03_thesis

df<-read.csv("df.csv")
names(df)

##  [1] "num"         "headcount"   "composition" "Sex"         "Age"        
##  [6] "Career"      "Task"        "Edu"         "smoke"       "disease"    
## [11] "harm"        "edu_imp"     "edu_charge"  "edu_time"    "edu_need"   
## [16] "test"        "place"       "clean_use"   "clean_no"    "clean"      
## [21] "skill"       "recruit"     "system_need" "rule_1"      "rule_2"     
## [26] "rule_3"      "rule_4"      "rule_5"      "tail_29_1"   "tail_29_2"  
## [31] "tail_29_3"   "tail_29_4"   "tail_29_5"   "comply_1"    "comply_2"   
## [36] "comply_3"    "comply_4"    "comply_5"    "tail_31_1"   "tail_31_2"  
## [41] "tail_31_3"   "tail_31_4"   "tail_31_5"   "rule_effect" "sales"      
## [46] "year_no_1"   "year_no_2"   "part_1"      "part_2"      "part_3"     
## [51] "part_4"

df3<-df[,c(6,24:28)]
names(df3)

## [1] "Career" "rule_1" "rule_2" "rule_3" "rule_4" "rule_5"

df3<-na.omit(df3)
library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.2     v dplyr   1.0.6
## v tidyr   1.2.0     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.1

## Warning: 패키지 'ggplot2'는 R 버전 4.1.3에서 작성되었습니다

## Warning: 패키지 'tidyr'는 R 버전 4.1.3에서 작성되었습니다

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

df3$Career<-as.factor(df3$Career)
df4<-df3 %>% filter(Career!="15")
df4<-df4 %>% filter(rule_5!=2&rule_5!=3&rule_5!=4)
g3.out1<-lm(rule_1~Career,data=df4)
anova(g3.out1)

## Analysis of Variance Table
## 
## Response: rule_1
##           Df Sum Sq  Mean Sq F value Pr(>F)
## Career     4 0.0829 0.020714  0.2279 0.9215
## Residuals 49 4.4542 0.090902

g3.out2<-lm(rule_2~Career,data=df4)
anova(g3.out2)

## Analysis of Variance Table
## 
## Response: rule_2
##           Df Sum Sq Mean Sq F value Pr(>F)
## Career     4 0.6037 0.15093  0.9802  0.427
## Residuals 49 7.5444 0.15397

g3.out3<-lm(rule_3~Career,data=df4)
anova(g3.out3)

## Analysis of Variance Table
## 
## Response: rule_3
##           Df Sum Sq Mean Sq F value  Pr(>F)  
## Career     4 1.3839 0.34597  2.5062 0.05398 .
## Residuals 49 6.7643 0.13805                  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

g3.out4<-lm(rule_4~Career,data=df4)
anova(g3.out4)

## Analysis of Variance Table
## 
## Response: rule_4
##           Df Sum Sq Mean Sq F value Pr(>F)
## Career     4 0.4863 0.12157  0.8493 0.5009
## Residuals 49 7.0137 0.14314