Good Morning

In the following analysis are going to be considered the Spearman´s correlation and the Mann-Whitney analysis based on the characteristics of the database.

1.Database exploration

summary(rafa)
##  D.H       Hbacter        cS100A12         SEI         GPEI  
##  D:11   Min.   :0.00   Min.   :0.00   Min.   :0   Min.   :0  
##  H: 9   1st Qu.:1.00   1st Qu.:0.00   1st Qu.:0   1st Qu.:0  
##         Median :1.00   Median :0.00   Median :0   Median :0  
##         Mean   :1.35   Mean   :0.35   Mean   :0   Mean   :0  
##         3rd Qu.:2.00   3rd Qu.:1.00   3rd Qu.:0   3rd Qu.:0  
##         Max.   :3.00   Max.   :1.00   Max.   :0   Max.   :0  
##     F.GN.MA           IL          LPL.Plm         LPE         LPN     
##  Min.   :0.00   Min.   :0.00   Min.   :0.0   Min.   :0   Min.   :0.0  
##  1st Qu.:0.00   1st Qu.:0.00   1st Qu.:1.0   1st Qu.:0   1st Qu.:0.0  
##  Median :0.00   Median :0.00   Median :1.0   Median :0   Median :0.0  
##  Mean   :0.05   Mean   :0.15   Mean   :0.9   Mean   :0   Mean   :0.1  
##  3rd Qu.:0.00   3rd Qu.:0.00   3rd Qu.:1.0   3rd Qu.:0   3rd Qu.:0.0  
##  Max.   :1.00   Max.   :1.00   Max.   :2.0   Max.   :0   Max.   :1.0  
##       GLH   
##  Min.   :0  
##  1st Qu.:0  
##  Median :0  
##  Mean   :0  
##  3rd Qu.:0  
##  Max.   :0

Footnotes:

  1. SEI, GPEI, LPE, and GLH variables don´t have any values, therefore their values aren´t going to be taken into account.
  2. Ordinal variables are going to be analysed using Spearman Correlation. The interest variables Hbacter and cS100A12 are going to be related with all variables.

2. Graphics

Database correlation

corrplot(M, method="pie")

3. Correlation dataframes

Hbacter Correlation

as.data.frame(datos)
##   Variables        rho pvalues
## 1  cS100A12 0.04770849  0.8417
## 2   F.GN.MA 0.18793690  0.4275
## 3        IL 0.16569320  0.4851
## 4   LPL.Plm 0.18115950  0.4447
## 5       LPN 0.06068133  0.7994

cS100A12 Correlation

as.data.frame(datos1)
##   Variables         rho pvalues
## 1   Hbacter  0.04770849 0.84170
## 2   F.GN.MA -0.16834510 0.47800
## 3        IL  0.27889960 0.23370
## 4   LPL.Plm  0.33833250 0.14450
## 5       LPN  0.45425680 0.04422

The most related variables are LPN and cS100A12 with a direct association(+). The relation between LPN and cS100A12 has an asociation strenght of 45% (Moderate). The probability to find a correlation coefficient r>=0.45 if the real r was 0 is 4% (p=0.04422)

4. Mann-Whitney U

We want to compare the mean of two independent groups, in this case would be the health variable with two possible results “Healthy” or “Disease”. Based on the ordinal and the non parametric behaviour of the variables we are going to choose the Mann-Whitney U test.

as.data.frame(datos3)
##   Variables    W pvalues
## 1   Hbacter 55.0  0.6901
## 2  cS100A12 58.0  0.4625
## 3   F.GN.MA 45.0  0.4214
## 4        IL 56.0  0.4617
## 5   LPL.Plm 56.5  0.5401
## 6       LPN 50.5  0.9418

The p-value is not significant for any of the variables, then, it means that healthy and disease patients can´t be differentiated with the values given in the Hbacter,cS100A12,F.GN.MA,IL,LPL.Plm, and LPN variables.