
numSummary(survey$Height, statistics=c("mean", "sd", "se(mean)", "IQR", 
        "quantiles", "cv", "skewness", "kurtosis"))

     mean       sd  se(mean) IQR         cv  skewness   kurtosis  0% 25% 50% 75% 100%   n NA
 172.3809 9.847528 0.6811677  15 0.05712657 0.2189719 -0.3935254 150 165 171 180  200 209 28

Egy numerikus változó különböző csoportjai, egy-egy mutató csoportonként

A szokásos mutatószámoló függvények (mean(), sd() stb.) használata a tapply(), aggregate() és by() függvényekkel. Most a mean() függvényent használjuk fel.

Az átlag csoportokra, egy csoportosító faktor

tapply(survey$Height, survey$Sex, mean, na.rm=T)

  Female     Male 
165.6867 178.8260

aggregate(survey[, "Height", drop=F], survey[, "Sex", drop=F], mean, na.rm=T)

     Sex   Height
1 Female 165.6867
2   Male 178.8260

by(survey$Height, survey$Sex, mean, na.rm=T)

survey$Sex: Female
[1] 165.6867
--------------------------------------------------------------------------- 
survey$Sex: Male
[1] 178.826

Az átlag csoportokra, két csoportosító faktor

tapply(survey$Height, survey[c("Sex", "Exer")], sd, na.rm=T)

        Exer
Sex          Freq     None     Some
  Female 6.421165 4.795058 5.890017
  Male   7.944103 9.616406 8.201259

aggregate(survey[, "Height", drop=F], survey[, c("Sex", "Exer")], sd, na.rm=T)

     Sex Exer   Height
1 Female Freq 6.421165
2   Male Freq 7.944103
3 Female None 4.795058
4   Male None 9.616406
5 Female Some 5.890017
6   Male Some 8.201259

Az átlag csoportokra, három vagy több csoportosító faktor

aggregate(survey[, "Height", drop=F], survey[, c("Sex", "Exer", "Smoke")], sd, na.rm=T)

      Sex Exer Smoke    Height
1  Female Freq Heavy  2.538372
2    Male Freq Heavy  4.041452
3    Male None Heavy        NA
4  Female Some Heavy  5.077027
5    Male Some Heavy        NA
6  Female Freq Never  7.005686
7    Male Freq Never  8.532033
8  Female None Never  4.795058
9    Male None Never 11.314006
10 Female Some Never  5.871820
11   Male Some Never  8.006079
12 Female Freq Occas  4.557354
13   Male Freq Occas  7.558523
14 Female None Occas        NA
15   Male None Occas        NA
16 Female Some Occas  1.527525
17   Male Some Occas        NA
18 Female Freq Regul        NA
19   Male Freq Regul  6.115471
20   Male None Regul        NA
21 Female Some Regul  5.388154
22   Male Some Regul  5.393564

Egy numerikus változó különböző csoportjai, több mutató csoportonként

Több mutató csoportokra, egy csoportosító faktor

library(psych)
psych::describeBy(x = survey$Height, group = survey$Sex)

group: Female
  vars   n   mean   sd median trimmed  mad min    max range  skew kurtosis   se
1    1 102 165.69 6.15 166.75   165.9 5.32 150 180.34 30.34 -0.33    -0.32 0.61
--------------------------------------------------------------------------- 
group: Male
  vars   n   mean   sd median trimmed  mad    min max range skew kurtosis   se
1    1 106 178.83 8.38    180     179 7.41 154.94 200 45.06 -0.2    -0.11 0.81

library(pastecs)
by(survey$Height, survey$Sex, function(x) round(stat.desc(x, norm=T),3))

survey$Sex: Female
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
     102.000        0.000       16.000      150.000      180.340       30.340    16900.040 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     166.750      165.687        0.609        1.208       37.844        6.152        0.037 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
      -0.330       -0.691       -0.321       -0.339        0.980        0.131 
--------------------------------------------------------------------------- 
survey$Sex: Male
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
     106.000        0.000       12.000      154.940      200.000       45.060    18955.560 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     180.000      178.826        0.814        1.614       70.229        8.380        0.047 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
      -0.203       -0.433       -0.114       -0.123        0.992        0.772

library(DescTools)
Desc(Height ~ Sex, data=survey)


Call:
Desc.formula(Height ~ Sex, data = survey)

-------------------------------------------------------------------------------------------------- 
Height ~ Sex

Summary: 
n pairs: 237, valid: 208 (90%), missings: 29 (10%), groups: 2

          Female      Male 
mean    165.6867' 178.8260"
median    166.75'   180.00"
sd      6.151777  8.380252 
IQR         7.44     12.21 
n            102       106 
np         0.490     0.510 
NAs           16        12 
0s             0         0 

' min, " max

Kruskal-Wallis rank sum test:
  Kruskal-Wallis chi-squared = 96.6766, df = 1, p-value < 2.2e-16
Warning:
  Grouping variable contains 1 NAs (0.422%).

library(Rcmdr)
numSummary(survey$Height, groups = survey$Sex)

           mean       sd   IQR     0%    25%    50% 75%   100% data:n data:NA
Female 165.6867 6.151777  7.44 150.00 162.56 166.75 170 180.34    102      16
Male   178.8260 8.380252 12.21 154.94 172.79 180.00 185 200.00    106      12

numSummary(survey$Height, groups = survey$Sex, 
           statistics=c("mean", "sd", "se(mean)", 
                        "IQR", "quantiles", "cv", "skewness", "kurtosis"))

           mean       sd  se(mean)   IQR         cv   skewness     kurtosis     0%    25%    50%
Female 165.6867 6.151777 0.6091167  7.44 0.03712898 -0.3402723 -0.220423939 150.00 162.56 166.75
Male   178.8260 8.380252 0.8139620 12.21 0.04686259 -0.2091088 -0.003157064 154.94 172.79 180.00
       75%   100% data:n data:NA
Female 170 180.34    102      16
Male   185 200.00    106      12

Több mutató csoportokra, kettő vagy több csoportosító faktor

library(psych)
psych::describeBy(x = survey$Height, group = list(survey$Sex, survey$Exer))

: Female
: Freq
  vars  n   mean   sd median trimmed mad min    max range skew kurtosis   se
1    1 45 167.13 6.42 167.64  167.38 5.4 150 180.34 30.34 -0.5     -0.1 0.96
--------------------------------------------------------------------------- 
: Male
: Freq
  vars  n   mean   sd median trimmed  mad    min max range  skew kurtosis   se
1    1 59 180.35 7.94 180.34  180.44 7.53 154.94 200 45.06 -0.25     0.72 1.03
--------------------------------------------------------------------------- 
: Female
: None
  vars n mean  sd median trimmed  mad    min max range skew kurtosis  se
1    1 9  163 4.8    165     163 7.41 157.48 170 12.52    0    -1.84 1.6
--------------------------------------------------------------------------- 
: Male
: None
  vars  n   mean   sd median trimmed mad min   max range skew kurtosis  se
1    1 11 173.96 9.62    171  173.68 8.9 160 190.5  30.5 0.33    -1.23 2.9
--------------------------------------------------------------------------- 
: Female
: Some
  vars  n   mean   sd median trimmed  mad min   max range  skew kurtosis   se
1    1 48 164.84 5.89 165.05  165.05 5.86 152 176.5  24.5 -0.41    -0.47 0.85
--------------------------------------------------------------------------- 
: Male
: Some
  vars  n   mean  sd median trimmed  mad min    max range  skew kurtosis   se
1    1 36 177.81 8.2 179.55  177.86 7.41 160 193.04 33.04 -0.18    -0.79 1.37

library(pastecs)
by(survey$Height, list(survey$Sex, survey$Exer), function(x) round(stat.desc(x, norm=T),3))

