 Excel can help us to illustrate a line of best fit. The line of best fit is also known as the regression line. We can use the Excel function regression, which is found under the data tab. Then we click on data analysis, then select regression. Here we have to choose our input range. The input y range is our dependent variable, and x range is our independent variable. Excel has produced the regression analysis in a new worksheet. First I'll tidy up the columns so that I can see all of the data clearly. Excel has calculated the gradient for us, which confirms our calculation in the previous video. I'll highlight in yellow. The gradient is also known as the coefficient of the independent variable. I'll also highlight our squared value. We will talk more about this in the next video. Now I'll expand the charts so that I can see all of the points. Remember the blue points are the actual data points we have measured, and the orange points are those that have been calculated by Excel to predict the levels of caffeine based on all of the data. From a visual inspection, it appears that the data has a direct linear relationship. To add a linear line of best fit, I'll go to chart design, then click on the menu option for add chart element, then select trend line, linear. I'll make the trend line red. To explain the r squared value in the next video, I've made two sets of data for this example. The first set I've shown has relatively high error terms. This would mean that there was a fair amount of random error in either the manufacturing process or the measurements I've made, or both. A data set with low error terms would suggest that I have measured every piece of chocolate to have almost exactly the same amount of caffeine. In the next video, we will compare what happens with the statistics for these two scenarios. Of course, when collecting data from your own experiments, you won't have a high error and a low error data set. You'll just have your data.