The first job in getting to know your data is to understand something about it. In our case we start with ‘descriptive statistics’, that is the mean and standard deviation of a numerical variable. In our case we will use the variable ‘number’, which is the number of people embarked on the ship.
Click on the Analyse menu, then Descriptive Statistics. A dialog box will open:
From the list of variables, choose number and click on the Right Arrow; number will be displayed in the right hand column. Click OK.
The results will be displayed on the output pane (which is a separate window).
There is a problem with this data. You can see that the maximum number of people on board is 999, which is a very large number for a sailing ship. In fact, 999 is the code used to indicate that the number value is missing in a particular case. Including it distorts the results. It can be removed by using the missing values entry for the number variable.
Once done, we can rerun the descriptive statistics function and get a more sensible and useful result.
This shows that we have 4636 valid cases (voyages), with a mean number of slaves embarked of 250. A minimum number of slaves was 2; the maximum, 898, still looks a little large and that might need to be checked again, in this case in the historical record.
Nevertheless, the descriptive statistics function is a start to understanding and analysing our data. We can now move on to counting things.
Durham SPSS 