TEST HYPOTHESE DIRECTIONAL (NOT FINSIHED BUTT TRY)

TWO SAMPLE T TEST THATT IS THE POINT

R prend T1-T2 donc selon le contacte iul faut etre logique seous Ho Alternative G/L concerne HA only!!!!

T1=rnorm(30,40,5)
T1
##  [1] 42.83090 48.07389 37.14641 42.64902 46.73069 44.36233 31.37641 52.06788
##  [9] 35.93240 40.96014 37.42985 27.41557 29.56081 37.18600 39.93982 40.83930
## [17] 40.43272 47.38023 36.09329 39.68980 40.42178 36.41299 37.15071 39.33595
## [25] 32.12157 42.04517 40.98756 35.78425 44.07895 44.36122
T2=rnorm(30,20,5)
###T2 is lower than T1 selon le plan experimentale i.extemps de reaction ameliorer donc meanT2 < T1
boxplot(T1,T2)

t.test(T1,T2)#R prend T1-T2 donc positif on doit zmetre greater
## 
##  Welch Two Sample t-test
## 
## data:  T1 and T2
## t = 14.293, df = 57.979, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  17.67067 23.42652
## sample estimates:
## mean of x mean of y 
##  39.69325  19.14465
t.test(T1,T2,alternative = "greater")
## 
##  Welch Two Sample t-test
## 
## data:  T1 and T2
## t = 14.293, df = 57.979, p-value < 2.2e-16
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
##  18.14537      Inf
## sample estimates:
## mean of x mean of y 
##  39.69325  19.14465
t.test(T2,T1)
## 
##  Welch Two Sample t-test
## 
## data:  T2 and T1
## t = -14.293, df = 57.979, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -23.42652 -17.67067
## sample estimates:
## mean of x mean of y 
##  19.14465  39.69325
t.test(T2,T1,alternative = "less")
## 
##  Welch Two Sample t-test
## 
## data:  T2 and T1
## t = -14.293, df = 57.979, p-value < 2.2e-16
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
##       -Inf -18.14537
## sample estimates:
## mean of x mean of y 
##  19.14465  39.69325
t.test(T2,T1,alternative = "greater")
## 
##  Welch Two Sample t-test
## 
## data:  T2 and T1
## t = -14.293, df = 57.979, p-value = 1
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
##  -22.95183       Inf
## sample estimates:
## mean of x mean of y 
##  19.14465  39.69325