Data Analytics Using SAS Training Course

  Module-1 SAS Base Programming
Part-1 Access and Create Data Structures 
·       Lecture-1 SAS Programs

·       Introduction to SAS programs

·       Submitting a SAS program

·       Working with SAS program syntax

·       Lecture-2 Create temporary and permanent SAS data sets.

·       Use a DATA step to create a SAS data set from an existing SAS data set.

·       Example:

·       Data Mylib.NewData;

·       Set Mylib.OldData;

·       <other SAS statements>

·       Run;

·       Lecture-3 Investigate SAS data libraries using base SAS utility procedures.

·       Use a LIBNAME statement to assign a library reference name to a SAS library.

·       Investigate a library programmatically using the CONTENTS procedure.

·       Lecture-4 Combine SAS data sets.

·       Concatenate data sets.

·       Merge data sets one-to-one.

·       Merge data sets one-to-many.

·       Lecture-5 Access an Excel workbook.

·       Use the SAS/ACCESS XLSX engine to read an .xlsx file.

·       Lecture-6 Create and manipulate SAS date values.

·       Explain how SAS stores date and time values.

·       Use SAS date and time formats to specify how the values are displayed.

·       Lecture-7 Export data to create standard and comma-delimited raw data files.

·       Create a simple raw data file by using the EXPORT procedure as an alternative to the DATA step.

·       Lecture-8 Control which observations and variables in a SAS data set are processed and output.

·       Use the WHERE statement in the DATA step to select observations to be processed.

·       Subset variables to be output by using the DROP and KEEP statements.

·       Use the DROP= and KEEP= data set options to specify columns to be processed and/or output.

Part-2 Manage Data 
·       Lecture-9 Sort observations in a SAS data set.

·       Use the SORT Procedure to re-order observations in place or output to a new dataset.

·       Lecture-10 Conditionally execute SAS statements.

·       Use IF-THEN/ELSE statements to process data conditionally.

·       Use DO and END statements to execute multiple statements conditionally.

·       Lecture-11 Use assignment statements in the DATA step.

·       Create new variables and assign a value.

·       Assign a new value to an existing variable.

·       Assign the value of an expression to a variable.

·       Assign a constant date value to a variable.

·       Lecture-12 Modify variable attributes using options and statements in the DATA step.

·       Change the names of variables by using the RENAME= data set option.

·       Use LABEL and FORMAT statements to modify attributes in a DATA step.

·       Define the length of a variable using the LENGTH statement.

·       Lecture-13 Accumulate sub-totals and totals using DATA step statements.

·       Use the BY statement to aggregate by subgroups.

·       Lecture-14 Use SAS functions to manipulate character data, numeric data, and SAS date values.

·       Use SAS functions such as SCAN, SUBSTR, TRIM, UPCASE, and LOWCASE to perform tasks such as the tasks shown below.

·       Replace the contents of a character value.

·       Trim trailing blanks from a character value.

·       Search a character value and extract a portion of the value.

·       Convert a character value to upper or lowercase.

·       Use SAS arithmetic, financial, and probability functions to create or modify numeric values by using the INT and ROUND functions.

·       Create SAS date values by using the functions MDY, TODAY,DATE, and TIME.

·       Extract the month, year, and interval from a SAS date value by using the functions YEAR, QTR, MONTH, and DAY.

·       Perform calculations with date and datetime values and time intervals by using the functions INTCK, INTNX, DATDIF and YRDIF.

·       Lecture-15 Use SAS functions to convert character data to numeric and vice versa.

·       Explain the automatic conversion that SAS uses to convert values between data types.

·       Use the INPUT function to explicitly convert character data values to numeric values.

·       Lecture-16 Process data using DO LOOPS.

·       Explain how iterative DO loops function.

·       Use DO loops to eliminate redundant code and to perform repetitive calculations.

·       Use conditional DO loops.

·       Use nested DO loops.

·       Lecture-17 Validate and clean data.

·       Use PROC FREQ to list unique values, with the nlevel option to show the number of distinct values, with the order=freq to check for duplicate or missing values.