: Female
: Freq
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
      45.000        0.000        4.000      150.000      180.340       30.340     7520.880 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     167.640      167.131        0.957        1.929       41.231        6.421        0.038 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
      -0.500       -0.707       -0.097       -0.070        0.964        0.170 
--------------------------------------------------------------------------- 
: Male
: Freq
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
      59.000        0.000        6.000      154.940      200.000       45.060    10640.820 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     180.340      180.353        1.034        2.070       63.109        7.944        0.044 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
      -0.253       -0.406        0.718        0.586        0.985        0.655 
--------------------------------------------------------------------------- 
: Female
: None
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
       9.000        0.000        2.000      157.480      170.000       12.520     1466.960 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     165.000      162.996        1.598        3.686       22.993        4.795        0.029 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
       0.001        0.001       -1.842       -0.658        0.879        0.154 
--------------------------------------------------------------------------- 
: Male
: None
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
      11.000        0.000        2.000      160.000      190.500       30.500     1913.600 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     171.000      173.964        2.899        6.460       92.475        9.616        0.055 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
       0.335        0.253       -1.230       -0.481        0.954        0.690 
--------------------------------------------------------------------------- 
: Female
: Some
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
      48.000        0.000       10.000      152.000      176.500       24.500     7912.200 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     165.050      164.838        0.850        1.710       34.692        5.890        0.036 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
      -0.411       -0.599       -0.472       -0.350        0.965        0.165 
--------------------------------------------------------------------------- 
: Male
: Some
     nbr.val     nbr.null       nbr.na          min          max        range          sum 
      36.000        0.000        4.000      160.000      193.040       33.040     6401.140 
      median         mean      SE.mean CI.mean.0.95          var      std.dev     coef.var 
     179.550      177.809        1.367        2.775       67.261        8.201        0.046 
    skewness     skew.2SE     kurtosis     kurt.2SE   normtest.W   normtest.p 
      -0.175       -0.223       -0.790       -0.514        0.975        0.585

Több numerikus változó, egy mutató

Az adattábla numerikus változóinak mutatói az apply() és sapply() függvény, valamint a szokásos mutatószámoló függvényekkel is meghatározhatók. Speciális esetben használhatjuk a colMeans() és a colSums() függvényeket is. Az átlag és szórás kiszámítására mutatunk példát.

A változók átlaga

colMeans(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], na.rm = T)

   Wr.Hnd    NW.Hnd     Pulse    Height       Age 
 18.66907  18.58263  74.15104 172.38086  20.37451

apply(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], 2, mean, na.rm = T)

   Wr.Hnd    NW.Hnd     Pulse    Height       Age 
 18.66907  18.58263  74.15104 172.38086  20.37451

sapply(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], mean, na.rm = T)

   Wr.Hnd    NW.Hnd     Pulse    Height       Age 
 18.66907  18.58263  74.15104 172.38086  20.37451

A változók szórása

apply(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], 2, sd, na.rm = T)

   Wr.Hnd    NW.Hnd     Pulse    Height       Age 
 1.878981  1.967068 11.687157  9.847528  6.474335

sapply(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], sd, na.rm = T)

   Wr.Hnd    NW.Hnd     Pulse    Height       Age 
 1.878981  1.967068 11.687157  9.847528  6.474335

Több numerikus változó, több mutató

library(psych)
psych::describe(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")])

       vars   n   mean    sd median trimmed   mad    min   max range  skew kurtosis   se
Wr.Hnd    1 236  18.67  1.88  18.50   18.61  1.48  13.00  23.2 10.20  0.18     0.30 0.12
NW.Hnd    2 236  18.58  1.97  18.50   18.55  1.63  12.50  23.5 11.00  0.02     0.44 0.13
Pulse     3 192  74.15 11.69  72.50   74.02 11.12  35.00 104.0 69.00 -0.02     0.33 0.84
Height    4 209 172.38  9.85 171.00  172.19 10.08 150.00 200.0 50.00  0.22    -0.44 0.68
Age       5 237  20.37  6.47  18.58   18.99  1.61  16.75  73.0 56.25  5.16    33.47 0.42

library(pastecs)
round(stat.desc(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], norm = T), digits=3)

               Wr.Hnd   NW.Hnd     Pulse    Height      Age
nbr.val       236.000  236.000   192.000   209.000  237.000
nbr.null        0.000    0.000     0.000     0.000    0.000
nbr.na          1.000    1.000    45.000    28.000    0.000
min            13.000   12.500    35.000   150.000   16.750
max            23.200   23.500   104.000   200.000   73.000
range          10.200   11.000    69.000    50.000   56.250
sum          4405.900 4385.500 14237.000 36027.600 4828.760
median         18.500   18.500    72.500   171.000   18.583
mean           18.669   18.583    74.151   172.381   20.375
SE.mean         0.122    0.128     0.843     0.681    0.421
CI.mean.0.95    0.241    0.252     1.664     1.343    0.829
var             3.531    3.869   136.590    96.974   41.917
std.dev         1.879    1.967    11.687     9.848    6.474
coef.var        0.101    0.106     0.158     0.057    0.318
skewness        0.183    0.024    -0.017     0.216    5.163
skew.2SE        0.576    0.074    -0.047     0.641   16.327
kurtosis        0.303    0.441     0.331    -0.437   33.472
kurt.2SE        0.481    0.699     0.474    -0.653   53.139
normtest.W      0.981    0.984     0.987     0.988    0.456
normtest.p      0.003    0.009     0.086     0.088    0.000

library(DescTools)
Desc(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")])


--------------------------------------------------------------------------------------------------
'data.frame':    237 obs. of  5 variables:
 1 $ Wr.Hnd: num  18.5 19.5 18 18.8 20 18 17.7 17 20 18.5 ...
 2 $ NW.Hnd: num  18 20.5 13.3 18.9 20 17.7 17.7 17.3 19.5 18.5 ...
 3 $ Pulse : int  92 104 87 NA 35 64 83 74 72 90 ...
 4 $ Height: num  173 178 NA 160 165 ...
 5 $ Age   : num  18.2 17.6 16.9 20.3 23.7 ...

