Statistical Data Analysis with SAS

Learn the SAS workflow for general data analysis, including libraries, datasets, variables, and basic coding rules, plus importing data, creating permanent datasets, and planning for future lectures.

Learn the SAS workflow from planning and data preparation to analysis and reporting, using data steps and proc steps to prepare, analyze, interpret results, and generate reports.

Learn how to import external files into SAS with proc import, using datalines for in-stream data and options like out=, datafile=, dbms, delimiter, and the Excel import wizard.

Use the SAS 9.x import wizard to import an Excel sheet, store the dataset in a library, name it, save the SAS code to a standalone file, and finish.

Import excel data into SAS Studio from a shared folder by selecting worksheet, outputting to the WORK library, and enabling generate SAS variable names; CSV or TXT imports are supported.

Bring in a preexisting SAS data set from a library into the work library using the set statement and two-level names, then create a permanent dataset by specifying location.

Master data manipulation in SAS by creating new variables with if-then-else, applying do loops, and performing subsetting, appending and concatenation, merging, and transposition to prepare clean datasets for analysis.

Master SAS naming conventions for library, dataset, and variable names, including length limits, allowed characters, and case-insensitivity, then distinguish numeric versus character variables, length requirements, and missing values.

Master conditional code with if then else statements, use operators on numeric and character values, and categorize ranges (like senior and smoking_status) with else if.

Learn how to keep or drop variables in SAS using dataset options and keep or drop statements, with examples showing their equivalence.

Explore SAS data manipulation with numeric and character functions, applied to the correct variable type. Learn the do loop and counter variable for repetitive tasks.

Explore SAS functions for numeric and character data, including min, max, sum, mean, and missing values. Learn string operations like cat, strip, upcase, substr, and scan.

Explore dataset-level data manipulation techniques, including subsetting and appending, and learn how to use set, where, and if statements, plus proc append for concatenation.

Learn how to subset SAS data using the set, where, if, and between operators, with firstobs and obs options, plus creating temporary work datasets from sashelp.heart.

Learn to concatenate SAS data sets with the set statement and to append with proc append using base equals and data equal to merge two datasets.

Learn how to merge SAS datasets using a by statement and proc sort to create a combined dataset. Explore match merge and one-to-one merge and their sorting requirements.

Explore descriptive statistics techniques in statistical data analysis with SAS, from data preparation to pattern discovery, using proc print, means, univariate, and freq for continuous and categorical data.

Learn descriptive statistics in SAS using proc means, univariate, and freq to summarize numeric and categorical data. Use by and class statements and output data sets for tailored analyses.

Explore hypothesis testing concepts with one-sample and three-or-more-sample t tests and ANOVA, including null and alternative hypotheses, alpha levels, p-values, and the role of descriptive statistics.

Apply the one-sample t test to determine whether a sample mean differs from a specified mean, mu zero. Use SAS procedures—proc t test, proc means, and proc univariate—to assess p-values.

Learn to perform two-sample t tests in SAS to compare means between two groups, using pooled or Satterthwaite methods and evaluating variance equality; apply paired t tests for related data.

Explore analysis of variance for comparing three or more means with SAS proc Anova. Learn to use class and model statements, interpret p-values, and apply Duncan, Tukey, and Bonferroni methods.

John introduces linear regression to predict outcomes, contrasts statistical significance with meaningful difference, and covers simple and multiple regression, dummy coding, descriptive statistics, and hypothesis testing.

Learn to convert categorical variables like gender and weight status into dummy variables for regression analysis, using if-then-else in SAS and interpreting the resulting coefficients.