3 days of focused workshop training on Statistics Modeling Using STATA Package
Statistical analysis is broken down into five discrete steps of; a) describing the nature of the data to be analysed, b) exploring the relationship between the selected data and the underlying population, c) creating a model in order to summarize the understanding of how the data relates to the underlying population, d) proving (or disprove) the validity of the model and the last step e) employing predictive analytics to run scenarios that will help guide future actions. Handling all these five steps which every person might experience it in different fields such as economics, social science, management, political science and etc. might be cumbersome without using an power full statistical package.
STATA is one of the powerful statistical software which commonly used in many disciplines. It is a known as a general-purpose statistical software package created in 1985 by StataCorp. STATA's capabilities include data management, statistical analysis, graphics, simulations, regression analysis (linear and multiple), and custom programming.
This course will show how to program and employ the powerful statistical commands available in STATA package by recalling some statistical concepts. The course include but not limited to , introducing STATA windows environment, discusses how to create a dataset, importing data from other sources, data manipulations, descriptive statistics and regression analysis. It will assist trainees in developing the data analysis skills necessary for autonomous and efficient computer processing, manipulation, and analysis of empirical data various fields such as social science and business.
Interactive lessons and analytical tools
Relevant and up-to-date content
Pre- course diagnostic test
Reference and support materials
At the end of the course, the trainee will:
At the end of the course, the trainee will:
Recall a basic understanding of statistics,
Be able to efficiently and professionally use of STATA package for statistical analysis and reporting the results,
Gain the self-confidence for the statistical solutions.
Who Should Attend?
Anyone who wants to learn the statistical concepts by using statistical methods with STATA,
Managers who are fighting to solve their daily problems involve statistical matters,
Statistical Fresh Researchers studying in different areas,
Data miners or researchers.
Day 1- Getting to know STATA, getting data into STATA and data manipulation
Background, advantages, and disadvantages of STATA,
Working with STATA: menu vs. command line vs. do files,
Help files, online PDF documentation,
Creating datasets and Data import: different ways of importing data,
Import data from main public data sources and dealing with missing values,
Generating new variables. Generate, Egen, Replace, Dummy variables, Lags and leads,
To recall the standard research phases, including but not limited to proposing a methodology, analyzing and reporting the results,
To emphasis on the importance of good data,
To recall what the descriptive statistics; frequencies and measure of tendency are and how to handle these all using STATA commands such as describe, summarize, tab, display, fre and ….,
Day 2- Some advanced analysis and reporting
To recall the concept of statistical significance and confidence interval , mean, standard deviation, correlation, one-way anova, two-way anova, percentiles, (t-)test on mean difference, comparing groups within one variable, compare two variables, using ci and etc.
Review of Least Squares Estimation, OLS with one explanatory variable,
Review of Least Squares Estimation, OLS with multiple explanatory variables,
Working with regress, estat hettest, imtest, whitetst,….
Post estimation commands such as prediction, hypothesis testing, extracting results such as ttest,
Regression including dummy variables; using xi: reg and i. commands,
Review of logistic Regression concepts,
Working with logit, probit, margins, ….
Day 3 Some advanced analysis and reporting
Panel data analysis
Data structure: Wide vs. long
Describe pattern of xt data
Summarize xt data
Tabulate xt data
Panel regressions using xtreg,
Time Series data
Stata Date and Time-series Variables
Getting dates into Stata format
Using the time series date variables
Making Use of Dates
Lag and forward operator
First difference and dlog
Time Series Tricks Using Dates
Graphing and programming in do files
Line plot, Legend, labels, shapes, colors, using tsline,
Scatter plot using scatter,
Combining graphs: ”twoway”, e.g. scatter with regression line
Working with Histogram, kdensity commands,
Plot the residuals versus the fitted values or predictor of y using rvfplot and rvpplot commands,
Creating and working with do files, clear, set, cd and use commands