﻿ Workshop on Statistical Modeling via SPSS | SLIIT

### Workshop on Statistical Modeling via SPSS All phenomenon in the real world are nondeterministic. In statistics, modeling is considered as a tool to develop a statistical equation to explain the variability of an observed response variable using one or more explanatory variables. The basic concept of modelling is:

Observed response variable = model + error.

Thus, the model should have a systematic pattern while the error should not have a systematic pattern. Such modeling is generally carried out under regression environment.   The regression models are

very popular among statistics users. The regression models are the key tools in predictive analytics in data science and such models are used when we need to incorporate uncertainty explicitly in the underlying observed data.

Regression analysis is a form of predictive modelling technique which investigates the relationship between a dependent (target) and independent variable (s) (predictor).  Such modelling is useful in data driven decision making (DDDM).

Developing regression models using SPSS is not a difficult task.  Whatever you input to the computer you will get something, “Garbage in garbage out”. The important thing is how to decide the correct model, how it is convey to any users and how to interpret results so that it can be understood by any client for the use of planning based on data.

Learning Objectives

On the successful completion of the course participants will be able to:

• Understand what regression is and how to visualize data,
• Decide the best type of models to be fitted for data
• Validate models
• Derive inferences and interpret results based on SPSS outputs
• Use SPSS with confident for modeling
• Write statistical reports
• Introduction
• Concept of modeling
• Type of Data measurement,
• Correlation coefficient
• Simple Linear Regression
• Fitting models (Example 1)
• Hypothesis testing
• Coefficient of determination (R2)
• Detecting outliers
• Validation of model
• Interpretation of the model
• Interpretation of confidence intervals
• Prediction
• Recommendations and report writing
• Non linear models
• Introduction to intrinsically linear and non-linear models
• Model development (Example 2)
• Writing the model
• Interpretation
• Multiple linear regression
• Concept of multiple regression
• Use of example 3
• Partial correlation coefficient
• Interpretation standardized and unstandardized estimates
• Selection of variables
• Use of example 4
• Multicollinearity problem
• Interpretation results
• Report writing
• Binary Logistics Regression
• Concept of logistics model
• Basic theory of Binary logistic
• Concept of odds and odds ratio
• Model development (Example 5)
• Interpretation and writing reports

Researchers, Acedemics,  PG students and Policy Makers

Professor Sarath Peiris is the Head of the Department of Mathematics, Faculty of Humanities and Sciences in SLIIT, Malabe. He received the President’s Award for Scientific Publications in four years. He has done many workshops and short-term courses on various area in Statistics using SPSS under IASSL. His research areas are Multivariate Statistics, Regression Modelling, Time Series Modelling, Teaching Statistics and Climate Change.

Online/In Class/Hybrid

#### Commencement Date: 21st August 2021 (Saturday)

24 Hours |  Saturdays from 9 am to 5 pm

Per Participant Fee: Rs. 12,000/-

Program fee can be paid to/transferred to Bank of Ceylon in favor of the SLIIT current A/C 0072821605 and the receipt should be emailed to romi.f@sliit.lk before the commencement of the Program. Please mention your NIC Number on the Bank Deposit Slip, when making the payment as it is required to cross check the payment.

Following are the required Payment Details:

• Name of the Bank – Bank of Ceylon
• Name of the Account – Sri Lanka Institute of Information Technology
• Account Number - 0072821605
• Branch – Kollupitiya
• Branch Code - 034

### RESERVE A SEAT

#### To confirm your seat please hand over your bank slip before the class commencement to avoid any disappointments.

[]
1 Step 1   