Home | MyESC | Site Index

Check announcements and deadlines, contact someone for help and get to the pages and services you use the most.

Check your financial and academic records, activate your login, and update your contact information.

Access your online courses, choose your studies for upcoming terms, and plan your studies.

Visit the online library, get help with writing and math, find a tutor and more.

Financial aid and scholarships, billing, college bookstore, disabilities services and all other student services.

Analyzing The Data in Excel

Math Tutorials Home > Statistics Social Sciences >

Downloads

At this point you have copied the data from the RVLS raw data webpage and pasted it into Excel. And you have downloaded and opened the Boxplot add-in for Excel.

Using the techniques demonstrated in the boxplot tutorial, plot the two data sets.

Your plot should look something like this:

Based on the graph it appears that the physicians from this study would plan to spend less time with their overweight patients.

But is the difference between the means significant? How confident can we be that the means of these samples are reflective of the population, and not the result of chance sampling variability?

We use inferential statistics to determine the probability that the difference between the means may have resulted from chance.

The t Test (more formally Student's t Test) is commonly used to determine the statistical significance of the difference between the means of two data sets. Using the two-sample t Test we can compute the probability that the difference between two means might have resulted from chance variability in the samples.

Of course, there's a bit more to it than that. One of the difficulties we all encounter when evaluating statistical evidence is that it is easy to lose track of the context. This is especially true when we plug numbers into a tool like SPSS or Excel and get back "an answer". To avoid this it is important to keep in mind the actual question we are asking and attempting to answer.

In statistical terms, we want to determine if there is support for the null hypothesis that the difference between the means is zero. Using the traditional statistical symbols this is:

We will apply the Two-Sample t Test to determine if we can refute the null hypothesis. If there is strong evidence that the null hypothesis is wrong, then we will have reason to believe that there is a meaningful difference between the means.

Excel provides the Two Sample t Test as part of the Data Analysis Toolpak. If you have not previously used the Data Analysis Toolpak it may need to be installed. We have created a demonstration to show you how to do this. (opens in a new window)

Applying the t Test->>>