Red and Black 220902

8월 23일자 출석부에만 나오는 사람들의 분포

id	group
20163304	Red
20173426	Red
20175257	Red
20182202	Red
20182716	Red
20182998	Red
20192329	Black
20192429	Black
20192535	Red
20192737	Black
20192918	Red
20193606	Red
20193611	Black
20193624	Red
20193632	Red
20193645	Red
20193966	Red
20195170	Red
20196218	Red
20196506	Black
20202725	Red
20203604	Black
20203924	Black
20205120	Red
20212426	Red
20212603	Red
20216272	Black
20216277	Red
20216733	Red
20221084	Black
20222422	Black
20222583	Black
20222627	Red
20222975	Red
20223849	Red
20226104	Black
20226175	Black
20226238	Black
20226707	Black

Red	Black
24	15

8월 23일 출석부에도 나오는 사람들의 데이터 구조

## 'data.frame':    974 obs. of  7 variables:
##  $ dept   : chr  "스마트IoT전공" "철학전공" "사회학과" "디지털미디어콘텐츠전공" ...
##  $ id     : chr  "20095324" "20141321" "20142239" "20152552" ...
##  $ name   : chr  "김태언" "오재석" "최종원" "양성일" ...
##  $ status : chr  "학생" "학생" "학생" "학생" ...
##  $ email  : chr  "youngble@kakao.com" "mintohjs@gmail.com" "cjw950712@hanmail.net" "kerect@naver.com" ...
##  $ cell_no: chr  "01020556431" "01071709869" "01025038265" "01041712254" ...
##  $ group  : Factor w/ 2 levels "Red","Black": 1 2 2 2 2 2 1 2 1 1 ...

수강신청 변경으로 나간 사람들의 데이터 구조

## tibble [39 × 7] (S3: tbl_df/tbl/data.frame)
##  $ dept   : chr [1:39] "반도체전공" "화학과" "빅데이터전공" "사회학과" ...
##  $ id     : chr [1:39] "20163304" "20173426" "20175257" "20182202" ...
##  $ name   : chr [1:39] "강윤구" "이준영" "조우형" "곽민수" ...
##  $ status : chr [1:39] "휴학" "학생" "학생" "학생" ...
##  $ email  : chr [1:39] "jnh04136@daum.net" "ak5566@naver.com" "uh9222959@gmail.com" "kmen000@gmail.com" ...
##  $ cell_no: chr [1:39] "01027037496" "01085076590" "01027202959" "01056581614" ...
##  $ group  : Factor w/ 2 levels "Red","Black": 1 1 1 1 1 1 2 2 1 2 ...

수강 신청 변경으로 새로 들어온 사람들의 데이터 구조

## 'data.frame':    108 obs. of  7 variables:
##  $ dept   : chr  "사회복지학전공" "광고홍보학과" "법학과" "경영학과" ...
##  $ id     : chr  "20172304" "20172627" "20172741" "20172877" ...
##  $ name   : chr  "김나영" "이종명" "이준환" "이상훈" ...
##  $ status : chr  "학생" "학생" "학생" "학생" ...
##  $ email  : chr  "na09320932@naver.com" "mlele@naver.com" "jhl012248@gmail.com" "dkrlenf1001@naver.com" ...
##  $ cell_no: chr  "01072230932" "01055797134" "01048511088" "01055917376" ...
##  $ group  : Factor w/ 2 levels "Red","Black": NA NA NA NA NA NA NA NA NA NA ...

남아 있던 사람들 + 새로 들어온 사람들

## 'data.frame':    1082 obs. of  7 variables:
##  $ dept   : chr  "스마트IoT전공" "철학전공" "사회학과" "디지털미디어콘텐츠전공" ...
##  $ id     : chr  "20095324" "20141321" "20142239" "20152552" ...
##  $ name   : chr  "김태언" "오재석" "최종원" "양성일" ...
##  $ status : chr  "학생" "학생" "학생" "학생" ...
##  $ email  : chr  "youngble@kakao.com" "mintohjs@gmail.com" "cjw950712@hanmail.net" "kerect@naver.com" ...
##  $ cell_no: chr  "01020556431" "01071709869" "01025038265" "01041712254" ...
##  $ group  : Factor w/ 2 levels "Red","Black": 1 2 2 2 2 2 1 2 1 1 ...

