KNR 497 KNR 497: Practice Questions – Controlling for Threats to Validity Below are a set of research scenarios. Go through each scenario to discuss the potential threats to validity, and discuss how the study might be better designed to help control for these threats. 1. A researcher wants to examine hyperactivity among children. The researcher randomly establishes a control group and an experimental group and tests each participant for hyperactivity in the morning and in the afternoon. This continues daily for three months. History – Selection – Statistical regression – Pre-testing Instrumentation Attrition Experimenter Subject effect 2. An undergrad class taught by the researcher is split into 3 groups of 30. One third is assigned to a plyometric strength-training program, 1/3 to an isometric program, and 1/3 do nothing. Before assigning them, the researcher makes sure to tell the entire class about the purpose of the research, and explains we are doing it to see if the researcher’s suspicions about plyometrics are correct. History – Selection – Statistical regression – Pre-testing Instrumentation Attrition Experimenter Subject effect - KNR 497 3. A teacher wants to examine his students’ level of improvement during a three-week basketball unit. He places them in two groups (high-skilled and low skilled) based upon their performance during the first day of the unit. He then measures their performance against a pre-existing rubric each day of the unit. History – Selection – Statistical regression – Pre-testing Instrumentation Attrition Experimenter Subject effect 4. A researcher wants to examine the fitness levels of college students. She chooses to use the students enrolled in a fitness class she teaches as her participants. Students are required to participate in a set of fitness tests on the first day of the semester, in the middle of the semester, and on the last day of the semester. History – Selection – Statistical regression – Pre-testing Instrumentation Attrition Experimenter Subject effect 5. A researcher wants to study the educational achievements of children as they progress from kindergarten through twelfth grade. Students are placed into groups based upon the socioeconomic status of their parents or guardians. Scores from standardized tests are obtained and analyzed for each student during this time period. History – Selection – Statistical regression – Pre-testing Instrumentation Attrition Experimenter Subject effect - KNR 497 Answers KNR 497: Practice Questions – Controlling for Threats to Validity Below are a set of research scenarios. Go through each scenario to discuss the potential threats to validity, and discuss how the study might be better designed to help control for these threats. 1. A researcher wants to examine hyperactivity among children. The researcher randomly establishes a control group and an experimental group and tests each participant for hyperactivity in the morning and in the afternoon. This continues daily for three months. History – Testing every day for 3 months; reduce # of times subjects are tested Selection – Good that it is randomly selected Statistical regression – Could occur. Taking enough measure to get it back to the mean Pre-testing – no pre-test done Instrumentation – need to be consistent in use of instrument. If observations are made, need consistency Attrition – possible over 3 months Experimenter – A relationship will build. If testing can be biased, control for this. Subject effect – Can happen, but 3 months will likely reduce this factor. 2. An introductory wellness undergrad class taught by the researcher is split into 3 groups of 30. One third is assigned to a plyometric strength-training program, 1/3 to an isometric program, and 1/3 do nothing. Before assigning them, the researcher makes sure to tell the entire class about the purpose of the research, and explains we are doing it to see if the researcher’s suspicions about plyometrics are correct. Measures of their changes will be taken once a week for 6 weeks. History – Illness, injury could influence results; pull them from the study if this happens Selection – Need to randomly select people to the group. This class may attract people who are physically active & unwilling to do nothing for 6 weeks if they are selected to that group. Statistical regression – Will even out high/low testers Pre-testing - NA Instrumentation – Must ensure calibration of tests are accurate; researchers stay consistent Attrition – 6 weeks may lose people; some may not complete the required exercises. Experimenter – Researcher is their instructor. Subject effect – Wellness class and the up-front purpose & suspicions of the researcher were made known. People may seek to fulfill suspicions. KNR 497 3. A teacher wants to examine his students’ level of improvement during a three-week basketball unit. He places them in two groups (high-skilled and low skilled) based upon their performance during the first day of the unit. He then measures their performance against a pre-existing rubric each day of the unit. History – 3 week time span; Selection – random sampling would increase validity but is prohibitive; Statistical regression – Don’t place in groups after the first test Pre-testing – maybe, depends on the test Instrumentation – keep instrument consistent Attrition - 3 weeks tolose people Experimenter – teacher is measuring Subject effect – May increase effect 4. A researcher wants to examine the fitness levels of college students. She chooses to use the students enrolled in a fitness class she teaches as her participants. Students are required to participate in a set of fitness tests on the first day of the semester, in the middle of the semester, and on the last day of the semester. History – Data collected over a semester; Selection – random sampling would increase validity but is prohibitive; Statistical regression – Could occur. Taking enough measure to get it back to the mean Pre-testing - won’t improve from practicing test Instrumentation – Keep instrument consistent Attrition – Potential, 16 weeks of a class Experimenter – Teacher is measuring, get someone else to help measure Subject effect - Potential 5. A researcher wants to study the educational achievements of children as they progress from kindergarten through twelfth grade. Students are placed into groups based upon the socioeconomic status of their parents or guardians. Scores from standardized tests are obtained and analyzed for each student during this time period. History – High Selection – random sampling would increase validity but is prohibitive; Statistical regression – Could occur. Taking enough measure to get it back to the mean Pre-testing - NA Instrumentation – Standardized test will increase the validity Attrition – High – 12 years; Experimenter - NA Subject effect - NA