This is a step-by-step guide to doing a t-test using the Acastat software.
First enter your data into the spreadsheet, making sure you have labelled each variable at the head of each column.
The data is arranged in two columns:
- The first is your dependent data- in the example they are the number of lugworm in different quadrats
- The second column is a grouping variable- a number which refers to the treatment given to each quadrat. In the example the treatment refers to whether the quadrat was taken from the top of the beach (1) or just above the low tide mark (2).
For more info on how to label the columns with the names of the variables go here
The Statistical Procedure
Select your dependent and independent variables
Click the t-test button and enterthe values you have used to code for your different treatments.
You can have more than 2 treatments.
Results
The results are shown in the AnalysisOutput screen.
Of interest are the means, the T-statistics, the DF (degrees of freedom) and the P-value.
At A-level you can presume that you have Equal Variance, so use the statistics from the top row of the final table on the output page (shown within the red lines in the picture above).
What do the Results Actually Mean?
The means show you which treatment had the greatest effect on your replicates.
In this example, sample 2, the quadrats from low down on the beach, have on average more lugworm within them than those from sample 1- those taken from higher up the beach.
Is this just luck though?
The t-statistic = 2.36 (ignore any minus signs) and with 10 degrees of freedom, the P-value of 0.0397 is less than 0.05.
The result then is statistically significant at the 5% level. We can be confident that there really are more lugworm low down on the beach than higher up, with a less than 1 in 20 chance that our results are due to chance.
How Do I Lay Out my Results in my Write-Up?
Here's an example:
The Number of Lugworm in Different Beach Postions
The graph below shows the mean number of lugworm (with the standard deviations) found in quadrats in different beach areas. The table on the right shows the results of a t-test comparing the numbers within each beach zone.
 |
|
There are more lugworm in lower areas of the beach than in higher beach areas. The result is statistically significant at the 5% level (t=2.36, P<0.05).
....and in your conclusion you would go on to explain WHY such a result makes sense using BIOLOGICAL ideas and information.