- Title of the workshops / seminars conducted: Systematic Review and Meta-Analysis Hands-On Workshop
- Date: 21st June 2019, Time: 9 am to 1pm and Venue: Computer Lab, Symbiosis Statistical Institute, Pune
- Resource Person(s): Dr. Rahul Mhaskar, Director- Morsani College of Medicine office RISE and Associate Professor at Department of Internal Medicine, University of South Florida, USA
- Abstract/short note on the workshop/seminar: This workshop aimed to give an introduction to systematic literature review and meta-analysis of research studies. There was a detailed discussion about the approach for conducting a systematic review in which different examples were taken up to explain the process. The difference between systematic review and meta-analysis was explained, highlighting the use of quantitative analysis in the latter. This was followed by a step-by-step tutorial on using RevMan for conducting metaanalysis.
- Approximate number of attendees:36
Title of the workshop- R Workshop
Date: May 8-9 and May 15-16, 2021
Resource persons: SSI faculty and industry experts
Short note on workshop: Symbiosis Statistical Institute, Pune (SSI) organized a virtual four-day hands-on workshop on R in collaboration with Symbiosis School of Economics (SSE)..
The first day of the workshop began with a brief introduction of the workshop and the hosts of the session given by Dr. Sharvari Shukla, Director and Professor at SSI. In the first session we explained the basics of the R programming language, the importance of it and why it is such a popular tool in the industry. And we also guided the participants in installing the R packages and explained the ABC of R by introducing them to the built-in data types, including Lists, Vectors and Matrices, as well as doing basic operations such as Mathematical or Logical, etc. Further, we explained the Flow Control and Loops, Slicing and Indexing and lastly Functions and Exception Handling which are extremely vital fundamentals to learn before going for advanced concepts. After the buildup of learning the basics of R, this session was more focused on the application part of the programming language. This included how to import the CSV and Excel files in the R environment as well as creating data frames out of it.
Further resource persons focused on the application part of R for the purpose of Data Analysis, majorly focusing on Data Visualization. We also used and explained about different libraries for the purpose of Data Analysis and Data Manipulation. On last day of the workshop carried forward the knowledge of the last three days to understand the process of model building in real life. Experts initiated the session with Likert Scale analysis in R using different parametric and Non parametric tests which is an important part of the survey data analysis. Followed by this, the students were given a brief introduction of classification modelling, Logistic regression which is extensively used in financial domain. The students learned credit risk modelling in R for this. Finally, a walkthrough to the QuantMod library which gives real time data for Time series analysis was given. Also, State wise COVID 19 results were used to familiarize the students with Linear Regression and ARIMA modelling in R. The four-day workshop concluded with a Q&A session, where the hosts helped the participants clearing any doubts, they had regarding the content taught in the workshop.
Approximate number of attendees: 25
Title of the workshop- Python Workshop
Date: April 24-25 and May 1-2 , 2021.
Resource persons: SSI faculty and industry experts
Short note on workshop: Symbiosis Statistical Institute, Pune (SSI) organized a virtual two-day hands-on workshop on Python in collaboration with Symbiosis School of Economics (SSE) on May 1st– 2nd, 2021. The workshop was attended by Final Year students of BSc and MSc students from SSE for an opportunity to learn.
During the first day session resource persons explained the basics of the Python programming language, the importance of it and why it is such a popular tool in the industry. They guided the participants in installing the Python environments and explained the ABC of Python by introducing them to the built-in data types, including Lists, Dictionaries and Sets, as well as doing basic operations such as Mathematical or Logical, etc. Further, explained the Flow Control and Loops, Slicing and Indexing and lastly Functions and Exception Handling which are extremely vital fundamentals to learn before going for advanced concepts.
In the second session, the focus moved to the NumPy package, which is a basic but a really important library in Python as a lot of advanced libraries are built on its basis. This session covered how to create multi-dimensional arrays and matrices using NumPy as well as the indexing and slicing them for the purpose of data manipulation.
The final session of the day introduced Pandas libraries, which is one of the most popular libraries used for the purpose of Data Analysis and Data Manipulation. After the buildup of first two sessions of learning the basics of Python, this session was more focused on the application part of the programming language. This included how to import the CSV and Excel files in the Python environment as well as creating data frames out of it. Along with that, the participants also learned about conducting exploratory data analysis of the data such as basic statistics, missing values, etc. and fitting a linear regression model on the data. The day ended with further Q&A about the doubts and difficulties by the students.
Second day of the workshop was focused on the application part of Python for the purpose of Data Analysis. The session introduces the participants with different Data Visualization techniques such as Bar plots, Scatter plots, Histogram, etc. which was done using the Matplotlib and Seaborn libraries.
The penultimate session was about carrying out different types of basic Statistical tests such as t-test, test for Normality and Heteroscedasticity as well looking for Multicollinearity in the data along with correlation matrix. Many of these tests form the pre-checks which are required to be conducted before fitting a regression model to satisfy its assumptions. All of these was explained with a hands-on approach by using a data of bank customers based on their credit card spending. The final session of the workshop saw Data modelling using the sklearn library which includes various regression as well classification models. This was demonstrated specifically with an example of Logistic regression. Further, the hosts talked about how to import data using an API key with example of Quandl, a data source website used for obtaining a wide range of Financial as well as Economic data. Lastly, a stock price data of Tesla and General Motors imported from Quandl was used to demonstrate how to approach and perform basics functions of Time Series Analysis in Python. The two-day workshop concluded with a Q&A session, where the hosts helped the participants clearing any doubts they had regarding the content taught in the workshop.
Approximate number of attendees: 113