MINISSA in Hamlet II for multidimensional scaling

The last article talked about the application and interpretation of singular value decomposition (MDPREF) using Hamlet II to represent the number of subjects preferred by each group of stimuli in graphical form. This article focuses on the application and interpretation of non-metric Multidimensional Scaling (MDS) method Michigan-Nijmegen Integrated Smallest Space Analysis (MINISSA) in Hamlet II.

MINISSA is one of the most preferred methods of non-metric multidimensional scaling. Using each of these methods will result in the three-dimensional graph displaying the corresponding labeled points of the words in the original text file.

Similar to a lot of other analyses, MDS also takes one of the joint frequency output, matrix standardized joint frequencies, as its input. After saving the file (in this case “sample matrix.mat”), MDS can be performed as many times with different combinations of items present in the existing word list without the need of starting the whole process again.

Steps to perform MINISSA using Hamlet II

Follow the below steps to perform MDS technique MINISSA using Hamlet II.

Step 1

  • Go to Tool Bar.
  • Select ‘MDS’
  • Click on ‘Multidimensional Scaling’.
Figure: Selecting the matrix file for performing MINISSA in Hamlet II

Figure 1: Selecting the matrix file for performing MINISSA in Hamlet II

Step 2

The second step is to select the matrix file to perform the analysis. Select the number of dimensions for displaying in a graph.  Click on “Scale these items” to generate the graph.

The below figure shows the plotting of the dimensions of all the keywords in a 3D graph. To retrieve these dimensions, click on ‘Data’ on the toolbar. It will also show Spence’s approximation for Kruskal’s Stress values. This window also provides a few basic options or tools to make changes and toggle the setting of the plots.

Figure 2: Graphical presentation of the matrix in MINISSA

Figure 2: Graphical presentation of the matrix in MINISSA in Hamlet II

One can also generate the same results in network form by clicking on “Toggle Display” as shown in the figure above and selecting ‘Network’ as shown in the figure below.

Figure 3: Network map for the matrices

Editing the MINISSA graph

Options present in Hamlet II for editing the MINISSA graph are:

  1. Tools like ‘Left’, ‘Right’, ‘Down’ and ‘Up’ for making changes in the orientation of the currently displayed graph.
  2. Keys like ‘In’ and ‘Out’ allow the user to magnify a specific part of the graph in order to focus and make changes.
  3. With the help of basic drawing functions, one may draw on the graph.
  4. ‘Line’ function helps to create straight lines anywhere on the graph and also to make changes in colour and thickness of lines on the graph.
  5. ‘Ellipse’ helps to create perfect ellipse on the graphs.
  6. ‘Text’ allows the user to write text on the graph.
  7. Simply click on the axis to rotate the configurations clockwise where needed. One can also use the keys 1, 2 and 3 to rotate the configurations clockwise.
  8. ‘Labels’ option allows modifying the number of characters in all the labels. Also, click the label points using a mouse to highlight the labels, if needed.
  9. ‘Reflect’ option on the output window toolbar helps the user to simply mirror the plot vertically or horizontally.
  10. “Grid” option helps in toggling the grid of the graph.

Metric scaling of MDS

MINISSA in Hamlet II is a non-metric analysis displaying a matrix of joint word frequencies of individual texts in 3D form. This type of text-based quantitative analysis allows graphical and network presentation of the word usage or co-occurrence of categories. The advantage of using non-metric textual analysis is that it allows identification of various categories of the search list to be distributed throughout the transcript. The next article explains the metric scaling of MDS.

Avishek Majumder

Avishek Majumder

Research Analyst at Project Guru
Avishek is a Master in Biotechnology and has previously worked with Lifecell International Private Limited. Apart from data analysis and biological research, he loves photography and reading. He loves to play football and basketball in his spare time with an avid interest in adventure and nature. He was also a member of the Scouts in his school and has attended Military training.
Avishek Majumder

Related articles

Discuss

We are looking for candidates who have completed their master's degree or Ph.D. Click here to know more about our vacancies.