Hypotheses and Research Questions

1. Hypotheses and Research Questions Predicting functional relationships between variables

2. Definition: • A hypothesis is a tentative prediction about the nature of the relationship between two or more variables. • A hypothesis represents an educated guess about what will happen in an experiment • Hypotheses are always held tentatively • A research question is simply a hypothesis stated in question form.

3. Research Questions Useful if there is little previous research on the topic Allows a researcher to conduct more open-ended inquiries. A wider range of outcomes can be reported May encourage excessive manipulation of findings or “fishing expeditions.” Hypotheses Useful if there is an established line of research Useful if a likely outcome can be anticipated in advance Useful to test a specific theory or model Can inhibit flexibility or blind a researcher to unanticipated results Should I use a hypothesis or a research question?

4. Types of Hypotheses • Null hypothesis Symbol = Ho or H0 • Experimental hypothesis Symbol = H1, Ha, etc. nondirectional (two-way) directional (one-way) • Research Question Symbol = RQ or R

5. Null Hypothesis • the null hypothesis is a statistical hypothesis, used to determine whether the results of an experiment are statistically significant. • It posits that there is “no relationship” between two variables, or “no difference” between two groups. • The null hypothesis is “supported,” if the results are statistically non-significant • the null hypothesis is never “proven” (at least not by a single study) • impossibility of proving a negative • The null hypothesis is “rejected,” in favor of the experimental hypothesis, if the results are statistically significant

6. Experimental hypothesis • A prediction that there will be statistically significant findings • significant differences or correlations between groups or among variables • Nondirectional hypothesis • significant difference in any direction • Directional hypothesis • Predicts that a specific group or condition will be higher or have more of something, or • predicts the specific direction that a correlation will take (positive negative, curvilinear)

7. Examples • Null hypothesis: • Ho: High exposure to violent video games does not produce more antisocial behavior in elementary school children than low exposure. • Non directional hypothesis: • H1: Japanese and American supervisors will differ significantly in their use of threats as a compliance gaining strategy. • Directional hypothesis • Ha: Deaf children whose parents are deaf will acquire language faster than deaf children whose parents are not deaf.

8. Phrasing hypotheses and research questions • Avoid vague or nebulous wording • the hypothesis or research question must be clear and concise • The hypothesis or research question must betestable. • The hypothesis or research question must be falsifiable. • Wrong: Do students with high GPAs feel better about themselves than students with low GPAs? • Right: Do undergraduates with GPAs greater than 3.0 have higher self esteem than undergraduates with GPAs of lower than 2.0?

9. Identify each of the following: • There are significantly more Republicans than Democrats among registered voters earning $100,000 or more per year. • There is no correlation between college GPA and employees’ salaries 5 years post graduation. • Does frequency of church attendance predict marital fidelity? • Repeated head trauma caused by participation in children’s sports has a significant effect on children’s critical thinking skills. • Experienced elementary teachers will display less negative attitudes toward stutterers than inexperienced teachers.