새로 들어온 사람에게만 랜덤화 적용

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.79    3.63    4.40    4.49    5.26   11.81

## [1] 1.2

## 4010368 4071302 4347866 4384724 4616274 4634838 4640294 4737156 4860036 4936595 
##    0.97    0.90    0.79    0.91    0.99    0.90    0.79    0.99    0.89    0.98

## [1] "4347866"

Randomization

# set.seed(Xmin)
set.seed(Xmin)
id_red <- sample(1:N_new, size = red_new)
class_roll[class_roll$id %in% id_new, "group"] <- 
  factor(ifelse(1:N_new %in% id_red, "Red", "Black"), levels = c("Red", "Black")) 
red_and_black(Xmin)

## [1] 0.7872892

학번

class_roll$id_2 <-
  class_roll$id %>%
  ifelse(. <= 2016, "2016", .)
tbl1 <- class_roll %$%
  table(.$group, .$id_2 %>% substr(1, 4)) %>%
  `colnames<-`(c("2016 이전", 2017:2022)) 
tbl1 %>%
  pander

	2016 이전	2017	2018	2019	2020	2021	2022
Red	14	33	64	63	50	73	244
Black	15	31	62	64	51	73	245

class_roll <- class_roll[, names(class_roll0823)]
X1min <- tbl1 %>%
  chisq.test(simulate.p.value = TRUE) %>%
  `[[`(1)
X1min

## X-squared 
## 0.1485488

학번 홀짝

tbl2 <- class_roll$id %>%
  as.numeric %>%
  `%%`(2) %>%
  factor(levels = c(1, 0), labels = c("홀", "짝")) %>%
  table(class_roll$group, .) 
tbl2 %>%
  pander

	홀	짝
Red	286	255
Black	284	257

X2min <- tbl2 %>%
  chisq.test(simulate.p.value = TRUE) %>%
  `[[`(1)
X2min

##  X-squared 
## 0.01483004

학적 상태

tbl3 <- class_roll$status %>%
  table(class_roll$group, .) 
tbl3 %>%
  pander

	학생	휴학
Red	532	9
Black	533	8

X3min <- tbl3 %>%
  chisq.test(simulate.p.value = TRUE) %>%
  `[[`(1)
X3min

## X-squared 
## 0.0597625

e-mail 서비스업체

tbl4 <- class_roll$email %>%
  strsplit("@", fixed = TRUE) %>%
  sapply("[", 2) %>%
  `==`("naver.com") %>%
  ifelse("네이버", "기타서비스") %>%
  factor(levels = c("네이버", "기타서비스")) %>%
  table(class_roll$group, .) 
tbl4 %>%
  pander

	네이버	기타서비스
Red	430	111
Black	433	108

X4min <- tbl4 %>%
  chisq.test(simulate.p.value = TRUE) %>%
  `[[`(1)
X4min

##  X-squared 
## 0.05152463

전화번호의 분포

cut_label <- paste(paste0(0:9, "000"), paste0(0:9, "999"), 
                   sep = "~")
tbl5 <- class_roll$cell_no %>%
  substr(start = 8, stop = 11) %>%
  sapply(as.numeric) %>%
  cut(labels = cut_label, 
      breaks = seq(0, 10000, by = 1000)) %>%
  table(class_roll$group, .) 
tbl5 %>%
  pander

	0000~0999	1000~1999	2000~2999	3000~3999	4000~4999	5000~5999	6000~6999	7000~7999	8000~8999	9000~9999
Red	50	50	47	57	62	53	61	59	48	54
Black	47	49	50	58	62	56	59	59	47	54

X5min <- tbl5 %>%
  chisq.test(simulate.p.value = TRUE) %>%
  `[[`(1)
X5min

## X-squared 
## 0.3307921

성씨 분포

f_name <- class_roll$name %>%
  substring(first = 1, last = 1) 
tbl6 <- f_name %>%
  `%in%`(c("김", "이", "박")) %>%
  ifelse(f_name, "기타") %>%
  factor(levels = c("김", "이", "박", "기타")) %>%
  table(class_roll$group, .) 
tbl6 %>%
  pander

	김	이	박	기타
Red	127	78	38	298
Black	124	80	41	296

X6min <- tbl6 %>%
  chisq.test(simulate.p.value = TRUE) %>%
  `[[`(1)
X6min

## X-squared 
## 0.1818311

Sum of Chi_Squares

Xsum_min <- X1min + X2min + X3min + X4min + X5min + X6min
Xsum_min

## X-squared 
## 0.7872892