-------------------------------------------------------------------------------------------------- 
1 - Wr.Hnd (numeric)

  length      n    NAs unique     0s   mean meanSE
     237    236      1     60      0 18.669  0.122

     .05    .10    .25 median    .75    .90    .95
      16 16.500 17.500 18.500 19.800 21.150 22.050

     rng     sd  vcoef    mad    IQR   skew   kurt
  10.200  1.879  0.101  1.483  2.300  0.183  0.303

lowest : 13 (2), 14 (2), 15, 15.4, 15.5 (2)
highest: 22.5 (4), 22.8, 23 (2), 23.1, 23.2 (3)

Shapiro-Wilks normality test  p.value : 0.0026825 

-------------------------------------------------------------------------------------------------- 
2 - NW.Hnd (numeric)

  length      n    NAs unique     0s   mean meanSE
     237    236      1     68      0 18.583  0.128

     .05    .10    .25 median    .75    .90    .95
  15.500 16.300 17.500 18.500 19.725     21 22.225

     rng     sd  vcoef    mad    IQR   skew   kurt
      11  1.967  0.106  1.631  2.225  0.024  0.441

lowest : 12.5, 13 (2), 13.3, 13.5, 15
highest: 22.7, 23, 23.2 (2), 23.3, 23.5

Shapiro-Wilks normality test  p.value : 0.0090864 

-------------------------------------------------------------------------------------------------- 
3 - Pulse (integer)

  length      n    NAs unique     0s   mean meanSE
     237    192     45     43      0 74.151  0.843

     .05    .10    .25 median    .75    .90    .95
  59.550     60     66 72.500     80     90     92

     rng     sd  vcoef    mad    IQR   skew   kurt
      69 11.687  0.158 11.119     14 -0.017  0.331

Shapiro-Wilks normality test  p.value : 0.086311 

lowest : 35, 40, 48 (2), 50 (2), 54
highest: 96 (3), 97, 98, 100 (2), 104 (2)

-------------------------------------------------------------------------------------------------- 
4 - Height (numeric)

   length       n     NAs  unique      0s    mean  meanSE
      237     209      28      67       0 172.381   0.681

      .05     .10     .25  median     .75     .90     .95
      157     160     165     171     180 185.420 189.600

      rng      sd   vcoef     mad     IQR    skew    kurt
       50   9.848   0.057  10.082      15   0.216  -0.437

lowest : 150, 152, 152.4, 153.5, 154.94 (2)
highest: 191.8, 193.04, 195, 196, 200

Shapiro-Wilks normality test  p.value : 0.088436 

-------------------------------------------------------------------------------------------------- 
5 - Age (numeric)

  length      n    NAs unique     0s   mean meanSE
     237    237      0     88      0 20.375  0.421

     .05    .10    .25 median    .75    .90    .95
  17.083 17.217 17.667 18.583 20.167 23.583 30.684

     rng     sd  vcoef    mad    IQR   skew   kurt
  56.250  6.474  0.318  1.606  2.500  5.163 33.472

lowest : 16.75, 16.917 (3), 17 (2), 17.083 (7), 17.167 (11)
highest: 41.583, 43.833, 44.25, 70.417, 73

Shapiro-Wilks normality test  p.value : < 2.22e-16

library(Rcmdr)
numSummary(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")])

            mean        sd    IQR     0%     25%     50%     75%  100%   n NA
Wr.Hnd  18.66907  1.878981  2.300  13.00  17.500  18.500  19.800  23.2 236  1
NW.Hnd  18.58263  1.967068  2.225  12.50  17.500  18.500  19.725  23.5 236  1
Pulse   74.15104 11.687157 14.000  35.00  66.000  72.500  80.000 104.0 192 45
Height 172.38086  9.847528 15.000 150.00 165.000 171.000 180.000 200.0 209 28
Age     20.37451  6.474335  2.500  16.75  17.667  18.583  20.167  73.0 237  0

numSummary(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], 
           statistics=c("mean", "sd", "se(mean)", "IQR", "quantiles", 
                        "cv", "skewness", "kurtosis"))

            mean        sd  se(mean)    IQR         cv    skewness   kurtosis     0%     25%
Wr.Hnd  18.66907  1.878981 0.1223113  2.300 0.10064677  0.18493154  0.3646210  13.00  17.500
NW.Hnd  18.58263  1.967068 0.1280452  2.225 0.10585522  0.02390177  0.5064567  12.50  17.500
Pulse   74.15104 11.687157 0.8434479 14.000 0.15761285 -0.01677374  0.4073207  35.00  66.000
Height 172.38086  9.847528 0.6811677 15.000 0.05712657  0.21897194 -0.3935254 150.00 165.000
Age     20.37451  6.474335 0.4205532  2.500 0.31776634  5.22905090 34.5311761  16.75  17.667
           50%     75%  100%   n NA
Wr.Hnd  18.500  19.800  23.2 236  1
NW.Hnd  18.500  19.725  23.5 236  1
Pulse   72.500  80.000 104.0 192 45
Height 171.000 180.000 200.0 209 28
Age     18.583  20.167  73.0 237  0

Több numerikus változó különböző csoportjai, egy-egy mutató csoportonként

Az átlag csoportokra, egy csoportosító faktor

aggregate(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], 
          survey[, "Sex", drop=F], mean, na.rm=T)

     Sex   Wr.Hnd   NW.Hnd    Pulse   Height      Age
1 Female 17.59576 17.45678 75.12632 165.6867 20.40753
2   Male 19.74188 19.71453 73.19792 178.8260 20.33196

Az átlag csoportokra, több csoportosító faktor

aggregate(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], 
          survey[, c("Sex","Exer") ], sd, na.rm=T)

     Sex Exer   Wr.Hnd   NW.Hnd     Pulse   Height      Age
1 Female Freq 1.615381 1.708435 12.491753 6.421165 4.831792
2   Male Freq 1.792848 1.733761  9.593214 7.944103 7.098771
3 Female None 1.201741 1.320606 11.414277 4.795058 7.345709
4   Male None 1.738958 2.511257 15.204166 9.616406 7.024934
5 Female Some 1.035148 1.127183 10.270261 5.890017 8.244537
6   Male Some 1.708058 1.655429 13.501122 8.201259 3.516292

