Transcript
SPEAKER
Descriptive statistics. Using a simple data set, this tutorial will show you how to produce descriptive statistics using Jamovi. The data in this example is loosely based on the evaluation of the Schools Linking Network. As the name suggests, this project links schools in different communities to put the contact hypothesis into practice. The contact hypothesis suggests that by increasing contacts between people from diverse backgrounds, prejudice can be reduced and positive attitudes towards out-groups can be fostered.
This is what the data looks like in Jamovi, and this can be found in the file below. Each column represents a different variable, and each row contains the data from one participant. The different columns display the following data-- ID number-- this refers to the ID number assigned to the participants. We use these numbers as identifiers instead of participant names, as this allows us to collect data whilst keeping the participants anonymous. As anonymity is ethically important in psychology research, this is generally considered good practice.
Gender ID-- this column contains categorical, nominal information about participant's gender identity. Ethnicity-- this column contains information about participant's ethnicity. Like gender identity, this is a categorical or nominal variable as participants belong to different groups or categories. Enjoyment-- this variable measures pupils enjoyment of meeting new people through the Linking School Network on a scale of 1 to 5d where 1 equals did not enjoy at all, and 5 equals really enjoyed. As this is a single scale with five ordered categories to choose from, it's an ordinal variable.
Respect1-- the Linking School Network aims to reduce prejudice between different groups. To assess this, a questionnaire that measures participants respect for the rights of others was given to students both before and after their participation in the program. This variable represents their respect for others before the intervention. As this is measured using a standardized questionnaire, this is a continuous variable. Respect2-- following Respect1, this variable represents participants respect for others after the intervention. It uses the same questionnaire and is calculated in the same way as Respect1. Again, this is a continuous variable.
Getting descriptive statistics in Jamovi. Now you've had a chance to explore what the different variables are. You need a way to inspect and summarize the data so you can get a better idea of any patterns that may exist within it. You can do this by looking at descriptive statistics for the data. To obtain the descriptive statistics, you need to click on Analyses, select Exploration, and click Descriptives.
This will bring up the Descriptives dialog box. It has the names of your variables in the pane on the left-hand side, and empty panes on the right-hand side, labeled Variables and Split by. When producing descriptive statistics, you only want to do so for continuous and ordinal variables. It doesn't make sense to ask Jamovi to produce means and standard deviations for nominal data.
Continuous variables are represented by a ruler symbol, ordinal variables by a bar chart, and categorical variables by the three circles. Always remember to check that these are set correctly before beginning any analyses. See previous tutorials for details.
To tell Jamovi which variables you want descriptive statistics for, you need to move the variables from the box on the left-hand side to the boxes on the right. This process is quite common for many of the analyzes you will undertake using Jamovi. First, select the Enjoyment variable in the left-hand box and click on the arrow to move it to the right-hand box titled Variables. Then select the Respect1 variable in the left-hand box and click on the arrow to move it to the right-hand box titled Variables.
Next, select Respect2 variable in the left-hand box, and click on the arrow to move it to the right-hand box titled Variables. Once you've done this, it should look like this. If you wanted to produce separate statistics for different groups of participants, you would add the appropriate grouping variable to the Split by box. For example, if you moved Gender_ID into the Split by box, Jamovi would calculate separate enjoyment and respect scores for each gender identity. For the purposes of this tutorial though, just leave this box empty.
Next, click on the arrow next to Statistics to expand the options available. Once you've expanded this box, you will see the descriptive statistics that Jamovi selects by default. For the purpose of this tutorial, let's add the range to our descriptive statistics. To do this, select the box to the left of this option so the box becomes ticked. Once this has all been done, the output will update on the right-hand side of the window.
The output. The descriptive statistics table displays all the information you've requested. Variable names are listed at the top-- Enjoyment, Respect1, Respect2-- with the descriptives listed in the left-hand column. These descriptive statistics represent the following-- N stands for the number of participants. This column simply tells you how many participants you have data for each variable. We have 50 participants in our data set, so our N equals 50 for each variable.
Missing-- this tells us if we have any data missing from our data set. In this case, missing equals 0. So we know we do not have any data missing. Mean-- the mean column shows the mathematical average for each of the variables. This is the sum of the scores divided by the number of scores, or the N. Median-- the median represents the middle number or data point in the data set, if the data was arranged from the lowest value data point to the highest value data point.
Standard deviation-- this column displays the standard deviation for each variable. This refers to the spread of the scores around the mean, and represents how much variation you have in the data. The larger the values relative to the means, the more disperse the scores are. Range-- this column measures the spread of the scores obtained. Essentially, the range is the difference between the highest and the lowest value. Minimum-- this refers to the lower end of the range, and the minimum column is the lowest score of the variable in each row. Maximum-- this refers to the upper end of the range, and the maximum column is the highest score of the variable in each row.
When carrying out research that has continuous data, you should always report the means and standard deviations of your variables, as each statistic provides a useful summary to help make sense of the data. They are usually reported to two decimal places. In this case, looking at the table, you could say on average, pupils seem to enjoy the Linking Schools Project with a mean enjoyment score of 3.74 standard deviation 1.14. In addition, participants respect scores before taking part in the project appeared lower, with a mean of 71.10 and a standard deviation of 13.60. Then afterwards-- where the mean was 79.44 and the standard deviation was 11.70.
Now you have been shown how to enter data and produce descriptive statistics. Why don't you try creating your own set and calculating the means, standard deviations, and other descriptive statistics? Or download the data file used in this tutorial and see if you can produce the same output yourself. Why not explore these options and see what output you can produce? Practicing using Jamovi yourself will help you increase your confidence with using the program and analyzing statistics. So we really do recommend that you take advantage of any opportunities for practice that are available.