In a past blog, I explained how Pivot Tables are your friends, not your enemy (Links to an external site.). When you have obtained your Market Research data, you are going to want to ask yourself, “Is there a statistically significant difference between the data.
Statistically significant means unlikely (improbable) to have occurred by chance. The significance testing is designed to determine whether there is an actual difference representing a real, meaningful difference, and make sure it is not a blip in the data.
Each critical value will be accompanied by a P VALUE, which will stand for the probability that the results were a result of chance. To determine statistical significance, you are going to want to look for the P-Value if:
P = .05 or less there will be a Significant
P = .051 or higher there will NOT be Significant
There are 2 types of test statistics you will encounter:
T-test (two groups or two occasions)
F-test [ANOVA] (more than two groups or occasions)
Compares the means of two sub-groups within a sample.
Males or Female
Subscribers or Non-Subscribers
Compares the means from one respondent pair
Apple Users rating battery life and memory
The test you will use when you are comparing three or more means
Likelihood to stay at a current job to stay by job tenure
Age by Income
Using Microsoft Excel, you can determine what the P-Value is for your data.
First, you want to make sure you have the Analysis ToolPak installed on your excel program.
Learn how to set up an Independent T-Test
Learn how to set up a Paired T-Test
F-Test – ANOVA
Learn how to set up an ANOVA test
Next time you are grabbing data from the survey’s use, any of these excel data analyses to determine if there is a statistical significance in your data.