I am doing an independent 2-sample T-test on a study about horses. My experiment

Question

I am doing an independent 2-sample T-test on a study about horses. My experimental hypothesis states: cribbing has an effect on horse's teeth length and my null states: cribbing does not have an effect on horses teeth length. Since it's the end of the semester, my professer instructed us to make up our own data (the numbers we input). So far, I have made the type of horse (cribbing=1 and noncribbing=2) my categorical variable and the horses teeth length the continuous variable. How do I go about running this test correctly? I need step by step instruction. I thought I was supposed to do a test of normality first, but I got a P=0.000, so wouldn't I have to then do a nonparametric test then T-test? Is there a way I can manipulate the numbers I entered so I can go straight to a T-test and just get my results? What am I doing wrong? I am doing an independent 2-sample T-test on a study about horses. My experimental hypothesis states: cribbing has an effect on horse's teeth length and my null states: cribbing does not have an effect on horses teeth length. Since it's the end of the semester, my professer instructed us to make up our own data (the numbers we input). So far, I have made the type of horse (cribbing=1 and noncribbing=2) my categorical variable and the horses teeth length the continuous variable. How do I go about running this test correctly? I need step by step instruction. I thought I was supposed to do a test of normality first, but I got a P=0.000, so wouldn't I have to then do a nonparametric test then T-test? Is there a way I can manipulate the numbers I entered so I can go straight to a T-test and just get my results? What am I doing wrong?

Explanation / Answer

Solution :

here we have continuous dependent variable and cribbing is categorical independent variable.

So yes here you need to first do normlaity test.For a given set of independent and dependent variables, there are two statistical tests available: one parametric and one non-parametric. Parametric tests are appropriate when continuous variables follow a normal distribution, and non-parametric tests are appropriate when they do not.

So as here you got p-value as 0 < 0.05, so we reject Ho and get that it does not follow normal distribution.

And that is why here you need to use Non-parametric test.That is here you need to do Wilcoxon Signed rank test.

Related Questions

Navigate

• Browse (All)
• Browse I
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.