2.3 Analyzing Findings

Correlational Research

• Correlation

  • means that there is a relationship between two or more variables.
  • however, it does not imply cause and effect
  • it can be measured by calculating a statistic known as the correlation coefficient.

• Correlation Coefficient

  • a number between -1 to +1 that indicates the strength and direction of the relationship between variables.
  • number indicates the strength of the relationship; how strongly related the variables are.
  • the sign indicates the direction of the relationship.
    • positive correlation means that variables move the same direction
      (when one variable increases so does the other)
    • negative correlation means the variables move in the opposite directions
      (when one variable increases, the other decreases)

Correlation does not Indicate Causation

• While correlational research is useful, it tells us little about cause and effect.
• When variables are sometimes correlated because one does cause to the other, a confounding variable may be a cause to the systematic movement in our variables.
• We should not assume that correlation implies one variable causes changes to another, even when we cannot fully clear or point out confounding variables in our relationship.

Illusory Correlations

• occurs when people believe a relationship exists between two things when no such relationship exists.

• one good example is the moon’s phases affect human behavior

• Why do we Believe on Illusory Correlations?

  • We often hear or read about them and simply accept it as true
  • We might have an instinct on how something works, then looks for evidence that supports that instinct while ignoring evidence that tells our instinct is false (confirmation bias)
  • We might find illusory correlations based on information that comes easily to mind, which is often limited.

• Illusory Correlations that inaccurately attribute behaviors to certain groups are shown to lead in the formation of prejudicial attitudes and eventually, discriminatory behavior.

  • This states that illusory correlations may have significant drawbacks in our understanding of the world around us.

Conducting Experiments and Using the Data

• Conducting a scientific experiment is an only way to establish a cause-and-effect relationship.
• However, experiments in the scientific context has a precise set of requirements for design and implementation.

The Experimental Hypothesis

• In conducting an experiment, the researcher must begin with a specific hypothesis to be tested.
• Personal observations are what leads us to formulate hypotheses, however, designing an experiment is essential to find out if real-world data supports our hypothesis.

Designing an Experiment

• The most basic experimental design involves two groups: the experimental group and the control group.
  • The two groups are designed to be the same.
  • The experimental group receives the experimental manipulation
  • The control group does not.
  • Since the only difference between the two groups are the experimental manipulation, we can be sure that the changes are due to the manipulation rather than by pure chance.
• In designing an experiment, we must provide an accurate description of what we want to measure.
  • Operational definitions precisely describe and define our variables
  • It allows others to identify how and what a researcher measures in a particular experiment
  • For example, if we want to measure learning or proficiency, we can instead measure them as a performance on a test.
• We should also establish how we should run our experiment
• As much as possible, we should also design our experiments in a way that should eliminate experimenter bias
  • Experimenter bias is a possibility that a researcher’s expectations might skew the results of the study.
  • To avoid this, there are two possible methods of conducting the experiment.
    • A single-blind study, where one of the groups (participants) are unaware of which group are they in (if they are in the experiment or control), while the researchers know which participants are in which group.
    • A double-blind study, where both the researchers and the participants are blind to group assignments.
      • By doing this, we can control for expectations of both experimenter and the participants
      • This way we can prevent placebo effects influencing the results of the study.
      • The placebo effect occurs when people’s expectations/beliefs influence their experiences
        (expecting something to happen can make it happen)

Independent and Dependent Variables

• Variables, or things that can be changed, are essential in a research study as oftentimes, as we observe that changes in one thing influences another.
  • Independent Variables: things that can be freely manipulated or controlled by the experimenter
    • In a well-designed experiment study, the independent variable is the only difference between the experiment and control groups.
  • Dependent Variables: things that a researcher measures to see how much effect the independent variable had.

Selecting and Assigning Experimental Participants

• Participants

  • the subjects of psychological research
  • individuals who actively participate in the psychological research.

• We use samples of a population to serve as participants of our study as it is usually too large or too impractical to include in our experiment.

• A random sample is a subset of a population where each member has an equal chance is being selected.

  • Often preferred as percentages of the characteristics in the sample are closer to the percentages of the larger population.

• Next, we split the participants into the experimental and control groups

  • This can be done via random assignment.
  • Random assignment is when all participants have an equal chance