The goal of this study was to illustrate survival analysis with higher education data and gain insight into a limited set of factors that predict when students passed their first-year examination at a Dutch university. Study participants consisted of 565 first-year students in four departments. Data were collected on when students pass their first-year examination, prior achievement and procrastination. The analysis showed that 69% of the students had not passed their examination within the nominal study length of 12 months. The estimated median lifetime, the time when 50% of the students had passed their examination, was after 23 months. Students from the 2nd department passed their examination fastest. Female students reached the estimated median lifetime at 20 months, younger students at 16 months, older students at 24+ months and students with high prior achievement scores at 12 months. The analysis finally indicated that age, prior achievement and procrastination predicted passing first-year examinations.
IntroductionFor many years, researchers have been interested in examining those variables that predict whether university students graduate or drop out. These studies have generated an enormous knowledge database on factors related to whether students drop out or graduate. However, wouldn't it be even more interesting to also know when students dropout or graduate? This study aims to illustrate the use and advantages of survival analysis within the field of higher education and to predict, based on a limited set of factors, when students pass their first-year examination.The question of why certain students decide to drop out while others decide to persist has been a starting-point for many studies in higher education. A major theoretical focus has been the so-called 'interaction model'. These interaction models, which emphasize the interaction between students and the environment, have often been used to explain variance in dropout, persistence or achievement. Most of these interaction models are based on Spady's model (see Bean, 1980;Spady, 1970;Tinto, 1975). A central aspect in Spady's model is 'social integration', which is, among others, affected by study results and complex patterns of ability, aptitude, interests, goals, values and expectations, support by friends and group values. Tinto (1975) elaborated on this and proposed that both student characteristics and interactions with the
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.