lundi 22 mars 2021

Using notation to sample rows from a data file and run individual T-test on the in R

I am trying to do three steps with my data file.

  1. Resample from the data file 100 times with replacement. My code is below
    Q3<-question.3
    Q.3<-data.frame(question.3)
    resample<-Q.3[sample(100, replace = TRUE),]'

        x1    x2
    61     9.49 10.17
    18    10.96  9.42
    30    10.12  8.08
    51    10.72 10.23
    70    10.52  9.14
    87    10.32  8.32
    42    10.21  9.77
    72     8.66 10.80
    87.1  10.32  8.32
    76     8.78 10.15
    25    11.11  9.42
    29    11.68 12.37
    87.2  10.32  8.32
    66     7.91  7.96
    51.1  10.72 10.23
    22     9.24 11.57
    90     9.99 10.19
    92    10.02  9.30
    75    10.04 10.23
    8      9.83  8.96
    41     9.60  9.86
    79     8.59  8.93
    5      9.51  9.19
    10     9.27  7.50
    36    10.15 10.85
    68    11.26  8.47
    88     9.03  8.71
    79.1   8.59  8.93
    6      9.75  9.83
    58    11.05  8.58
    6.1    9.75  9.83
    21     9.94 13.32
    34     8.56 10.21
    10.1   9.27  7.50
    67     9.10  9.90
    35     9.59  9.65
    82    10.61  9.46
    62    11.18  8.71
    58.1  11.05  8.58
    77    11.50 10.94
    4     11.01 11.77
    71    10.92  9.51
    24    10.35  9.23
    26     9.91  9.49
    29.1  11.68 12.37
    96     9.33  8.62
    76.1   8.78 10.15
    81    13.52  8.69
    66.1   7.91  7.96
    34.1   8.56 10.21
    91     9.93 11.53
    100   10.52  9.94
    76.2   8.78 10.15
    86    11.55 10.26
    30.1  10.12  8.08
    59     9.22 11.00
    44     8.76 10.40
    83     9.93 10.49
    77.1  11.50 10.94
    73     8.34  8.90
    7      8.55  7.09
    58.2  11.05  8.58
    4.1   11.01 11.77
    37    10.29 10.80
    84    10.20  9.78
    87.3  10.32  8.32
    50    10.23  9.72
    8.1    9.83  8.96
    44.1   8.76 10.40
    76.3   8.78 10.15
    74    11.55 11.30
    51.2  10.72 10.23
    28    11.25 10.13
    53    10.54  9.43
    51.3  10.72 10.23
    47     7.65  8.56
    99    10.26 11.21
    96.1   9.33  8.62
    23     7.58 11.08
    43     9.20  8.84
    40     8.68  9.94
    31    10.16 10.32
    36.1  10.15 10.85
    62.1  11.18  8.71
    55    10.40 10.14
    20     9.95  9.71
    100.1 10.52  9.94
    80    10.34  7.09
    86.1  11.55 10.26
    6.2    9.75  9.83
    56     9.01  9.77
    51.4  10.72 10.23
    45     7.86  7.09
    77.2  11.50 10.94
    9      8.43  9.79
    48    10.28  9.52
    36.2  10.15 10.85
    69    10.92 10.14
    3      8.07 11.98
    38     9.41  9.60
  1. Conduct an independent sample t-test for each of the re-sampled data to obtain 100 p-values.

I am stuck here. I can conduct a T-test for the 2 columns but I am stuck on how to do this for reach row?

I tried unlisting my re-sample and using notation to work within the R object resample to collect T.test but this doesn't work.

resample1<-unlist(resample)
resample1[t.test(resample1,mu = .05),] #didnt work
resample1[t.test(resample,mu = .05, alternative = "greater",)] #didnt work
  1. I then want to extract the 100 p-values from each T-test. I want to code p-values <0.05 as 1 and p-values >0.05 as 0.

If I had the 100 values I would use a if else statement and the $ to fun the if statement in each row. I would use a for loop and if else statement to extract the p-values and code them as 1's and 0's

  1. I want to compute the mean to see if it is close to 0.05.

thanks
P.S I am using CTRL-K to make the code be in the right format for asking a question but its not working for some reason

Aucun commentaire:

Enregistrer un commentaire