#导入数据
# 直接file-》import dataset，选择文件即可
library(haven)
# 导入数据默认为数据框格式（data.frame）
eee_data <- read_sav("https://gitee.com/vv_victorwei/r-language-data-analysis/raw/master/Untitled2.sav")
# head会呈现eee_data的前六行数据，以预览概况
head(eee_data)## # A tibble: 6 × 55
## V1 time_used IP id gender age birth…¹ roman…² hukou hair homet…³
## <chr> <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 175 594 223.66… 2225… 1 23 1 0 0 1 0
## 2 124 178 101.88… 2222… 1 23 1 0 0 1 0
## 3 138 207 211.16… 2225… 1 22 0 0 1 1 0
## 4 74 176 58.246… 2122… 1 23 1 0 1 1 0
## 5 149 232 120.25… 2222… 1 22 0 0 0 1 0
## 6 11 142 58.40.… 1601… 1 23 1 0 1 1 0
## # … with 44 more variables: family_income <dbl>, minzhu <dbl>, zhiyuan <dbl>,
## # height <dbl>, weight <dbl>, zhengzhi <dbl>, personality <dbl>, a1 <dbl>,
## # a2 <dbl>, a3 <dbl>, a4 <dbl>, a5 <dbl>, a6 <dbl>, a7 <dbl>, a8 <dbl>,
## # a9 <dbl>, a10 <dbl>, a11 <dbl>, a12 <dbl>, a13 <dbl>, b1 <dbl>, b2 <dbl>,
## # b3 <dbl>, b4 <dbl>, b5 <dbl>, b6 <dbl>, importance_ranking <chr>,
## # importance_ranking_d <dbl>, daode <dbl>, zhishi <dbl>, jineng <dbl>,
## # yishu <dbl>, food <chr>, chuan_food <dbl>, yue_food <dbl>, …table(eee_data$hometown,eee_data$zhiyuan)##
## 1 2 3
## 0 48 17 38
## 1 30 15 27summary(table(eee_data$hometown,eee_data$zhiyuan))## Number of cases in table: 175
## Number of factors: 2
## Test for independence of all factors:
## Chisq = 0.67, df = 2, p-value = 0.7153# 课堂例子
library(haven)
e2_gender <- read_sav("https://gitee.com/vv_victorwei/r-language-data-analysis/raw/master/%E5%9D%87%E5%80%BC%E5%88%86%E6%9E%90/4.5%20E2%20gender%20difference%20.sav")
head(e2_gender)## # A tibble: 6 × 2
## group score
## <dbl+lbl> <dbl>
## 1 1 [boy] 70
## 2 1 [boy] 68.3
## 3 1 [boy] 86.7
## 4 1 [boy] 70
## 5 1 [boy] 75.0
## 6 1 [boy] 58.0# 因子化 性别
e2_gender$group_f<-factor(e2_gender$group,levels = c(1,2),labels = c("male","female"))
# Wilcoxon秩和检验
wilcox.test(score~group_f, data=e2_gender)## Warning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): cannot
## compute exact p-value with ties##
## Wilcoxon rank sum test with continuity correction
##
## data: score by group_f
## W = 129, p-value = 0.0565
## alternative hypothesis: true location shift is not equal to 0-Wilcoxon符号秩检验
# 课堂例子
library(haven)
e3_test <- read_sav("https://gitee.com/vv_victorwei/r-language-data-analysis/raw/master/%E5%9D%87%E5%80%BC%E5%88%86%E6%9E%90/4.5%20E3%20pretest%20and%20posttest.sav")
head(e3_test)## # A tibble: 6 × 3
## 学号 pretest posttest
## <dbl> <dbl> <dbl>
## 1 4 25.8 30
## 2 96 41.5 43
## 3 12 45.5 50
## 4 13 45.7 50
## 5 77 49.4 55
## 6 6 50.4 56wilcox.test(e3_test$pretest,e3_test$posttest, paired = TRUE)##
## Wilcoxon signed rank test with continuity correction
##
## data: e3_test$pretest and e3_test$posttest
## V = 1301, p-value = 2.59e-05
## alternative hypothesis: true location shift is not equal to 0library(haven)
e1_3groups <- read_sav("https://gitee.com/vv_victorwei/r-language-data-analysis/raw/master/%E5%9D%87%E5%80%BC%E5%88%86%E6%9E%90/4.6%20E1%20three%20groups%20comparison.sav")
head(e1_3groups)## # A tibble: 6 × 2
## grade testscore
## <dbl+lbl> <dbl>
## 1 1 [小班] 70
## 2 1 [小班] 80
## 3 1 [小班] 75
## 4 1 [小班] 86
## 5 1 [小班] 77
## 6 1 [小班] 75e1_3groups$grade_f<-factor(e1_3groups$grade,levels = c(1,2,3),labels = c("class 1","class 2","class 3"))
kruskal.test(testscore ~ grade_f, data = e1_3groups)##
## Kruskal-Wallis rank sum test
##
## data: testscore by grade_f
## Kruskal-Wallis chi-squared = 9.9827, df = 2, p-value = 0.006797library(haven)
# 导入数据默认为数据框格式（data.frame）
three_waves <- read_sav("https://gitee.com/vv_victorwei/r-language-data-analysis/raw/master/%E5%9D%87%E5%80%BC%E5%88%86%E6%9E%90/4.6%20E3%20R%20ANOVA.sav")
# head会呈现的前六行数据，以预览概况
head(three_waves)## # A tibble: 6 × 3
## score_t1 score_t2 score_t3
## <dbl> <dbl> <dbl>
## 1 64 75 76
## 2 62 70 71
## 3 70 72 68
## 4 60 73 74
## 5 89 92 93
## 6 76 82 83# 重复测量的数据变换
# R需要的模式是ID,TIMEPOINT, SCORE
# 可以把t1、t2和t3的数据堆砌一下，ID按1：20重复3遍堆砌，timepoint按1重复20遍、2重复20次，3重复20次堆砌
id<-rep(1:20,3)
time<-c(rep(1,20),rep(2,20),rep(3,20))
score<-c(three_waves$score_t1,three_waves$score_t2,three_waves$score_t3)
# 因子化
time<-factor(time)
id<-factor(id)
#合并三个变量为一个数据框
three_waves_new<-data.frame(id,time,score)
friedman.test(score~time|id,three_waves_new)##
## Friedman rank sum test
##
## data: score and time and id
## Friedman chi-squared = 10.842, df = 2, p-value = 0.004422