Több numerikus változó különböző csoportjai, több mutató csoportonként

Egy csoportosító faktor

library(psych)
psych::describeBy(x = survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], 
                  group = survey$Sex)

group: Female
       vars   n   mean    sd median trimmed   mad    min    max range  skew kurtosis   se
Wr.Hnd    1 118  17.60  1.31  17.50   17.64  1.19  13.00  20.80  7.80 -0.65     1.60 0.12
NW.Hnd    2 118  17.46  1.41  17.60   17.52  1.04  12.50  20.70  8.20 -0.78     1.94 0.13
Pulse     3  95  75.13 11.41  75.00   75.19 10.38  40.00 104.00 64.00 -0.14     0.41 1.17
Height    4 102 165.69  6.15 166.75  165.90  5.32 150.00 180.34 30.34 -0.33    -0.32 0.61
Age       5 118  20.41  6.91  18.42   18.83  1.48  16.92  73.00 56.08  4.72    28.42 0.64
--------------------------------------------------------------------------- 
group: Male
       vars   n   mean    sd median trimmed   mad    min    max range  skew kurtosis   se
Wr.Hnd    1 117  19.74  1.75  19.50   19.73  1.48  14.00  23.20  9.20 -0.05     0.02 0.16
NW.Hnd    2 117  19.71  1.80  19.50   19.73  1.48  13.30  23.50 10.20 -0.29     0.68 0.17
Pulse     3  96  73.20 12.00  72.00   72.88 11.86  35.00 104.00 69.00  0.11     0.24 1.22
Height    4 106 178.83  8.38 180.00  179.00  7.41 154.94 200.00 45.06 -0.20    -0.11 0.81
Age       5 118  20.33  6.07  18.88   19.15  1.67  16.75  70.42 53.67  5.63    39.17 0.56

library(pastecs)
by(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], survey$Sex,
   function(x) round(stat.desc(x, norm=T),3))

survey$Sex: Female
               Wr.Hnd   NW.Hnd    Pulse    Height      Age
nbr.val       118.000  118.000   95.000   102.000  118.000
nbr.null        0.000    0.000    0.000     0.000    0.000
nbr.na          0.000    0.000   23.000    16.000    0.000
min            13.000   12.500   40.000   150.000   16.917
max            20.800   20.700  104.000   180.340   73.000
range           7.800    8.200   64.000    30.340   56.083
sum          2076.300 2059.900 7137.000 16900.040 2408.089
median         17.500   17.600   75.000   166.750   18.417
mean           17.596   17.457   75.126   165.687   20.408
SE.mean         0.121    0.130    1.170     0.609    0.636
CI.mean.0.95    0.240    0.257    2.324     1.208    1.259
var             1.729    1.982  130.112    37.844   47.694
std.dev         1.315    1.408   11.407     6.152    6.906
coef.var        0.075    0.081    0.152     0.037    0.338
skewness       -0.654   -0.782   -0.139    -0.330    4.722
skew.2SE       -1.468   -1.756   -0.280    -0.691   10.603
kurtosis        1.597    1.939    0.408    -0.321   28.422
kurt.2SE        1.807    2.194    0.417    -0.339   32.160
normtest.W      0.962    0.946    0.984     0.980    0.471
normtest.p      0.002    0.000    0.291     0.131    0.000
--------------------------------------------------------------------------- 
survey$Sex: Male
               Wr.Hnd   NW.Hnd    Pulse    Height      Age
nbr.val       117.000  117.000   96.000   106.000  118.000
nbr.null        0.000    0.000    0.000     0.000    0.000
nbr.na          1.000    1.000   22.000    12.000    0.000
min            14.000   13.300   35.000   154.940   16.750
max            23.200   23.500  104.000   200.000   70.417
range           9.200   10.200   69.000    45.060   53.667
sum          2309.800 2306.600 7027.000 18955.560 2399.171
median         19.500   19.500   72.000   180.000   18.875
mean           19.742   19.715   73.198   178.826   20.332
SE.mean         0.162    0.167    1.225     0.814    0.559
CI.mean.0.95    0.321    0.330    2.431     1.614    1.107
var             3.065    3.257  143.992    70.229   36.843
std.dev         1.751    1.805   12.000     8.380    6.070
coef.var        0.089    0.092    0.164     0.047    0.299
skewness       -0.051   -0.292    0.107    -0.203    5.629
skew.2SE       -0.114   -0.654    0.218    -0.433   12.637
kurtosis        0.016    0.683    0.240    -0.114   39.169
kurt.2SE        0.018    0.770    0.246    -0.123   44.320
normtest.W      0.981    0.976    0.981     0.992    0.435
normtest.p      0.100    0.033    0.186     0.772    0.000

library(DescTools)
Desc(Wr.Hnd + NW.Hnd + Pulse + Height + Age ~ Sex, data=survey)


Call:
Desc.formula(Wr.Hnd + NW.Hnd + Pulse + Height + Age ~ Sex, data = survey)

-------------------------------------------------------------------------------------------------- 
Wr.Hnd ~ Sex

Summary: 
n pairs: 237, valid: 235 (99.2%), missings: 2 (0.8%), groups: 2

          Female      Male 
mean    17.59576' 19.74188"
median      17.5'     19.5"
sd      1.314768  1.750775 
IQR          1.5       2.5 
n            118       117 
np         0.502     0.498 
NAs            0         1 
0s             0         0 

' min, " max

Kruskal-Wallis rank sum test:
  Kruskal-Wallis chi-squared = 83.8777, df = 1, p-value < 2.2e-16
Warning:
  Grouping variable contains 1 NAs (0.422%).

-------------------------------------------------------------------------------------------------- 
NW.Hnd ~ Sex

Summary: 
n pairs: 237, valid: 235 (99.2%), missings: 2 (0.8%), groups: 2

          Female      Male 
mean    17.45678' 19.71453"
median      17.6'     19.5"
sd      1.407822  1.804605 
IQR          1.4       2.4 
n            118       117 
np         0.502     0.498 
NAs            0         1 
0s             0         0 

' min, " max

Kruskal-Wallis rank sum test:
  Kruskal-Wallis chi-squared = 90.1132, df = 1, p-value < 2.2e-16
Warning:
  Grouping variable contains 1 NAs (0.422%).

-------------------------------------------------------------------------------------------------- 
Pulse ~ Sex

Summary: 
n pairs: 237, valid: 191 (80%), missings: 46 (20%), groups: 2

          Female      Male 
mean    75.12632" 73.19792'
median        75"       72'
sd      11.40664  11.99967 
IQR           14        15 
n             95        96 
np         0.497     0.503 
NAs           23        22 
0s             0         0 

' min, " max

Kruskal-Wallis rank sum test:
  Kruskal-Wallis chi-squared = 2.0832, df = 1, p-value = 0.1489
Warning:
  Grouping variable contains 1 NAs (0.422%).

-------------------------------------------------------------------------------------------------- 
Height ~ Sex

Summary: 
n pairs: 237, valid: 208 (90%), missings: 29 (10%), groups: 2

          Female      Male 
mean    165.6867' 178.8260"
median    166.75'   180.00"
sd      6.151777  8.380252 
IQR         7.44     12.21 
n            102       106 
np         0.490     0.510 
NAs           16        12 
0s             0         0 

' min, " max

Kruskal-Wallis rank sum test:
  Kruskal-Wallis chi-squared = 96.6766, df = 1, p-value < 2.2e-16
Warning:
  Grouping variable contains 1 NAs (0.422%).

