Notes on digital tools for data analysis for UGC NET Paper 1 Research Aptitude, in 5 short sub-topics. Each one gives the concept, the facts to memorise and the traps examiners set.
5 sub-topics
11 memory points
5 exam-trap notes
4 min read
Topic 23 of 29
What this topic covers
5 sub-topics, in the order to study them. Tap one to jump to it.
SPSS (Statistical Package for the Social Sciences, now IBM SPSS) is menu-driven and popular in social science and education. SAS is strong in business and pharmaceutical analytics; Stata in economics and epidemiology; Minitab in quality control; EViews in time-series econometrics; AMOS and LISREL in structural equation modelling; SmartPLS in PLS-SEM. R is a free, open-source language for statistics with thousands of packages on CRAN and the RStudio environment, and Python (pandas, NumPy, SciPy, statsmodels, scikit-learn) serves data science. PSPP is a free SPSS-like program, and JASP and jamovi are free graphical programs built on R. Excel handles basic statistics through its Data Analysis ToolPak.
Memorise
SPSS = social sciences; SAS = business/pharma; Stata = economics; R = free and open source.
PSPP, JASP and jamovi = free alternatives with menus.
AMOS/LISREL = SEM.
Analyse / traps
R and Python need code; SPSS, JASP and jamovi can be used through menus.
CAQDAS (computer-assisted qualitative data analysis software) helps organise, code and retrieve text, audio, video and images. Leading packages are NVivo, ATLAS.ti, MAXQDA, Dedoose (web-based and suited to mixed methods), QDA Miner and the free Taguette. Typical functions are coding (called nodes in NVivo), queries, word-frequency counts, word clouds and matrix comparisons. Voyant Tools is a web-based text-analysis tool, AntConc supports corpus linguistics, and sentiment analysis and topic modelling (such as LDA) apply computational text mining. The software stores and retrieves codes; the researcher still decides what the codes and themes mean.
5C.3Visualisation, Data Mining and Computational Tools#
Concept
Tableau, Power BI and Looker Studio build interactive dashboards; Datawrapper and Flourish produce web charts; Gephi analyses networks; VOSviewer (from Leiden University) and CiteSpace map bibliometric networks. For mining and machine learning, WEKA (University of Waikato), Orange, KNIME and RapidMiner offer visual workflows. Jupyter Notebook is an interactive document that combines code, output and text for Python, R and Julia, and Google Colab provides Jupyter-style notebooks in the cloud. Python’s Matplotlib, Seaborn and Plotly and R’s ggplot2 are common plotting libraries.
Memorise
VOSviewer: bibliometric maps. Gephi: networks. WEKA: data mining. Jupyter: code + text notebooks.
Colab: cloud notebooks. ggplot2: R graphics.
Analyse / traps
Tableau and Power BI are for visualisation, not for storing or collecting data.
5C.4Collaboration and Writing Tools: Git, Overleaf and LaTeX#
Concept
Git, created by Linus Torvalds in 2005, is a distributed version-control system that tracks changes to files, and GitHub and GitLab host Git repositories for collaboration. LaTeX (based on TeX by Donald Knuth and developed by Leslie Lamport) is a typesetting system favoured for mathematical and technical documents, with BibTeX handling references, and Overleaf is an online collaborative LaTeX editor. Google Docs and Microsoft 365 allow real-time co-editing. The Open Science Framework (OSF) supports project management and pre-registration, Zenodo (from CERN) and Figshare issue DOIs for data and code, and protocols.io shares methods.
Memorise
Git: version control (Torvalds, 2005). LaTeX: typesetting. Overleaf: online LaTeX. OSF: open-science projects and pre-registration.
Zenodo and Figshare: DOIs for datasets.
Analyse / traps
Git tracks versions of files; it is not a word processor.
A Geographic Information System (GIS) captures, stores, analyses and displays spatial data in layers. ArcGIS (Esri) is commercial, QGIS is free and open source, and Google Earth Engine handles large satellite archives; in India Bhuvan is ISRO’s geoportal. Data cleaning detects and corrects errors, duplicates, inconsistent labels, missing values and outliers before analysis. OpenRefine (formerly Google Refine) clusters and standardises messy data, and Excel Power Query and R’s tidyverse also support data wrangling. Cleaning decisions must be documented so the analysis stays reproducible.
Last updated: . Notes are a revision aid; check official UGC sources for any rule or scheme that changes over time. Spotted a mistake? Write to netlawverse@gmail.com.