·       Use PROC PRINT with the WHERE statement to display observations with invalid values.

·       Use PROC MEAN to validate the range of numeric variables.

·       Use PROC UNIVARIATE to display extreme observations and missing values and with the ID statement to display the value of identifying variable(s)

Part-3 Generate Reports 
·       Lecture-18 Generate list reports using the PRINT procedure.

·       Modify the default behavior of PROC PRINT by adding statements and options such as

·       use the VAR statement to select and order variables.

·       calculate totals with a SUM statement.

·       select observations with a WHERE statement.

·       use the ID statement to identify observations.

·       use the BY statement to process groups.

·       Lecture-19 Generate summary reports and frequency tables using base SAS procedures.

·       Produce one-way and two-way frequency tables with the FREQ procedure.

·       Enhance frequency tables with options.

·       Use PROC FREQ to validate data in a SAS data set.

·       Calculate summary statistics and multilevel summaries using the MEANS procedure

·       Enhance summary tables with options.

·       Identify extreme and missing values with the UNIVARIATE procedure.

·       Lecture-20 Enhance reports through the use of user-defined formats, titles, footnotes and SAS System reporting.

·       Use the LABEL statement to define descriptive column headings.

·       Control the use of column headings with the LABEL and SPLIT=options in Proc Print output.

·       Lecture-21 Generate reports using ODS statements.

·       Identify the Output Delivery System destinations.

·       Create HTML, PDF, RTF, and files with ODS statements.

·       Use the STYLE=option to specify a style template.

·       Create files that can be viewed in Microsoft Excel.

Part-4 Error Handling 
·       Lecture-22 Identify and resolve programming logic errors.

·       Use the PUTLOG Statement in the Data Step to help identify logic errors.

·       Use PUTLOG to write the value of a variable, formatted values, or to write values of all variables.

·       Use PUTLOG with Conditional logic.

·       Use temporary variables N and ERROR to debug a DATA step.

·       Lecture-23 Recognize and correct syntax errors.

·       Identify the characteristics of SAS statements.

·       Define SAS syntax rules including the typical types of syntax errors such as misspelled keywords, unmatched quotation marks, missing semicolons, and invalid options.

·       Use the log to help diagnose syntax errors in a given program.

·       Lecture-24 Examine and resolve data errors.

·       Given a SAS program, use the log to determine the reason for a data error.

  Module-2 SAS Advance Programming
Part-1 Accessing Data Using SQL 
·       Lecture-1 Generate detail reports in SQL

·       Use PROC SQL to perform SQL queries.

·       Select columns in a table with a SELECT statement and FROM clause.

·       Create a table from a query result set.

·       Create new calculated columns.

·       Assign an alias with the AS keyword.

·       Use case logic to select values for a column.

·       Retrieve rows that satisfy a condition with a WHERE clause.

·       Subset data by calculated columns.

·       Join tables - inner joins, full joins (coalesce function), right joins, left joins.

·       Combine tables using set operators - union, outer union, except, intersect.

·       Sort data with an ORDER BY clause.

·       Assign labels and formats to columns.

·       Lecture-2 Generate summary reports in the SQL.

·       Summarize data across and down columns using summary functions (AVG, COUNT, MAX, MIN, SUM).

·       Group data using GROUP BY clause.

·       Filter grouped data using HAVING clause.

·       Eliminate duplicate values with the DISTINCT keyword.

·       Lecture-3 Construct sub-queries and in-line views.

·       Subset data by using non-correlated subqueries.

·       Reference an in-line view with other views or tables (multiple tables).

·       Lecture-4 Use SAS SQL procedure enhancements.

·       Use SAS data set options with PROC SQL (KEEP=, DROP=, RENAME=, OBS=).

·       Use PROC SQL invocation options (INOBS=, OUTOBS=. NOPRINT, NUMBER)

·       Use SAS functions (SCAN, SUBSTR, LENGTH).

·       Access SAS system information by using DICTIONARY tables (members, tables, columns)

·       Use the CALCULATED keyword.