-------------------------------------------------------------------------------------------------- 
Age ~ Sex

Summary: 
n pairs: 237, valid: 236 (99.6%), missings: 1 (0.4%), groups: 2

          Female      Male 
mean    20.40753" 20.33196'
median    18.417'   18.875"
sd      6.906053  6.069863 
IQR      2.47925   2.37450 
n            118       118 
np         0.500     0.500 
NAs            0         0 
0s             0         0 

' min, " max

Kruskal-Wallis rank sum test:
  Kruskal-Wallis chi-squared = 4.3469, df = 1, p-value = 0.03708
Warning:
  Grouping variable contains 1 NAs (0.422%).

library(Rcmdr)
numSummary(survey$Height, groups = survey$Sex)

           mean       sd   IQR     0%    25%    50% 75%   100% data:n data:NA
Female 165.6867 6.151777  7.44 150.00 162.56 166.75 170 180.34    102      16
Male   178.8260 8.380252 12.21 154.94 172.79 180.00 185 200.00    106      12

numSummary(survey$Height, groups = survey$Sex, 
           statistics=c("mean", "sd", "se(mean)", 
                        "IQR", "quantiles", "cv", "skewness", "kurtosis"))

           mean       sd  se(mean)   IQR         cv   skewness     kurtosis     0%    25%    50%
Female 165.6867 6.151777 0.6091167  7.44 0.03712898 -0.3402723 -0.220423939 150.00 162.56 166.75
Male   178.8260 8.380252 0.8139620 12.21 0.04686259 -0.2091088 -0.003157064 154.94 172.79 180.00
       75%   100% data:n data:NA
Female 170 180.34    102      16
Male   185 200.00    106      12

Több csoportosító faktor

library(psych)
psych::describeBy(x = survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], 
                  group = list(survey$Sex, survey$Exer))

: Female
: Freq
       vars  n   mean    sd median trimmed   mad    min    max range  skew kurtosis   se
Wr.Hnd    1 49  17.46  1.62  17.50   17.56  1.48  13.00  20.80  7.80 -0.68     0.97 0.23
NW.Hnd    2 49  17.37  1.71  17.50   17.53  0.89  12.50  20.70  8.20 -0.97     1.46 0.24
Pulse     3 41  73.61 12.49  72.00   73.45 11.86  40.00 104.00 64.00 -0.01     0.44 1.95
Height    4 45 167.13  6.42 167.64  167.38  5.40 150.00 180.34 30.34 -0.50    -0.10 0.96
Age       5 49  20.11  4.83  18.50   19.08  1.73  16.92  39.75 22.83  2.46     5.82 0.69
--------------------------------------------------------------------------- 
: Male
: Freq
       vars  n   mean   sd median trimmed  mad    min    max range  skew kurtosis   se
Wr.Hnd    1 65  19.88 1.79  19.80   19.90 1.78  14.00  23.20  9.20 -0.31     0.45 0.22
NW.Hnd    2 65  19.90 1.73  19.80   19.89 1.78  15.50  23.50  8.00 -0.05    -0.17 0.22
Pulse     3 53  70.68 9.59  70.00   70.23 8.90  48.00 100.00 52.00  0.48     0.54 1.32
Height    4 59 180.35 7.94 180.34  180.44 7.53 154.94 200.00 45.06 -0.25     0.72 1.03
Age       5 65  20.50 7.10  18.58   19.17 1.61  17.17  70.42 53.25  5.59    35.16 0.88
--------------------------------------------------------------------------- 
: Female
: None
       vars  n   mean    sd median trimmed  mad    min    max range  skew kurtosis   se
Wr.Hnd    1 11  17.67  1.20  18.00   17.71 1.04  15.50  19.50  4.00 -0.29    -1.24 0.36
NW.Hnd    2 11  17.20  1.32  17.90   17.23 1.19  15.10  19.00  3.90 -0.31    -1.57 0.40
Pulse     3  7  71.43 11.41  70.00   71.43 8.90  50.00  86.00 36.00 -0.58    -0.80 4.31
Height    4  9 163.00  4.80 165.00  163.00 7.41 157.48 170.00 12.52  0.00    -1.84 1.60
Age       5 11  22.33  7.35  19.83   20.76 1.85  17.17  41.58 24.42  1.69     1.50 2.21
--------------------------------------------------------------------------- 
: Male
: None
       vars  n   mean    sd median trimmed   mad    min    max range  skew kurtosis   se
Wr.Hnd    1 13  19.53  1.74  18.90   19.38  1.33  17.50  23.20  5.70  0.89    -0.52 0.48
NW.Hnd    2 13  19.28  2.51  19.10   19.46  1.04  13.30  23.30 10.00 -0.52     0.42 0.70
Pulse     3 10  80.50 15.20  80.00   80.12 20.02  60.00 104.00 44.00  0.15    -1.65 4.81
Height    4 11 173.96  9.62 171.00  173.68  8.90 160.00 190.50 30.50  0.33    -1.23 2.90
Age       5 13  20.76  7.02  18.92   19.01  1.11  16.92  43.83 26.92  2.69     5.97 1.95
--------------------------------------------------------------------------- 
: Female
: Some
       vars  n   mean    sd median trimmed  mad    min   max range  skew kurtosis   se
Wr.Hnd    1 58  17.69  1.04  17.60   17.70 0.89  15.50  20.1  4.60 -0.02    -0.48 0.14
NW.Hnd    2 58  17.58  1.13  17.60   17.55 1.11  15.00  20.2  5.20  0.12    -0.13 0.15
Pulse     3 47  77.00 10.27  76.00   77.03 8.90  50.00 100.0 50.00 -0.06    -0.22 1.50
Height    4 48 164.84  5.89 165.05  165.05 5.86 152.00 176.5 24.50 -0.41    -0.47 0.85
Age       5 58  20.29  8.24  18.21   18.55 1.24  16.92  73.0 56.08  4.98    27.13 1.08
--------------------------------------------------------------------------- 
: Male
: Some
       vars  n   mean    sd median trimmed   mad    min    max range  skew kurtosis   se
Wr.Hnd    1 39  19.59  1.71  19.50   19.57  1.48  16.00  23.10  7.10  0.07    -0.67 0.27
NW.Hnd    2 39  19.55  1.66  19.50   19.59  1.48  15.50  22.50  7.00 -0.19    -0.25 0.27
Pulse     3 33  75.03 13.50  75.00   75.89 14.83  35.00  96.00 61.00 -0.67     0.30 2.35
Height    4 36 177.81  8.20 179.55  177.86  7.41 160.00 193.04 33.04 -0.18    -0.79 1.37
Age       5 40  19.92  3.52  18.92   19.17  1.48  16.75  35.50 18.75  2.72     8.17 0.56

library(pastecs)
by(survey[, c("Wr.Hnd", "NW.Hnd", "Pulse", "Height", "Age")], list(survey$Sex, survey$Exer),
   function(x) round(stat.desc(x, norm=T),3))

