Introduction to Statistics and Data Analysis with SAS

Explore learning from a single variable using graphical and numerical methods for categorical and numerical data. Examine mean, median, and skew, apply the empirical rule, and do a lab exercise.

Learn to construct a box plot from the five numbers, including the median, quartiles, min, and max, to visualize the center, spread, and shape.

Learn how to compute a five-number summary in SAS using proc univariate and proc means, identifying min, max, median, and first and third quartiles (P25, P75) from a data set.

Review lab solutions identifying female prevalence, age symmetry, and the right-skewed savings, with mean–median implications, and use of a SAS macro to generate histograms and apply the empirical rule.

Explore how to create and interpret a two-way frequency table for two categorical variables, such as gender and age group, using SAS, including cell counts, percentages, and margins.

Explore scatter plots and correlation with SAS, using fake data for X and Y to show a strong linear relationship (Pearson ~0.87) and a cubic case where correlation fails.

Learn to add lines of best fit and smoothing curves to scatter plots in Sas with proc sgplot, using linear and kubic data to reveal the data’s trend and curvature.

Explore lab three solutions, review scatterplot correlations and linear relationships, note how data without noise yields exact linearity, and consider non-linear patterns beyond correlation.

Explore randomness, probability, and inference; define key terms; learn about probability distributions, expected value, and the normal distribution, with hands-on lab exercises.

Explore probability distributions by defining outcomes and their probabilities from surveys and dice, and build a probability model that lists all possible outcomes with their probabilities.

The mean equals the expected value when all outcomes are equally likely; weighting probabilities changes the expected value, showing how a weighted distribution shifts the data center.

Construct confidence intervals for proportions using p-hat and the standard normal critical value, then interpret 95 percent coverage with two standard deviations.

Run a one-sample hypothesis test for a proportion against 0.6 using p-hat and a standardized statistic. Use the 1.64 critical value or the p-value to decide.

Demonstrate the sampling distribution for the mean by simulating 1,000 samples of 500 from a normal population (mean 35, standard deviation 8) and compare the mean and standard deviation.

Demonstrates a one-sample hypothesis test for a mean with 500 observations, using 34.8 and s=8.08 to compute se and p-value, concluding the null mean of 35 is not rejected.

Dive into lab solutions for statistics and data analysis with SAS, solving proportion, mean, and standard deviation calculations, confidence intervals, and hypothesis tests.