Part-2 Macro Processing 
·       Lecture-5 Uuse user-defined and automatic macro variables

·       Use macro variable name delimiter. (.)

·       Use INTO clause of the SELECT statement in SQL to create a single variable or a list of variables.

·       Use the SYMPUTX routine in a DATA Step to create a single variable or a list of variables.

·       Control variable scope

·       Lecture-6 Automate programs by defining and calling macros.

·       Define a macro using the %MACRO and %MEND statements.

·       Calling a macro with and without parameters.

·       Document macro functionality with comments

·       Generate SAS Code conditionally by using the %IF-%THEN-%ELSE macro statements or iterative %DO statements.

·       Use the SAS AUTOCALL facility to permanently store and call macros.

·       Lecture-7 Use macro functions.

·       Use macro functions. (%SCAN, %SUBSTR, %UPCASE)

·       Use macro quoting functions. (%NRSTR, %STR)

·       Use macro evaluation functions. (%SYSEVALF)

·       Use %SYSFUNC to execute DATA step functions within the SAS Macro Language.

·       Lecture-8 Debug macros.

·       Trace the flow of execution with the MLOGIC option.

·       Examine the generated SAS statements with the MPRINT option.

·       Examine macro variable resolution with the SYMBOLGEN option.

·       Use the %PUT statement to print information to the log.

·       Lecture-9 Data-driven programs using SAS Macro Language.

·       Create a series of macro variables.

·       Use indirect reference to macro variables. (&&, etc.)

·       Incorporate DICTONARY tables in data driven macros.

·       Generate repetitive macro calls.

Part-3 Advanced Techniques 
·       Lecture-10 Process data using 1 and 2 dimensional arrays.

·       Define and use character arrays.

·       Define and use numeric arrays.

·       Create variables with arrays.

·       Reference arrays within a DO loop.

·       Specify the array dimension with the DIM function.

·       Define arrays as temporary arrays.

·       Load initial values for an array from a SAS data set.

·       Lecture-11 Process data using hash objects.

·       Declare hash and hash iterator objects

·       Dataset argument

·       Ordered argument

·       Multidata argument

·       Use hash object methods

·       definekey()

·       definedata()

·       definedone()

·       find()

·       add()

·       output()

·       Use hash iterator object methods

·       first()

·       next()

·       last()

·       prev()

·       Use hash objects as lookup tables.

·       Use hash objects to create sorted data sets.

·       Use hash iterator objects to access data in forward or reverse key order.

·       Lecture-12 Use SAS utility procedures.

·       Specify a template using the PICTURE statement within the FORMAT Procedure*

·       Specify templates for date, time, and datetime values using directives.

·       Specify templates for numeric values using digit selectors.

·       PICTURE statement options: round, default, datatype, multiplier, prefix

·       Create custom functions with the FCMP procedure

·       Create character and numeric custom functions with single or multiple arguments.

·       Create custom functions based on conditional processing.

·       Use custom functions with the global option CMPLIB=.

·       Lecture-13 Use advanced functions.

·       Finding strings or words with the FINDC/FINDW functions.

·       Counting strings or words with the COUNT/COUNTC/COUNTW functions.

·       Retrieve previous values with the LAG function.

·       Regular expression pattern matching with PRX functions

  Module-3 SAS/ETS Programming Training
Part-1 Overview of Time Series 
·       Lecture-1 Introduction

