Monday, August 10, 2009

4. Appropriate Statistical Test.

Before we start analyzing the data, first we have to determine which statistical test we are going to use.

Choosing the appropriate statistical test depends on the type of research question, whether is it
1. Difference, or
2. Correlation.

For our study, the research question is a correlation question, i.e. "Is a person's BMI related to his height?".

Another factor that we have to consider is the type of measurement of our variables.
Both the independent (height) and dependent (BMI) variables are scale variables

Taking reference from Figure 8.2 "Decision path - Relationship Question", Statistics in Health Sciences, 4th Edition, by Chia Choon Yee, we have determined that the appropriate statistical test to use for our study is Pearson's r.


Now that we have determined that Pearson's r is the statistical test we are going to use, here comes the big question. What is Pearson's r?

Pearson's r is a symmetric measure of association for interval level variables. Pearson's correlation coefficient ranges from -1.0 to +1.0
+1.0 indicates a perfect positive relationship, while,
-1.0 indicates a perfect negative relationship.

When using Pearson's r, there are four assumptions we must take note of.
  • Assumption 1 : All observations must be independent of each other.
  • Assumption 2 : The dependent variable should be normally distributed at each value of the independent variable.
  • Assumption 3 : The dependent variable should have the same variablility at each value of the independent variable.
  • Assumption 4 : The relationship between the dependent and independent variables should be linear.

0 comments:

Post a Comment