Marczyk, DeMatteo, Festinger CH 2

Choosing a Research Topic

  1. Interest
  • usually choose topics of interest to the researcher
  • interest may develop from
    • personal interest in a phenomenon
    • the influence of knowledge after having worked in the field
    • observations made from the world
  1. Problem Solving
  • there exists a need to generate an alternate more effective or efficient solution to a problem
  1. Previous Research
  • "Research begets research"
    • based on the findings of a previous study
      • one many seek to replicate the study
      • extend the generalizability of the study by testing different populations or, in different settings
    • Generally research raises more questions than it answers
  1. Theory
  • can serve as a rich source for hypothesis formulation
    • Theories make predictions
      • Which then can be transformed into a testable hypothesis

Literature Review

  1. Review the Existing Literature on a Topic
  • Purpose is to familiarize oneself with the works that have already been conducted in the topic area
  • It helps to guide the research in the appropriate direction by answering several questions related to the topic area…And generating other questions that may not have been previously considered
  1. Questions that should be Addresses in the Lit Review
  • Has work been conducted in this topic area?
  • What do the results of these studies suggest?
  • Was any unforeseen methodological difficulties encountered that I should be aware of for my study?
  • Does more research on this topic need to be conducted? And if so, in what specific areas?

Formulating a Research Problem

  1. It takes the form of a concise question regarding the relationship between two or more variables
  • Its important to make sure the question is specific enough to avoid confusion and to indicate clearly what is being studied
    • Vagueness is to be AVOIDED
  1. Criteria
  • Should describe the relationship between two or more variables
  • Should take the form f a question
  • Must be capable of being tested empirically
  1. Operational Definitions
  • Main function is to avoid confusion within the research design
  • it defines key concepts and terms so that readers understand clearly what and who is being measured in a research study
    • This is crucial for replication and understanding the limits of generalizability

Articulating Hypotheses

  1. Hypotheses attempt to explain, predict, and explore the phenomenon of interest
  • It is the researcher's educated guess about how the study will turn out
  • All hypotheses must be falsifiable
    • Meaning they are capable of being refuted based on the study's results
  • All hypotheses must make a prediction about the relationship between the two or more variables
  1. Null Hypothesis
  • Always predicts that there will be no difference between the groups/variables being studied
    • It is the null hypothesis which is tested
    • It is either rejected or not rejected based on the results of statistical analysis
    • Rejecting the null hypothesis only allows the researcher to not reject the alternate hypothesis…Never Accept
  1. Alternate Hypothesis
  • Always predicts that there will be a difference between the groups/variables being studied
  1. Hypotheses CAN NOT be "Accepted"
  • Reject
  • Fail to reject
  1. Directional vs. Nondirectional Hypothesis
  • The use of directional hypotheses depends on the researcher's knowledge about how the groups will differ
    • There is a belief that the groups will differ
    • AND, there is a belief about how the groups will differ
  • Nondirectional
    • There is a belief that the groups will differ
    • BUT, there is no belief regarding how the groups will differ

Choosing Variables to Study

Variable: anything that can take on different values
: Constant
something that can not vary
  1. Independent Variable
  • The factor manipulated or controlled by the researcher
    • This is what the experimental group will be exposed to
  • Levels of the Independent Variable
    • Simplest Form: it is either Present or Absent
      • one group is exposed to the experimental condition while the other is not
    • Multiple Levels
      • Groups in the experiment receive varying degrees of the independent variable
    • Multiple Independent Variable
      • a study can have multiple independent variable…this would demand for larger sample sizes based on the number of variables
  1. Dependent Variable
  • Is the measurable effect of the Independent variable
  • Baseline Measure
    • is necessary to show if any effect occurred as a result of experiencing the independent variable
    • this measure is taken prior to, and after exposure of the independent variable
  1. Categorical Variables
  • variable that can take on specific values only within a defined range of values
    • EX: gender, race, eye color
  1. Continuous Variables
  • Variables that can theoretically take on any value along a continuum
    • Benefit is that it allows precision of measuring
    • EX: income, weight, age
  • Continuous variables may be changed into categorical variables
    • EX: Age Categories (Young Adulthood, Elderly) or Income Brackets
  1. Quantitative Variables
  • Vary in amount
    • The frequency with which something happens
  1. Qualitative Variables
  • vary in kind

Research Participants


Pre-existing or target groups- some research studies require specific groups; difficulties may arise such as generalizability
Sample- representative subset of population
Random selection- participants are chosen in such a way that each member of the population has an equal probability to be selected to participate
- often difficult to accomplish, unless population is narrowly defined; narrowly defining population has negative effect of limiting the representativeness of the resulting sample
- the results of a study cannot be generalized based solely on random selection; evidence for generelizability comes from replication studies

Assigning Study Participants to Groups

Random Assignment- assigning in such way that each participant has equal probability of being assigned to any of the groups within the study; effective way to ensure that groups are equivalent
Nuisance Variables- variables that are not under researcher control
Without equivalent groups several variables may come into play; compromising results
Random Assignment is most effective in large sample sizes

Multiculturalism Considerations

- considerable effect on a researcher’s choice of a research question and design (even if researcher is unaware)
- important in selection and composition of the sample participants used in particular research studies

Unless otherwise stated, the content of this page is licensed under Creative Commons Attribution-ShareAlike 3.0 License