: Female
: Freq
              Wr.Hnd  NW.Hnd    Pulse   Height     Age
nbr.val       49.000  49.000   41.000   45.000  49.000
nbr.null       0.000   0.000    0.000    0.000   0.000
nbr.na         0.000   0.000    8.000    4.000   0.000
min           13.000  12.500   40.000  150.000  16.917
max           20.800  20.700  104.000  180.340  39.750
range          7.800   8.200   64.000   30.340  22.833
sum          855.700 851.200 3018.000 7520.880 985.502
median        17.500  17.500   72.000  167.640  18.500
mean          17.463  17.371   73.610  167.131  20.112
SE.mean        0.231   0.244    1.951    0.957   0.690
CI.mean.0.95   0.464   0.491    3.943    1.929   1.388
var            2.609   2.919  156.044   41.231  23.346
std.dev        1.615   1.708   12.492    6.421   4.832
coef.var       0.093   0.098    0.170    0.038   0.240
skewness      -0.677  -0.967   -0.007   -0.500   2.456
skew.2SE      -0.996  -1.423   -0.010   -0.707   3.613
kurtosis       0.966   1.455    0.444   -0.097   5.816
kurt.2SE       0.723   1.089    0.306   -0.070   4.353
normtest.W     0.947   0.902    0.976    0.964   0.638
normtest.p     0.029   0.001    0.517    0.170   0.000
--------------------------------------------------------------------------- 
: Male
: Freq
               Wr.Hnd   NW.Hnd    Pulse    Height      Age
nbr.val        65.000   65.000   53.000    59.000   65.000
nbr.null        0.000    0.000    0.000     0.000    0.000
nbr.na          0.000    0.000   12.000     6.000    0.000
min            14.000   15.500   48.000   154.940   17.167
max            23.200   23.500  100.000   200.000   70.417
range           9.200    8.000   52.000    45.060   53.250
sum          1292.000 1293.300 3746.000 10640.820 1332.667
median         19.800   19.800   70.000   180.340   18.583
mean           19.877   19.897   70.679   180.353   20.503
SE.mean         0.222    0.215    1.318     1.034    0.880
CI.mean.0.95    0.444    0.430    2.644     2.070    1.759
var             3.214    3.006   92.030    63.109   50.393
std.dev         1.793    1.734    9.593     7.944    7.099
coef.var        0.090    0.087    0.136     0.044    0.346
skewness       -0.308   -0.045    0.485    -0.253    5.586
skew.2SE       -0.519   -0.076    0.740    -0.406    9.400
kurtosis        0.453   -0.168    0.544     0.718   35.161
kurt.2SE        0.387   -0.143    0.422     0.586   29.989
normtest.W      0.973    0.981    0.978     0.985    0.391
normtest.p      0.166    0.397    0.437     0.655    0.000
--------------------------------------------------------------------------- 
: Female
: None
              Wr.Hnd  NW.Hnd   Pulse   Height     Age
nbr.val       11.000  11.000   7.000    9.000  11.000
nbr.null       0.000   0.000   0.000    0.000   0.000
nbr.na         0.000   0.000   4.000    2.000   0.000
min           15.500  15.100  50.000  157.480  17.167
max           19.500  19.000  86.000  170.000  41.583
range          4.000   3.900  36.000   12.520  24.416
sum          194.400 189.200 500.000 1466.960 245.584
median        18.000  17.900  70.000  165.000  19.833
mean          17.673  17.200  71.429  162.996  22.326
SE.mean        0.362   0.398   4.314    1.598   2.215
CI.mean.0.95   0.807   0.887  10.556    3.686   4.935
var            1.444   1.744 130.286   22.993  53.959
std.dev        1.202   1.321  11.414    4.795   7.346
coef.var       0.068   0.077   0.160    0.029   0.329
skewness      -0.295  -0.312  -0.583    0.001   1.688
skew.2SE      -0.223  -0.236  -0.367    0.001   1.277
kurtosis      -1.237  -1.570  -0.796   -1.842   1.501
kurt.2SE      -0.483  -0.614  -0.251   -0.658   0.586
normtest.W     0.962   0.910   0.927    0.879   0.653
normtest.p     0.798   0.246   0.523    0.154   0.000
--------------------------------------------------------------------------- 
: Male
: None
              Wr.Hnd  NW.Hnd   Pulse   Height     Age
nbr.val       13.000  13.000  10.000   11.000  13.000
nbr.null       0.000   0.000   0.000    0.000   0.000
nbr.na         0.000   0.000   3.000    2.000   0.000
min           17.500  13.300  60.000  160.000  16.917
max           23.200  23.300 104.000  190.500  43.833
range          5.700  10.000  44.000   30.500  26.916
sum          253.900 250.700 805.000 1913.600 269.834
median        18.900  19.100  80.000  171.000  18.917
mean          19.531  19.285  80.500  173.964  20.756
SE.mean        0.482   0.696   4.808    2.899   1.948
CI.mean.0.95   1.051   1.518  10.876    6.460   4.245
var            3.024   6.306 231.167   92.475  49.350
std.dev        1.739   2.511  15.204    9.616   7.025
coef.var       0.089   0.130   0.189    0.055   0.338
skewness       0.885  -0.524   0.149    0.335   2.689
skew.2SE       0.718  -0.425   0.108    0.253   2.181
kurtosis      -0.518   0.416  -1.649   -1.230   5.974
kurt.2SE      -0.218   0.174  -0.618   -0.481   2.508
normtest.W     0.882   0.910   0.935    0.954   0.465
normtest.p     0.075   0.186   0.499    0.690   0.000
--------------------------------------------------------------------------- 
: Female
: Some
               Wr.Hnd   NW.Hnd    Pulse   Height      Age
nbr.val        58.000   58.000   47.000   48.000   58.000
nbr.null        0.000    0.000    0.000    0.000    0.000
nbr.na          0.000    0.000   11.000   10.000    0.000
min            15.500   15.000   50.000  152.000   16.917
max            20.100   20.200  100.000  176.500   73.000
range           4.600    5.200   50.000   24.500   56.083
sum          1026.200 1019.500 3619.000 7912.200 1177.003
median         17.600   17.600   76.000  165.050   18.209
mean           17.693   17.578   77.000  164.838   20.293
SE.mean         0.136    0.148    1.498    0.850    1.083
CI.mean.0.95    0.272    0.296    3.015    1.710    2.168
var             1.072    1.271  105.478   34.692   67.972
std.dev         1.035    1.127   10.270    5.890    8.245
coef.var        0.059    0.064    0.133    0.036    0.406
skewness       -0.019    0.119   -0.058   -0.411    4.976
skew.2SE       -0.031    0.189   -0.083   -0.599    7.931
kurtosis       -0.479   -0.128   -0.216   -0.472   27.134
kurt.2SE       -0.387   -0.103   -0.159   -0.350   21.948
normtest.W      0.983    0.981    0.989    0.965    0.375
normtest.p      0.591    0.502    0.938    0.165    0.000
--------------------------------------------------------------------------- 
: Male
: Some
              Wr.Hnd  NW.Hnd    Pulse   Height     Age
nbr.val       39.000  39.000   33.000   36.000  40.000
nbr.null       0.000   0.000    0.000    0.000   0.000
nbr.na         1.000   1.000    7.000    4.000   0.000
min           16.000  15.500   35.000  160.000  16.750
max           23.100  22.500   96.000  193.040  35.500
range          7.100   7.000   61.000   33.040  18.750
sum          763.900 762.600 2476.000 6401.140 796.670
median        19.500  19.500   75.000  179.550  18.917
mean          19.587  19.554   75.030  177.809  19.917
SE.mean        0.274   0.265    2.350    1.367   0.556
CI.mean.0.95   0.554   0.537    4.787    2.775   1.125
var            2.917   2.740  182.280   67.261  12.364
std.dev        1.708   1.655   13.501    8.201   3.516
coef.var       0.087   0.085    0.180    0.046   0.177
skewness       0.073  -0.195   -0.675   -0.175   2.720
skew.2SE       0.096  -0.258   -0.826   -0.223   3.638
kurtosis      -0.665  -0.249    0.300   -0.790   8.175
kurt.2SE      -0.449  -0.168    0.188   -0.514   5.579
normtest.W     0.985   0.977    0.944    0.975   0.666
normtest.p     0.881   0.583    0.090    0.585   0.000

