Jamis J. Perrett

Exploring graduate and undergraduate course evaluations administered on paper and online: a case study

The purpose of this study was to analyse the students’ evaluations of the course and instructor for all statistics courses offered during fall semester 2009 at a large university in the southern United States. Data were collected and analysed for course evaluations administered both online and on paper to students in both undergraduate and graduate courses. Unlike most previous studies on this subject, class section rather than student was treated as the unit of analysis. It was of specific interest to verify prior research findings that evaluation surveys administered online would not result in lower course and instructor ratings and lower response rates. The results showed that there is not sufficient evidence within the collected data to conclude that either course and instructor ratings or response rates are lower for evaluations administered online (online evaluations) than they are for evaluations administered on paper (paper evaluations). Of secondary interest was whether class ratings would be associated with students’ attendance and a comparison of variability among answers for undergraduate vs. graduate students. It was observed that class and teacher ratings were not related to students’ attendance and individual students did not tend to give the same answer for every question on their survey.

Statistical Computation Methods

Within the context of linear models, there are different algorithms that have been developed to make computations more accurate and/or efficient (fewer basic operations). One problem deals with the size of a matrix.

Mathematical and Statistical Basics

There are many statistical equations that require finding the transpose of a matrix, the trace, rank, etc. Some of these operations are basic functions with sensible names that are easily discovered and used in IML. Some operations are less obvious.

The General Linear Model

The subject of linear models, and all of its intricacies is too vast to be properly dealt with in a book of this nature. Instead, a few examples of general applications of linear models in IML will be demonstrated. These examples can then be modified according to the needs of the researcher.

IML Language Structure

READ, UPDATE, RESET, PRINT? Many commands, functions, calls, and operators are pretty easy to figure out without explanation — It might be expected that the READ statement read values into a matrix, the NCOL function identify the number of columns in a given matrix, and the + operator add elements in a matrix. However, some of the commands, functions, calls, and operators used in IML are less obvious. This section will help the reader understand the basic use of commands, functions, calls, and operators with some examples.

Linear Mixed Models

In the early 1950s, C.R. Henderson developed mixed model estimation, something he began in the 1940s with his Ph.D. thesis. He wanted to analyze data for a linear model with fixed environmental and random genetic factors in the breeding of swine (Van Vleck, 1998).

SAS/IML: A Brief Introduction

IML stands for Interactive Matrix Language and is a matrix language written as a component of the SAS System. IML allows the user to enter numbers and other characters in matrix form and perform data manipulation, functions and algorithms commonly associated with matrices.

Matrix Manipulations in SAS/IML

IML allows different levels of matrix access: element access, row access, column access, submatrix access.

IML Programming Features

A SAS/IML module is a subprogram or subroutine. A module is set apart from the rest of the IML code and is not executed until called. Modules can be called various times within a single IML procedure.