**T-test are used when you have to test the hypotheses of an unknown population mean, it is used as a substitute.**

**a t distribution is computed through using sample variance . this is due to t- test using variance instead of error and the fact that t is used to test the difference between two means .****t distribution are often bell-shaped and have a definite mean of zero . the shape if the t distribution changes due tho the degrees of freedom: the larger the degrees f freedom the closer to z the t distribution looks even though they are known to have more variability, be flatter and more spread out than z – distributions which hs a more central peak. the flatness of the t is caused by the variability of the scores in the distribution. **

**although t-test are exactly as great as they sound – they have their complications to for example testing variable and finding causation.so how useful are they, a study that helps ys e answer this very question as it shows that t-test help us to see whether the null hypothesis is true rest and thus has any given effect, it also dictates the variability af a sample and the effect of sample size has on this. this study plainly highlights the strength of such test in cases where there are a small amount if variables pitted against each othe as : t-test become more complex as more variables are added to the mix. **

**http://beheco.oxfordjournals.org/content/14/3/446.short**

### Like this:

Like Loading...

*Related*

I enjoyed this blog, and how you have taken a different route to other blogs, and looked at some of the statistical analysis that are run on data. T-tests are used to compare the data from two condition in a study, in order to show that the effect of one variable has on another. However, the main downside to this form of analysis is that only two conditions can be compared at once, and if there are more condition that need to be taken into consideration, then an ANOVA needs to be used.