It is natural to expect the different behavior strategies of test takers who do not know the correct answer to the multiple choice test items. Some omit it; others try to guess the answer randomly or logically. Świst K. et al. (2015) consider guessing and item omission as risk-taking and risk-avoiding strategies. If assessment procedure involves penalties for incorrect answer, then the student might be less likely to take the risk of providing an uncertain answer. However, if the student can make an educated guess, the risk of providing an incorrect answer is reduced and might be considered as worth taking. Omitting test items may be considered as an indicator of the tendency to avoid this risk. Are these strategies used in the same manner by the representatives of different sexes in different countries?

Numerous empirical studies show that men are more at risk than women in many situations (Byrnes et al., 1999).  But sometimes these differences would vary by situation context. For instance, Wilson and Daly (1985) suggested that men would only be more likely than women to take risks when the context involves both competition and a large spread in rewards between winners and losers. Furthermore, risk behaviors are a function of both personal attitude and cultural driven expectancies (Arnett, 1992): in some cultures, women’s risk-seeking tendency can be dampened by cultural restrictions causing underestimation of the effect of sex differences in risk-seeking tendencies. As for testing, sex differences in guessing and item omission tendency have been examined in empirical studies over several decades. Świst K. et al. (2015) note that the majority of research showed that guessing is a phenomenon attributed to boys, while item omission is a phenomenon attributed to girls although there are studies that do not support these results. The omission tendency is associated rather with ability level – the higher the ability, the lower the tendency to omit. Not always a tendency to guessing is associated only with risk. One who has better problem solving skills and think logically and creatively can succeed in guessing the correct answer. If students do not know the correct answer for a particular item, they often use partial knowledge to eliminate the less likely answers, and rarely guess entirely according to chance. These are usually persons with high ability in question. While persons of both sexes with low ability often chooses a strategy of random guessing. Researchers usually deal with the phenomenon of guessing by estimating the c-parameter in a three-parameter logistic model using item response theory. Recently this parameter is not interpreted as pure random guessing indicator. Han (2012) proposed conceptualization of the c-parameter as the product of random guessing, logical guessing and problem solving. He suggests using a more appropriate term “random chance parameter”. Here we will consider c-parameter as a characteristic of the overall guessing process but interpret it depending on the ability of persons in the groups for which this parameter is significantly different.

The main objective of this study is to identify gender differences in random chance parameter and item omission in five countries: Tunisia, Morocco, Ukraine, Lithuania and Hungary. Since 2015, these countries execute the joint Erasmus+ project “Gender Studies Curriculum: A Step for Democracy and Peace in EU-Neighboring Countries with Different Traditions” which purpose is to introduce the gender courses into various master's programs, including educational measurement. This study will help us to better understand the behavior of boys and girls in countries with different histories, cultural and educational traditions.

Acar T and Kelecioglu H (2010) Comparison of Differential Item Functioning Determination Techniques: HGLM, LR and IRT-LR. Educational Sciences: Theory & Practice 10 (2): 639-649. Byrnes JP, Miller DC and Schafer WD (1999) Gender differences in risk taking: a meta-analysis. Psychological Bulletin 125(3): 367–383. Camilli G (2006) Test fairness. In: Brennan R (ed) Educational measurement. Westport, CT: ACE Praeger series on higher education, pp.221–256. Finch WH, French BF (2014) The impact of group pseudo-guessing parameter differences on the detection of uniform and nonuniform DIF. Psychological Test and Assessment Modeling 56 (1): 25-44. Han KT (2012) Fixing the c parameter in the three-parameter logistic model. Practical Assessment, Research & Evaluation 17(1): 1–24. Lopez GE (2012) Detection and Classification of DIF Types Using Parametric and Nonparametric Methods: A comparison of the IRT-Likelihood Ratio Test, Crossing-SIBTEST, and Logistic Regression Procedures. PhD Thesis, University of South Florida, USA. Mullis I, Martin M, Foy P and Arora A (2012) TIMSS 2011 International Results in Mathematics. Available at: http://timssandpirls.bc.edu/timss2011/international-results-mathematics.html Martin M, Mullis I, Foy P and Stanco G (2012) TIMSS 2011 International Results in Science. Available at: http://timssandpirls.bc.edu/timss2011/international-results-science.html Świst K, Skórska P, Koniewski M and Jasińska-Maciążek A (2015) Sex differences in guessing and item omission. Edukacja 3(134): 48-62. Thissen D (2001) IRTLRDIF v.2.0b: Software for the computation of the statistics involved in item response theory likelihood-ratio tests for differential item functioning. Available at: http://www.unc.edu/~dthissen/dl.html Thissen D, Steinberg L and Wainer H (1993) Detection of differential item functioning using the parameters of item response models. In Holland PW and Wainer H (ed) Differential item functioning. Hillsdale, NJ: Erlbaum, pp. 67–113. Wilson M, Daly M (1985) Competitiveness, risk taking and violence: the young male syndrome. Ethology and Sociology 6(1): 59–73.