This is what I know for HL. You need to specify the type of data format you used ordinal ratio etc... and you have to say why and what measures of dispersion you chose. You also need Descriptive and Inferential Statistics. Your Descriptive statistics are basic you can choose anything like mean, variance and standard deviation. You will have to plot say a bar graph or histogram that can relate to your experimental hypothesis. For your inferential statistics, choose the most suitable test according to your data. You can see the significance of your results. If less than 0.05 your hypothesis is confirmed. If greater null hypothesis is confirmed. All in all, you just have to link back to your hypothesis and make sure the choice of data can support it.