t = "F:\\NCKH - PHAN TICH THONG KE\\BAI GIANG CAC KHOA PT DL\\Kho hoc - Du lieu da tang SG1.2020\\Data for practice\\PISA Data Vietnam 2015.csv"
pisa = read.csv(t, header = T)
head(pisa)## School SchoolSize ClassSize STratio SchoolType Area Region Age
## 1 70400001 883 18 22.075 3 URBAN SOUTH 15.58
## 2 70400001 883 18 22.075 3 URBAN SOUTH 15.92
## 3 70400001 883 18 22.075 3 URBAN SOUTH 15.42
## 4 70400001 883 18 22.075 3 URBAN SOUTH 15.58
## 5 70400001 883 18 22.075 3 URBAN SOUTH 15.92
## 6 70400001 883 18 22.075 3 URBAN SOUTH 16.25
## Gender PARED HISCED WEALTH INSTSCIE JOYSCIE ICTRES Math Read
## 1 Boys 9 2 -2.0697 0.9798 2.1635 -1.5244 439.923 412.290
## 2 Boys 12 4 -1.7903 1.7359 2.1635 -1.9305 406.251 409.598
## 3 Girls 9 2 -2.1942 -0.2063 -0.1808 -1.6093 414.369 384.307
## 4 Girls 5 1 -2.0301 -0.3115 -0.4318 -1.6250 468.801 459.104
## 5 Girls 9 2 -1.0522 0.7648 1.3031 -0.5305 355.432 402.435
## 6 Girls 5 1 -3.0570 0.3708 0.5094 -2.5873 458.955 483.885
## Science
## 1 475.612
## 2 450.320
## 3 405.787
## 4 462.968
## 5 453.736
## 6 529.866# Xem kich thuoc bang du lieu (so hang, cot)
dim(pisa) ## [1] 5826 18# Tom tat du lieu
summary(pisa) ## School SchoolSize ClassSize STratio
## Min. :70400001 Min. : 113 Min. :13.00 Min. : 4.314
## 1st Qu.:70400052 1st Qu.: 650 1st Qu.:38.00 1st Qu.:14.024
## Median :70400096 Median :1090 Median :38.00 Median :16.627
## Mean :70400097 Mean :1082 Mean :40.57 Mean :16.497
## 3rd Qu.:70400143 3rd Qu.:1419 3rd Qu.:43.00 3rd Qu.:18.983
## Max. :70400188 Max. :4016 Max. :53.00 Max. :38.651
## NA's :34
## SchoolType Area Region Age Gender
## Min. :1.000 REMOTE: 410 CENTRAL:2006 Min. :15.33 Boys :2786
## 1st Qu.:3.000 RURAL :2368 NORTH :1958 1st Qu.:15.50 Girls:3040
## Median :3.000 URBAN :3048 SOUTH :1862 Median :15.75
## Mean :2.849 Mean :15.78
## 3rd Qu.:3.000 3rd Qu.:16.00
## Max. :3.000 Max. :16.25
## NA's :35
## PARED HISCED WEALTH INSTSCIE
## Min. : 3.000 Min. :0.00 Min. :-7.635 Min. :-1.9301
## 1st Qu.: 9.000 1st Qu.:2.00 1st Qu.:-2.829 1st Qu.: 0.0125
## Median : 9.000 Median :2.00 Median :-2.163 Median : 0.3708
## Mean : 9.374 Mean :2.58 Mean :-2.219 Mean : 0.4835
## 3rd Qu.:12.000 3rd Qu.:4.00 3rd Qu.:-1.504 3rd Qu.: 1.0218
## Max. :17.000 Max. :6.00 Max. : 3.211 Max. : 1.7359
## NA's :14 NA's :14 NA's :15 NA's :17
## JOYSCIE ICTRES Math Read
## Min. :-2.1154 Min. :-3.508 Min. :201.7 Min. :107.1
## 1st Qu.: 0.5094 1st Qu.:-2.587 1st Qu.:440.0 1st Qu.:442.5
## Median : 0.5094 Median :-1.855 Median :493.4 Median :489.5
## Mean : 0.6448 Mean :-1.795 Mean :496.1 Mean :489.9
## 3rd Qu.: 1.1049 3rd Qu.:-1.117 3rd Qu.:551.5 3rd Qu.:537.6
## Max. : 2.1635 Max. : 3.497 Max. :820.1 Max. :744.1
## NA's :19 NA's :34
## Science
## Min. :292.7
## 1st Qu.:470.9
## Median :523.9
## Mean :524.8
## 3rd Qu.:574.8
## Max. :807.3
## str(pisa)## 'data.frame': 5826 obs. of 18 variables:
## $ School : int 70400001 70400001 70400001 70400001 70400001 70400001 70400001 70400001 70400001 70400001 ...
## $ SchoolSize: int 883 883 883 883 883 883 883 883 883 883 ...
## $ ClassSize : int 18 18 18 18 18 18 18 18 18 18 ...
