ABSTRACT

The purpose of the study was to develop an instrument that will be used to assess students’ attitude to geography using the Rasch Model. The objectives of the study were specifically to determine the fit statistics, item difficulty, person parameter estimate, standard errors of measurement SEM for each item and person, item and person separation index, Differential Item Functioning DIF and mean attitude score with respect to school type and gender. The design of the study was instrumentation research design and the area of the study was South-East Nigeria. Ten Research Questions  and three Hypotheses  guided the study. The sample was made up of 850 students from 78 secondary schools in three states of South East. Simple randon sample and proportionate stratified random sample were employed in sampling of the states, schools and subjects. An 80- item draft instrument, called Geography Altitude Scale (GAS) was developed by the researcher and trial tested. The responses were subjected to factor analysis after which 38 items were dropped, and 42 items emerged. WINSTERS 3:81software (Linacre, 2010) was used to analyze the data in order to answer the Research Questions 1-8 and test Hypothesis one according to the Rasch model (IRT) procedures. The mean attitude score was used in answering Research Questions 9 and 10. Independent sample t- test analysis was applied to test Hypotheses 2 and 3 at 0.05 level of significance. The Rasch modeled expectation fits were met by forty (40) out of forty-two (42) items. The item threshold and person parameter estimates had accompanying SEM that were far below 0.5. Item and person separation index showed good alignment of item hierarchy, and persons have been separated into higher and lower levels of attitude. DIF effect was discovered in approximately eight (8) items which were also discarded. The independent t-test revealed that females had more positive attitude towards geography than their male counterparts and single-sex school students showed more positive attitude to geography than mixed-sex school students. With the total of 10 items discarded, made up of 2 misfitting ones during fit analysis and 8 for DIF effects, items of the GAS remained 32 in number. In conclusion, the study provides support for the validity and reliability of the instrument in assessing students’ attitude to Geography. Therefore, it was recommended among others that instrument GAS should be used to assess attitude of students to geography at secondary school levels in Nigeria.