t_test 考虑一列单词而不是一列数字

Question

我正在使用 R。

这是一个示例数据。

structure(list(conditions = c("secondCondition", "firstCondition", "firstCondition", 
                       "secondCondition", "secondCondition", "firstCondition", "firstCondition", 
                       "secondCondition", "firstCondition", "firstCondition", "firstCondition", 
                       "secondCondition", "firstCondition", "firstCondition", "firstCondition", 
                       "secondCondition", "firstCondition", "firstCondition", "firstCondition", 
                       "firstCondition", "firstCondition", "firstCondition", "secondCondition", 
                       "firstCondition", "firstCondition", "firstCondition", "secondCondition", 
                       "firstCondition", "firstCondition", "firstCondition", "secondCondition", 
                       "firstCondition", "firstCondition", "firstCondition", "secondCondition", 
                       "firstCondition", "secondCondition", "firstCondition", "secondCondition", 
                       "firstCondition", "firstCondition", "firstCondition", "secondCondition", 
                       "secondCondition", "firstCondition", "firstCondition", "secondCondition", 
                       "firstCondition", "firstCondition", "firstCondition"), WordsProduced = c("parking", 
                                                                                            "ball", "mobile", "dad", "agressive", "triple", "face", 
                                                                                            "donate", "serve", "happy", "hello", "cry", "distinct", 
                                                                                            "tribe", "confuse", "island", "hawai", "color", "smile", 
                                                                                            "walk", "good", "beach", "affect", "skin", "place", 
                                                                                            "run", "vigilant", "eager", "mountain", "gay", "fear", 
                                                                                            "love", "hate", "star", "sun", "doge", "moon", 
                                                                                            "bitcoin", "plantair", "tesla", "final", "fresh", "friend", 
                                                                                            "solitude", "life", "sadness", "sky", "terror", "shy", 
                                                                                            "table"), MeanWordsProduced = c(0.110952380952381, 2.94285714285714, 
                                                                                                                     0.110952380952381, 2.94285714285714, 0.110952380952381, 2.94285714285714, 
                                                                                                                     0.110952380952381, 2.94285714285714, 2.94285714285714, 2.94285714285714, 
                                                                                                                     0.110952380952381, 2.94285714285714, 2.94285714285714, 2.94285714285714, 
                                                                                                                     0.110952380952381, 2.94285714285714, 2.94285714285714, 2.94285714285714, 
                                                                                                                     2.94285714285714, 2.94285714285714, 2.94285714285714, 2.94285714285714, 
                                                                                                                     2.94285714285714, 2.94285714285714, 2.94285714285714, 0.110952380952381, 
                                                                                                                     2.94285714285714, 2.94285714285714, 2.94285714285714, 0.110952380952381, 
                                                                                                                     2.94285714285714, 2.94285714285714, 2.94285714285714, 0.110952380952381, 
                                                                                                                     2.94285714285714, 2.94285714285714, 0.110952380952381, 0.110952380952381, 
                                                                                                                     2.94285714285714, 2.94285714285714, 2.94285714285714, 0.110952380952381, 
                                                                                                                     2.94285714285714, 0.110952380952381, 2.94285714285714, 0.110952380952381, 
                                                                                                                     2.94285714285714, 2.94285714285714, 2.94285714285714, 0.110952380952381
                                                                                            )), row.names = c(NA, -50L), class = c("tbl_df", "tbl", "data.frame"
                                                                                            ))

显然，每个条件产生的均值词是不正确的，但这是因为我使用的数据要大得多。

所以，我有一个问题。我需要使用 t 检验比较两组（firstCondition 和 secondCondition）。我已经使用其他一些列中有数字的值/列完成了此操作。但现在我需要比较两组产生的单词数。

两个条件共有 300 个提示，但产生的单词总数因条件而异。例如，我可以在第一个条件下总共生成 882 个单词。

条件列中条件名称重复的总次数与产生的单词总数一致，而不是实际提示的总数。

我不知道是否需要所有这些额外信息，但我的问题是如何使用一列单词而不是数字来计算 t 值。

我一直使用的公式是...

  t_test(COLUMofInterest ~ conditions, mu = 0, alternative = "two.sided", conf.level = 0.95, var.equal = FALSE, paired = FALSE) %>% 
  add_significance() 

任何帮助或建议都会很棒。谢谢