## $ STratio : num 22.1 22.1 22.1 22.1 22.1 ...
## $ SchoolType: int 3 3 3 3 3 3 3 3 3 3 ...
## $ Area : Factor w/ 3 levels "REMOTE","RURAL",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ Region : Factor w/ 3 levels "CENTRAL","NORTH",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ Age : num 15.6 15.9 15.4 15.6 15.9 ...
## $ Gender : Factor w/ 2 levels "Boys","Girls": 1 1 2 2 2 2 2 2 2 1 ...
## $ PARED : int 9 12 9 5 9 5 3 5 9 5 ...
## $ HISCED : int 2 4 2 1 2 1 0 1 2 1 ...
## $ WEALTH : num -2.07 -1.79 -2.19 -2.03 -1.05 ...
## $ INSTSCIE : num 0.98 1.736 -0.206 -0.311 0.765 ...
## $ JOYSCIE : num 2.163 2.163 -0.181 -0.432 1.303 ...
## $ ICTRES : num -1.52 -1.93 -1.61 -1.62 -0.53 ...
## $ Math : num 440 406 414 469 355 ...
## $ Read : num 412 410 384 459 402 ...
## $ Science : num 476 450 406 463 454 ...# Liet ke so luong quan sat trong moi level, mac dinh sap xep cac level theo A,B,C,...
table(pisa$Area) ##
## REMOTE RURAL URBAN
## 410 2368 3048# dung ham factor de sap xep thu tu cac level cua bien Areas theo ý minh
pisa$Area = factor(pisa$Area, levels = c("URBAN", "RURAL", "REMOTE"))
# Xem cac truong level cua bien SchoolType
table(pisa$SchoolType) ##
## 1 3
## 436 5355pisa$Type [pisa$SchoolType == 1] = "Private"
pisa$Type [pisa$SchoolType == 3] = "Public"
table(pisa$Type)##
## Private Public
## 436 5355# Phan tich mo ta voi package "table 1" - Mo ta theo mien
## install.packages("table1", dependencies = T)
library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1 (~ WEALTH + PARED + Math + Read + Science | Region , data = pisa)| CENTRAL (n=2006) |
NORTH (n=1958) |
SOUTH (n=1862) |
Overall (n=5826) |
|
|---|---|---|---|---|
| WEALTH | ||||
| Mean (SD) | -2.40 (1.12) | -2.18 (1.18) | -2.06 (1.14) | -2.22 (1.16) |
| Median [Min, Max] | -2.33 [-7.64, 1.41] | -2.14 [-7.64, 2.63] | -2.03 [-7.64, 3.21] | -2.16 [-7.64, 3.21] |
| Missing | 6 (0.3%) | 8 (0.4%) | 1 (0.1%) | 15 (0.3%) |
| PARED | ||||
| Mean (SD) | 9.49 (3.44) | 9.76 (3.51) | 8.85 (3.54) | 9.37 (3.51) |
| Median [Min, Max] | 9.00 [3.00, 17.0] | 9.00 [3.00, 17.0] | 9.00 [3.00, 17.0] | 9.00 [3.00, 17.0] |
| Missing | 3 (0.1%) | 9 (0.5%) | 2 (0.1%) | 14 (0.2%) |
| Math | ||||
| Mean (SD) | 492 (86.5) | 501 (84.4) | 496 (72.2) | 496 (81.5) |
| Median [Min, Max] | 488 [202, 818] | 500 [251, 820] | 494 [241, 719] | 493 [202, 820] |
| Read | ||||
| Mean (SD) | 488 (74.3) | 489 (72.4) | 493 (64.4) | 490 (70.6) |
| Median [Min, Max] | 486 [233, 744] | 489 [107, 718] | 493 [272, 698] | 489 [107, 744] |
| Science | ||||
| Mean (SD) | 524 (79.8) | 523 (76.6) | 528 (67.3) | 525 (75.0) |
| Median [Min, Max] | 520 [307, 807] | 522 [293, 775] | 528 [337, 761] | 524 [293, 807] |
table1 (~ WEALTH + PARED + Math + Read + Science | Area , data = pisa)| URBAN (n=3048) |
RURAL (n=2368) |
REMOTE (n=410) |
Overall (n=5826) |
|
|---|---|---|---|---|
| WEALTH | ||||
| Mean (SD) | -2.12 (1.16) | -2.22 (1.08) | -3.00 (1.25) | -2.22 (1.16) |
| Median [Min, Max] | -2.10 [-7.64, 3.21] | -2.16 [-7.64, 1.43] | -2.83 [-7.64, -0.0430] | -2.16 [-7.64, 3.21] |
| Missing | 2 (0.1%) | 7 (0.3%) | 6 (1.5%) | 15 (0.3%) |
| PARED | ||||
