1. Do you know your muffins, man?
We have analyzed the data a bit, but there is still a bit of uncertainty as to how to interpret the results. In this lesson we'll specifically determine whether changing prices impacted sales. As we'll see, one helpful technique can be to separate the data into two distinct groups to compare. We will discuss this strategy in this video, and you'll practice this technique in the exercises that follow.
2. It's a DATE()
Because we changed prices on a specific date, we will need to separate the data into two groups. We can do so using the
FILTER() and
DATE() functions.
Remember that the FILTER() function takes a range and one or more conditions to use to filter that range.
For example, the formula you see will return rows 2 through 10 for columns A and B where the value in column A is more than 10. We could add additional conditions if we wanted to filter the data further. Because we're filtering based on dates, we'll also need the DATE() function. This function takes a given
year, month, and day and converts them into a date value.
We can now use these two functions together to get a dataset that only includes sales before or after a given point in time.
3. Function review
Let's review a couple more functions before we dive in. Recall that the
standard deviation measures how much variation exists in the data. More specifically, it indicates how much a given value varies (or deviates) from the average value for the dataset.
Recall also that a T.TEST() indicates whether there are statistically significant differences between two groups of data. This function takes four arguments.
The first two arguments are the two ranges to compare.
The third argument is the number of tails. Recall that a one-tailed test hypothesizes that one group's average is specifically higher or lower than the other, whereas a two-tailed test checks for differences in either direction.
The final argument is the type of t-test. Recall that we enter a value of 1 if we are conducting a paired test, which is similar to a pre- and post-test, a value of 2 if we are comparing two samples with roughly equal variation, and a value of 3 if we have two samples with very different standard deviations.
4. Let's practice!
All right. It's time to divide the data into groups and conquer!