·       Lecture-2 Analysis Methods and SAS/ETS Software

·       Options

·       How SAS/ETS Software Procedures Interrelate

·       Lecture-3 Simple Models: Regression

·       Linear Regression

·       Highly Regular Seasonality

·       Regression with Transformed Data

Part-2 Simple Models: Autoregression 
·       Lecture-4 Introduction

·       Terminology and Notation

·       Statistical Background

·       Lecture-5 Forecasting

·       Forecasting with PROC ARIMA

·       Backshift Notation B for Time Series

·       Yule-Walker Equations for Covariances

·       Fitting an AR Model in PROC REG

Part-3 General ARIMA Model 
·       Lecture-6 Introduction

·       Statistical Background

·       Terminology and Notation

·       Lecture-7 Prediction

·       One-Step-Ahead Predictions

·       Future Predictions

·       Lecture-8 Model Identification

·       Stationarity and Invertibility

·       Time Series Identification

·       Chi-Squared Check of Residuals

·       Summary of Model Identification

·       Lecture-9 Examples and Instructions

·       IDENTIFY Statement for Series

·       Example: Iron and Steel Export Analysis

·       Estimation Methods Used in PROC ARIMA

·       ESTIMATE Statement for Series

·       Nonstationary Series

·       Effect of Differencing on Forecasts

·       Examples: Forecasting IBM Series and Silver Series

·       Models for Nonstationary Data

·       Differencing to Remove a Linear Trend

·       Other Identification Techniques

Part-4 ARIMA Model: Introductory Applications 
·       Lecture-10 Seasonal Time Series

·       Introduction to Seasonal Modeling

·       Model Identification

·       Lecture-11 Models with Explanatory Variables

·       Case 1: Regression with Time Series Errors

·       Case 1A: Intervention

·       Case 2: Simple Transfer Function

·       Case 3: General Transfer Function

·       Case 3A: Leading Indicators

·       Case 3B: Intervention

·       Lecture-12 Methodology and Example

·       Case 1: Regression with Time Series Errors

·       Case 2: Simple Transfer Functions

·       Case 3: General Transfer Functions

·       Case 3B: Intervention

·       Lecture-13 Further Examples

·       North Carolina Retail Sales

·       Construction Series Revisited

·       Milk Scare (Intervention)

·       Terrorist Attack

Part-5 ARIMA Model: Special Applications 
·       Lecture-14 Regression with Time Series Errors and Unequal Variances

·       Autoregressive Errors

·       Example: Energy Demand at a University

·       Unequal Variances

·       ARCH, GARCH, and IGARCH for Unequal Variances

·       Lecture-15 Cointegration

·       Introduction

·       Cointegration and Eigenvalues

·       Impulse Response Function

·       Roots in Higher-Order Models

·       Cointegration and Unit Roots

·       An Illustrative Example

·       Estimating the Cointegrating Vector

·       Intercepts and More Lags

·       PROC VARMAX

·       Interpreting the Estimates

·       Diagnostics and Forecasts

Part-6 State Space Modeling 
·       Lecture-16 Introduction

·       Some Simple Univariate Examples

·       A Simple Multivariate Example

·       Equivalence of Statespace and Vector ARMA Models

·       Lecture-17 More Examples

·       Some Univariate Examples

·       ARMA (1, 1) of Dimension

·       Lecture-18 PROC STATESPACE

·       State Vectors Determined from Covariances

·       Canonical Correlations

·       Simulated Example

·       Lecture-18 PROC STATESPACE

·       State Vectors Determined from Covariances

·       Canonical Correlations

·       Simulated Example

·       Practical Exercise

Part-7 Spectral Analysis 
·       Lecture-19 Periodic Data: Introduction

·       Example: Plant Enzyme Activity

·       PROC SPECTRA Introduced

·      Testing for White Noise

·      Harmonic Frequencies

·      Extremely Fast Fluctuations and Aliasing

·      The Spectral Density

·       Some Mathematical Detail (Optional Reading)

·       Estimating the Spectrum: The Smoothed Periodogram

·       Cross Spectral Analysis

·       Interpreting Cross-Spectral Quantities

·       Interpreting Cross-Amplitude and Phase Spectra

·       PROC SPECTRA Statements

·       Cross-Spectral Analysis of the Neuse River Data

·       Details on Gain, Phase, and Pure Delay

Part-8 Data Mining and Forecasting 
·       Lecture-20 Introduction Data Mining and Forecasting

·       Forecasting Data Model

·       Time Series Forecasting System

·       HPF Procedure

·       Scorecard Development

·       Business Goal Performance Metrics

·       Graphical Displays

·       Goal-Seeking Model Development