Math for STAT project

Math for STAT project - After computing the calculations it...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
It was determined based on the data collected that a 2x2 Chi-Square test was the best decision to test the data collected. The main reason behind choosing a Chi-Square is the data was classified as categorical data. And the reason 2x2 was chosen is that the test involved comparing two different types of medicine and the effect that it was had on two different groups of patients. When testing our data to see if there is a significant difference we used an alpha of .05 which is to say, that we expect at least 95% of the time, our results will be conclusive. There are two results that can come from testing the data with a Chi-Square. The first is, that Clozapine gave a better effect then Haloperidol or vis versa. This is known as the alternative hypothesis. On the other end of the spectrum is that, the drugs worked equally and that no drug showed greater results then the other. This would be known as the null hypothesis.
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: After computing the calculations it was found that our p-value was greater then .20 which is much higher then our alpha at .05. What this states is that neither drug showed a greater improvement over the other in giving a result for schizophrenia and we cant reject our null hypothesis. Having a p-value, also known as a probability value greater then .20 means that we will be wrong more then 20% of the time which isnt acceptable in medical practices. Making conclusions that are incorrect or not significant could cause serious problems for the future. Even though the test taken as of now stated that both drugs worked equally, its not to say that they are equal in effect. At this time though based on the data given conclusions cant be made. For future testing what needs to be done is the use of a greater sample size that could give a more definitive answer compared to only sampling 322 people....
View Full Document

This note was uploaded on 10/01/2008 for the course STAT 250 taught by Professor Lewis during the Fall '07 term at SUNY Fredonia.

Ask a homework question - tutors are online