A teljes adattáblára vonatkozó mutatók

A beépített lehetőség

summary(survey)

     Sex          Wr.Hnd          NW.Hnd        W.Hnd          Fold         Pulse       
 Female:118   Min.   :13.00   Min.   :12.50   Left : 18   L on R : 99   Min.   : 35.00  
 Male  :118   1st Qu.:17.50   1st Qu.:17.50   Right:218   Neither: 18   1st Qu.: 66.00  
 NA's  :  1   Median :18.50   Median :18.50   NA's :  1   R on L :120   Median : 72.50  
              Mean   :18.67   Mean   :18.58                             Mean   : 74.15  
              3rd Qu.:19.80   3rd Qu.:19.73                             3rd Qu.: 80.00  
              Max.   :23.20   Max.   :23.50                             Max.   :104.00  
              NA's   :1       NA's   :1                                 NA's   :45      
      Clap       Exer       Smoke         Height            M.I           Age       
 Left   : 39   Freq:115   Heavy: 11   Min.   :150.0   Imperial: 68   Min.   :16.75  
 Neither: 50   None: 24   Never:189   1st Qu.:165.0   Metric  :141   1st Qu.:17.67  
 Right  :147   Some: 98   Occas: 19   Median :171.0   NA's    : 28   Median :18.58  
 NA's   :  1              Regul: 17   Mean   :172.4                  Mean   :20.37  
                          NA's :  1   3rd Qu.:180.0                  3rd Qu.:20.17  
                                      Max.   :200.0                  Max.   :73.00  
                                      NA's   :28

További lehetőségek a `psych` és a `DescTools` csomagokkal

library(psych)
psych::describeData(survey)

n.obs =  237 of which  168   are complete cases.   Number of variables =  12  of which all are numeric  TRUE  
       variable # n.obs type     H1       H2      H3      H4     T1     T2     T3     T4
Sex*            1   236    2 Female     Male    Male    Male Female Female   Male Female
Wr.Hnd          2   236    1   18.5     19.5    18.0    18.8   18.5   17.5   21.0   17.6
NW.Hnd          3   236    1   18.0     20.5    13.3    18.9   18.0   16.5   21.5   17.3
W.Hnd*          4   236    2  Right     Left   Right   Right  Right  Right  Right  Right
Fold*           5   237    2 R on L   R on L  L on R  R on L L on R R on L R on L R on L
Pulse           6   192    1     92      104      87    <NA>     88   <NA>     90     85
Clap*           7   236    2   Left     Left Neither Neither  Right  Right  Right  Right
Exer*           8   237    2   Some     None    None    None   Some   Some   Some   Freq
Smoke*          9   236    2  Never    Regul   Occas   Never  Never  Never  Never  Never
Height         10   209    1  173.0    177.8    <NA>   160.0  160.0  170.0  183.0  168.5
M.I*           11   209    2 Metric Imperial    <NA>  Metric Metric Metric Metric Metric
Age            12   237    1 18.250   17.583  16.917  20.333 16.917 18.583 17.167 17.750

psych::describe(survey)

       vars   n   mean    sd median trimmed   mad    min   max range  skew kurtosis   se
Sex*      1 236    NaN    NA     NA     NaN    NA    Inf  -Inf  -Inf    NA       NA   NA
Wr.Hnd    2 236  18.67  1.88  18.50   18.61  1.48  13.00  23.2 10.20  0.18     0.30 0.12
NW.Hnd    3 236  18.58  1.97  18.50   18.55  1.63  12.50  23.5 11.00  0.02     0.44 0.13
W.Hnd*    4 236    NaN    NA     NA     NaN    NA    Inf  -Inf  -Inf    NA       NA   NA
Fold*     5 237    NaN    NA     NA     NaN    NA    Inf  -Inf  -Inf    NA       NA   NA
Pulse     6 192  74.15 11.69  72.50   74.02 11.12  35.00 104.0 69.00 -0.02     0.33 0.84
Clap*     7 236    NaN    NA     NA     NaN    NA    Inf  -Inf  -Inf    NA       NA   NA
Exer*     8 237    NaN    NA     NA     NaN    NA    Inf  -Inf  -Inf    NA       NA   NA
Smoke*    9 236    NaN    NA     NA     NaN    NA    Inf  -Inf  -Inf    NA       NA   NA
Height   10 209 172.38  9.85 171.00  172.19 10.08 150.00 200.0 50.00  0.22    -0.44 0.68
M.I*     11 209    NaN    NA     NA     NaN    NA    Inf  -Inf  -Inf    NA       NA   NA
Age      12 237  20.37  6.47  18.58   18.99  1.61  16.75  73.0 56.25  5.16    33.47 0.42

library(DescTools)
Desc(survey)


--------------------------------------------------------------------------------------------------
'data.frame':    237 obs. of  12 variables:
  1 $ Sex   : Factor w/ 2 levels "Female","Male": 1 2 2 2 2 1 2 1 2 2 ...
  2 $ Wr.Hnd: num  18.5 19.5 18 18.8 20 18 17.7 17 20 18.5 ...
  3 $ NW.Hnd: num  18 20.5 13.3 18.9 20 17.7 17.7 17.3 19.5 18.5 ...
  4 $ W.Hnd : Factor w/ 2 levels "Left","Right": 2 1 2 2 2 2 2 2 2 2 ...
  5 $ Fold  : Factor w/ 3 levels "L on R","Neither",..: 3 3 1 3 2 1 1 3 3 3 ...
  6 $ Pulse : int  92 104 87 NA 35 64 83 74 72 90 ...
  7 $ Clap  : Factor w/ 3 levels "Left","Neither",..: 1 1 2 2 3 3 3 3 3 3 ...
  8 $ Exer  : Factor w/ 3 levels "Freq","None",..: 3 2 2 2 3 3 1 1 3 3 ...
  9 $ Smoke : Factor w/ 4 levels "Heavy","Never",..: 2 4 3 2 2 2 2 2 2 2 ...
 10 $ Height: num  173 178 NA 160 165 ...
 11 $ M.I   : Factor w/ 2 levels "Imperial","Metric": 2 1 NA 2 2 1 1 2 2 2 ...
 12 $ Age   : num  18.2 17.6 16.9 20.3 23.7 ...