| Mean (SD) | 9.56 (3.48) | 9.38 (3.47) | 7.90 (3.69) | 9.37 (3.51) |
| Median [Min, Max] | 9.00 [3.00, 17.0] | 9.00 [3.00, 17.0] | 9.00 [3.00, 17.0] | 9.00 [3.00, 17.0] |
| Missing | 1 (0.0%) | 5 (0.2%) | 8 (2.0%) | 14 (0.2%) |
| Math | ||||
| Mean (SD) | 499 (79.3) | 500 (81.9) | 450 (82.0) | 496 (81.5) |
| Median [Min, Max] | 497 [202, 820] | 498 [273, 818] | 446 [216, 696] | 493 [202, 820] |
| Read | ||||
| Mean (SD) | 496 (69.6) | 491 (67.6) | 440 (76.0) | 490 (70.6) |
| Median [Min, Max] | 495 [107, 718] | 490 [292, 744] | 439 [233, 643] | 489 [107, 744] |
| Science | ||||
| Mean (SD) | 527 (72.8) | 529 (75.5) | 482 (74.4) | 525 (75.0) |
| Median [Min, Max] | 525 [293, 799] | 529 [335, 807] | 475 [307, 698] | 524 [293, 807] |
# Phan tich mo ta voi package "compareGroups" theo mien nhung hon table1 la cung cap them tri so p. Doi voi bien phan loai, tri so p cung duoc tinh theo Chi-Square
## install.packages("compareGroups", dependencies = T)
library(compareGroups)## Loading required package: SNPassoc## Loading required package: haplo.stats## Loading required package: survival## Loading required package: mvtnorm## Loading required package: parallel## Registered S3 method overwritten by 'SNPassoc':
## method from
## summary.haplo.glm haplo.statst = compareGroups(Area ~ WEALTH + PARED + Math + Read + Science, data = pisa)
createTable(t)##
## --------Summary descriptives table by 'Area'---------
##
## ________________________________________________________
## URBAN RURAL REMOTE p.overall
## N=3048 N=2368 N=410
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## WEALTH -2.12 (1.16) -2.22 (1.08) -3.00 (1.25) <0.001
## PARED 9.56 (3.48) 9.38 (3.47) 7.90 (3.69) <0.001
## Math 499 (79.3) 500 (81.9) 450 (82.0) <0.001
## Read 496 (69.6) 491 (67.6) 440 (76.0) <0.001
## Science 527 (72.8) 529 (75.5) 482 (74.4) <0.001
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯t1 = compareGroups(Gender ~ WEALTH + PARED + Math + Read + Science, data = pisa)
createTable(t1)##
## --------Summary descriptives table by 'Gender'---------
##
## ___________________________________________
## Boys Girls p.overall
## N=2786 N=3040
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## WEALTH -2.20 (1.14) -2.24 (1.17) 0.250
## PARED 9.52 (3.48) 9.24 (3.54) 0.002
## Math 498 (84.1) 495 (79.1) 0.152
## Read 479 (72.8) 500 (67.1) <0.001
## Science 526 (77.1) 524 (72.9) 0.343
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯t2 = compareGroups(Gender ~ Area + WEALTH + PARED + Math + Read + Science, data = pisa)
createTable(t2)##
## --------Summary descriptives table by 'Gender'---------
##
## ______________________________________________
## Boys Girls p.overall
## N=2786 N=3040
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## Area: 0.034
## URBAN 1460 (52.4%) 1588 (52.2%)
## RURAL 1106 (39.7%) 1262 (41.5%)
## REMOTE 220 (7.90%) 190 (6.25%)
## WEALTH -2.20 (1.14) -2.24 (1.17) 0.250
## PARED 9.52 (3.48) 9.24 (3.54) 0.002
## Math 498 (84.1) 495 (79.1) 0.152
## Read 479 (72.8) 500 (67.1) <0.001
## Science 526 (77.1) 524 (72.9) 0.343
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