Kristin_MIT_v3

1. There are 4 groups of patients, separated by study ID:

• K - dialysis patient with acute infection
• J - dialysis patient without acute infection
• C - non-dialysis patient with acute infection
• D- non-dialysis patient without acute infection

2. Use original scale of ll37_1borre:

• The overall F test (H0: K=J=C=D) was not significant; thus we don’t have enough evidence to reject the null;
• Pvalue from Tukey’s post-hoc pairwise comprison show for C and D is >0.9999;
• If we don’t apply penalty for multiple testing, pvalue from t-test for C and D is 0.9671.

3. Apply log transformation of ll37_1borre:

• The overall F test for log ll37_1borre was borderline significant;
• Pvalue from Tukey’s post-hoc pairwise comprison show for C and D is 0.8067;
• If we don’t apply penalty for multiple testing, pvalue from t-test for C and D is 0.3422.

4. In short, no statistical significant difference of ll37_1borre between group C and group D.

original scale of ll37_1borre

## Analysis of Variance Table
## 
## Response: ll37_1borre
##            Df   Sum Sq Mean Sq F value  Pr(>F)  
## group       3  1028305  342768  2.2065 0.09174 .
## Residuals 104 16156071  155347                  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = fit1)
## 
## $group
##           diff        lwr      upr     p adj
## D-C   4.274545 -296.56540 305.1145 0.9999815
## J-C -54.245455 -343.11225 234.6213 0.9610934
## K-C 189.703578  -97.18527 476.5924 0.3152592
## J-D -58.520000 -337.20823 220.1682 0.9468203
## K-D 185.429032  -91.20848 462.0665 0.3033764
## K-J 243.949032  -19.61816 507.5162 0.0801892

## 
##  Welch Two Sample t-test
## 
## data:  ll37_1borre by group
## t = -0.041566, df = 34.822, p-value = 0.9671
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -213.0849  204.5358
## sample estimates:
## mean in group C mean in group D 
##        550.0455        554.3200

Apply log transformation of ll37_1borre

## Analysis of Variance Table
## 
## Response: log_ll37_1borre
##            Df Sum Sq Mean Sq F value  Pr(>F)  
## group       3  2.880 0.95994  2.5843 0.05722 .
## Residuals 104 38.631 0.37145                  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = fit2)
## 
## $group
##            diff          lwr       upr     p adj
## D-C -0.15970818 -0.624904997 0.3054886 0.8067138
## J-C -0.21245915 -0.659141564 0.2342233 0.6017757
## K-C  0.18680940 -0.256814454 0.6304333 0.6906241
## J-D -0.05275097 -0.483693999 0.3781921 0.9886430
## K-D  0.34651759 -0.081254368 0.7742895 0.1551014
## K-J  0.39926856 -0.008292415 0.8068295 0.0570939

## 
##  Welch Two Sample t-test
## 
## data:  log_ll37_1borre by group
## t = 0.9612, df = 40.427, p-value = 0.3422
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.1759930  0.4954094
## sample estimates:
## mean in group C mean in group D 
##        6.230783        6.071075