-------------------------------------------------------------------------------------------------- 
1 - Sex (factor - dichotomous)

  length      n    NAs unique
     237    236      1      2

       freq perc lci.95 uci.95'
Female  118   .5   .437   .563
Male    118   .5   .437   .563

' 95%-CI Wilson

-------------------------------------------------------------------------------------------------- 
2 - Wr.Hnd (numeric)

  length      n    NAs unique     0s   mean meanSE
     237    236      1     60      0 18.669  0.122

     .05    .10    .25 median    .75    .90    .95
      16 16.500 17.500 18.500 19.800 21.150 22.050

     rng     sd  vcoef    mad    IQR   skew   kurt
  10.200  1.879  0.101  1.483  2.300  0.183  0.303

lowest : 13 (2), 14 (2), 15, 15.4, 15.5 (2)
highest: 22.5 (4), 22.8, 23 (2), 23.1, 23.2 (3)

Shapiro-Wilks normality test  p.value : 0.0026825 

-------------------------------------------------------------------------------------------------- 
3 - NW.Hnd (numeric)

  length      n    NAs unique     0s   mean meanSE
     237    236      1     68      0 18.583  0.128

     .05    .10    .25 median    .75    .90    .95
  15.500 16.300 17.500 18.500 19.725     21 22.225

     rng     sd  vcoef    mad    IQR   skew   kurt
      11  1.967  0.106  1.631  2.225  0.024  0.441

lowest : 12.5, 13 (2), 13.3, 13.5, 15
highest: 22.7, 23, 23.2 (2), 23.3, 23.5

Shapiro-Wilks normality test  p.value : 0.0090864 

-------------------------------------------------------------------------------------------------- 
4 - W.Hnd (factor - dichotomous)

  length      n    NAs unique
     237    236      1      2

      freq  perc lci.95 uci.95'
Left    18  .076   .049   .117
Right  218  .924   .883   .951

' 95%-CI Wilson

-------------------------------------------------------------------------------------------------- 
5 - Fold (factor)

  length      n    NAs levels unique  dupes
     237    237      0      3      3      y


    level freq  perc cumfreq cumperc
1  R on L  120  .506     120    .506
2  L on R   99  .418     219    .924
3 Neither   18  .076     237   1.000

-------------------------------------------------------------------------------------------------- 
6 - Pulse (integer)

  length      n    NAs unique     0s   mean meanSE
     237    192     45     43      0 74.151  0.843

     .05    .10    .25 median    .75    .90    .95
  59.550     60     66 72.500     80     90     92

     rng     sd  vcoef    mad    IQR   skew   kurt
      69 11.687  0.158 11.119     14 -0.017  0.331

Shapiro-Wilks normality test  p.value : 0.086311 

lowest : 35, 40, 48 (2), 50 (2), 54
highest: 96 (3), 97, 98, 100 (2), 104 (2)

-------------------------------------------------------------------------------------------------- 
7 - Clap (factor)

  length      n    NAs levels unique  dupes
     237    236      1      3      3      y


    level freq  perc cumfreq cumperc
1   Right  147  .623     147    .623
2 Neither   50  .212     197    .835
3    Left   39  .165     236   1.000

-------------------------------------------------------------------------------------------------- 
8 - Exer (factor)

  length      n    NAs levels unique  dupes
     237    237      0      3      3      y


  level freq  perc cumfreq cumperc
1  Freq  115  .485     115    .485
2  Some   98  .414     213    .899
3  None   24  .101     237   1.000

-------------------------------------------------------------------------------------------------- 
9 - Smoke (factor)

  length      n    NAs levels unique  dupes
     237    236      1      4      4      y


  level freq  perc cumfreq cumperc
1 Never  189  .801     189    .801
2 Occas   19  .081     208    .881
3 Regul   17  .072     225    .953
4 Heavy   11  .047     236   1.000

-------------------------------------------------------------------------------------------------- 
10 - Height (numeric)

   length       n     NAs  unique      0s    mean  meanSE
      237     209      28      67       0 172.381   0.681

      .05     .10     .25  median     .75     .90     .95
      157     160     165     171     180 185.420 189.600

      rng      sd   vcoef     mad     IQR    skew    kurt
       50   9.848   0.057  10.082      15   0.216  -0.437

lowest : 150, 152, 152.4, 153.5, 154.94 (2)
highest: 191.8, 193.04, 195, 196, 200

Shapiro-Wilks normality test  p.value : 0.088436 

-------------------------------------------------------------------------------------------------- 
11 - M.I (factor - dichotomous)

  length      n    NAs unique
     237    209     28      2

         freq  perc lci.95 uci.95'
Imperial   68  .325   .265   .392
Metric    141  .675   .608   .735

' 95%-CI Wilson

-------------------------------------------------------------------------------------------------- 
12 - Age (numeric)

  length      n    NAs unique     0s   mean meanSE
     237    237      0     88      0 20.375  0.421

     .05    .10    .25 median    .75    .90    .95
  17.083 17.217 17.667 18.583 20.167 23.583 30.684

     rng     sd  vcoef    mad    IQR   skew   kurt
  56.250  6.474  0.318  1.606  2.500  5.163 33.472

lowest : 16.75, 16.917 (3), 17 (2), 17.083 (7), 17.167 (11)
highest: 41.583, 43.833, 44.25, 70.417, 73

Shapiro-Wilks normality test  p.value : < 2.22e-16

Bevezetés az R-be 2.0 - Feladatgyűjtemény

Mutatók

Adattábla beolvasása

Egy numerikus változó, egy mutató

Egy numerikus változó, több mutató

A beépített lehetőség: a summary() függvény

Mutatók a psych csomagokkal describe() függvényével

Mutatók a pastecs csomag stat.desc() függvényével

Mutatók a DescTools csomag Desc függvényével

Mutatók az Rcmdr csomag numSummary() függvényével

Egy numerikus változó különböző csoportjai, egy-egy mutató csoportonként

Az átlag csoportokra, egy csoportosító faktor

Az átlag csoportokra, két csoportosító faktor

Az átlag csoportokra, három vagy több csoportosító faktor

Egy numerikus változó különböző csoportjai, több mutató csoportonként

Több mutató csoportokra, egy csoportosító faktor

Több mutató csoportokra, kettő vagy több csoportosító faktor

Több numerikus változó, egy mutató

A változók átlaga

A változók szórása

Több numerikus változó, több mutató

Több numerikus változó különböző csoportjai, egy-egy mutató csoportonként

Az átlag csoportokra, egy csoportosító faktor

Az átlag csoportokra, több csoportosító faktor

Több numerikus változó különböző csoportjai, több mutató csoportonként

Egy csoportosító faktor

Több csoportosító faktor

A teljes adattáblára vonatkozó mutatók

A beépített lehetőség

További lehetőségek a psych és a DescTools csomagokkal

A beépített lehetőség: a `summary()` függvény

Mutatók a `psych` csomagokkal `describe()` függvényével

Mutatók a `pastecs` csomag `stat.desc()` függvényével

Mutatók a `DescTools` csomag `Desc` függvényével

Mutatók az `Rcmdr` csomag `numSummary()` függvényével

További lehetőségek a `psych` és a `DescTools` csomagokkal