The American Sociological Association (ASA) has identified scientific literacy (i.e., statistical literacy) as a key curricular goal that needs to pervade the sociology major (Howery and Rodriguez 2006). Research Methods is the core course that addresses statistical literacy, but unfortunately many students possess significant quantitative skill gaps, often accompanied by significant anxieties associated with statistical concepts (Wade 2003). This study has been undertaken to better understand gaps in statistics knowledge among undergraduate students. Participants were 111 students clustered in four courses- statistics, research methods without a prior statistics course, research methods with a prior statistics course and a control group. Three out of the four knowledge elements revealed significant differences between groups-higher scores were shown for the research methods class with prior statistics, for statistical thinking, reasoning and literacy. For critical questions, a significant difference was found between the research methods class with prior statistics and the statistics class. No significant difference was found between the research methods class with prior statistics, and the research methods class without prior statistics, even though pre- and post-test scores were higher for the research methods class with prior statistics. These results suggest that undergraduate students need to take both, statistics and research methods classes. Implications of these findings for the sociology curriculum are discussed.
The American Sociological Association (ASA) has identified scientific or statistical literacy as a key curricula goal that needs to pervade the sociology major (Howery and Rodriguez 2006). The concept of statistical literacy is broad. The National Council of Education and the Disciplines define seven elements, which characterize quantitative literacy. These are: 1) arithmetic-the use of simple calculations for numbers; 2) data-using data to draw inferences, understanding graphs and charts; 3) computers-to record data, create graphic displays, complete calculations; 4) modeling- the ability to understand linear, exponential, multivariate and simulation models; 5) statistics-to understand the importance of variability in a data set, recognizing the differences between correlation and causation, the difference between experiments and non-experiments, statistical significance and practical significance; 6) chance-to evaluate risks, understand the value of random samples and to understand that improbable coincidences are not uncommon; 7) reasoning-to exercise caution in making generalizations, checking hypotheses and using logical thinking (Steen 2001). Further strengthening this definition, the Royal Statistical Society believes statistical literacy involves the ability to critically evaluate the use of statistical data by others, in media and elsewhere. This refers to the use of official statistics, both in providing .snapshots' of current situations and in showing important changes over time. (Goodall 2005:96). The term quantitative literacy also purports to allow people a quantitative perspective for understanding the world. (Manaster 2001:68). Examples include charts of income distributions, effects of medical treatments, and differences between social programs, or policies, through descriptive statistics. Numbers, in this sense, help compare features of real-world situations and help us make decisions based on the numbers. It is a competency much like reading, because it involves comprehension and interpretation in order to make decisions using statistics as evidence.
Others define statistical literacy similarly, and emphasize its importance in a civil society. It is the ability to understand and critically evaluate statistical results that permeate our daily lives-coupled with the ability to appreciate the contributions that statistical thinking can make in public and private, professional and personal decisions. …