0

DON'T MARK DUPLICATE IF YOU CAN'T SPECIFICALLY ANSWER THIS QUESTION

and I am not using lapply nor does the question match with this

size income.gap count1 count2
 1    1000000   656   656  
 2    1000000   1443  1443  
 3    1000000   1232  1232  
 4    1000000   1036  1036  
 5    1000000   540   540  
 6    1000000   227   227  
 7    1000000    94    94  
 8    1000000    38    38  
 9    1000000    22    22  
10    1000000     4     4  



gap.data.conf <- ddply(data, ~ size, summarize, 
                   gap = mean(income[gender == "Male"], na.rm = TRUE) - mean(income[gender == "Female"], na.rm = TRUE),
                   upper = -t.test(income ~ gender)$conf.int[1],
                   lower = -t.test(income ~ gender)$conf.int[2])

ERROR:

 Error in t.test.default(x = c(35000L, 24000L, 24000L), y = 26000L) :
not enough 'y' observations

Can anyone guide me, why there are not enough y observations, although the count is equal as shown in the table above?

Community
  • 1
  • 1
YellowSunshine
  • 73
  • 2
  • 7
  • You do not have the column "gender" defined in the data shown above. income[gender == "Male"] with return a zero length vector. – Dave2e Dec 07 '16 at 15:28
  • Solved: That was not the issue. The issue was because of the 10th row `10 1000000 4 4` 4 is too less a value. – YellowSunshine Dec 08 '16 at 02:06

0 Answers0