Unit 2 Research Methods: Thinking Critically With Psychological Science

Module 6 Correlation and Experimentation Learning Targets 6-1 Explain what it means when we say two things are correlated, and describe positive and negative correlations. 6-2 Explain illusory correlations and regression toward the mean. 6-3 Discuss why correlations enable prediction but not cause-effect explanations. 6-4 Describe the characteristics of experimentation that make it possible to isolate cause and effect.

What does it mean when we say two things are correlated? a measure of the extent to which two factors vary together, and how well either factor predicts the other. So for instance… If we look at the instances of lung cancer and the prevalence of smoking behavior, we might say there is a correlation between smoking and lung cancer. If we look at study skills and GPA, we might say there is a correlation between studying and strong grades.

What is the difference between a positive correlation and a negative correlation? Two sets of data tend to rise or fall together Such as… college graduation and income levels. Those who complete college (rise) tend to earn more money (rise). One set of data rises while the other falls Such as… age and amount of nightly sleep. As we get older (rise) the amount of sleep we get decreases (fall).

Which of the following is an example of negative correlation? 1. What Would You Answer? 1. What Would You Answer? Which of the following is an example of negative correlation? People who spend more time exercising tend to weigh less. Teenage females tend to have fewer speeding tickets than teenage males. Students with lower IQ scores tend to have lower grades. As hours studying for a test decrease, so do grades on that test. Students’ shoe sizes are not related to their grades.

How do we measure correlations? The correlation coefficient: a statistical index of the relationship between two variables. Variables that are positively correlated are measured From r = .01 to +1.0 Variables that are negatively correlated are measured from r = -.01 to -1.0. Note that correlation coefficients are expressed as r values.

TRY IT What would you estimate the correlation coefficient to be in these cases? Closer to r = +1.0 or -1.0? The relationship between drinking and driving and auto fatalities? The connection between stress and disease? The relationship between the heat outside and the use of air conditioners?

What is a scatterplot? A graphed cluster of dots, each of which represents the values of two variables. The slope of the points suggests the positive or negative direction of the relationship between the two variables. The amount of scatter suggests the strength of the correlation. Values on the x and y axis must be quantified.

What does a positive correlation scatterplot look like? The variables increase together or decrease together. If one gets larger… so does the other. The slope of the line goes UP from left to right.

What does a negative correlation scatterplot look like? As one variable increases the other decreases. If one variable gets smaller, the other gets larger. The slope of the line goes DOWN from left to right.

What does a “no relationship” scatterplot look like? As one variable increases or decreases, the other increases or decreases randomly. There is no relationship between one and the other.

What is important to remember about correlation coefficients? A correlation coefficient, which can range from -1.0 to +1.0 reveals the extent to which two things relate. The closer the score gets to +1 or -1, the stronger the correlation. The (+) or (-) sign before the number indicates whether the correlation is positive or negative. The (+) or (-) sign indicates direction… not value.

TRY IT Which of the correlation coefficients below expresses the strongest relationship between two variables? +.76 -.91 1.2 0.01

What are illusory correlations? Perceiving a relationship where none exists. Or perceiving a stronger-than-actual relationship. So for instance… A sports fan wears a blue jersey the day her team wins and she decides to wear that blue jersey on game days from now on although the jersey had no impact on the score.

What is regression to the mean? The tendency for extreme scores or events to fall back toward the average. So for instance… An athlete has an amazing game and performs extremely well. In subsequent games, the athlete returns to his normal performance. A student scores much lower than normal on an exam. On future exams, the student’s scores return to their average.

How do correlations help us to predict events?

Correlation does not imply causation.

Correlation does not prove causation. Length of marriage positively correlates with hair loss in men. Does this mean that marriage causes men to lose their hair (or that balding men make better husbands)?

Correlation does not imply causation. AP ® Exam Tip Take note of how much emphasis is put on this idea. Correlation and association do not prove a cause-effect relationship. Correlation does not imply causation.

How can experiments establish cause and effect? Experiments enable researchers to isolate the effects of one or more factors by: (1) manipulating the factors of interest (2) holding constant (“controlling”) other factors.

What is an example of an experiment that shows cause and effect? Does breast feeding lead to smarter children? cause effect

How were the groups assigned? experimental group control group Subjects receive the treatment. The pediatricians promoted breast feeding to the mothers in their group. Subjects do not receive the treatment. The pediatricians provided normal care, but did not promote breastfeeding.

How was the experiment conducted? experimental group control group At 3 months of age, 43% of the babies were being breastfed At 3 months of age, 6% of the babies were being breastfed. (Kramer et al, 2008)

What were the results? At age 6, when nearly 14,000 of the children were restudied, those who had been in the breast-feeding promotion experimental group had intelligence test scores averaging six points higher than their control condition counterparts.

What is random assignment? Assigning participants to experimental and control groups by chance, thus minimizing preexisting differences between the different groups.

Why does random assignment help establish cause and effect? In order to control confounding variables, experimenters randomly assign subjects to the experimental and control group. What if all the babies in the experimental group, shared one specific trait that influenced intelligence?

What is the difference between random sampling and random assignment? Choosing a representative sample of the population being studied. Allows the results to be generalized to the population as a whole. Assigning the participants to the experimental or control group by chance. Minimizes pre-existing differences between the two groups.

How does using a blind procedure help establish cause and effect? single blind double blind The participants in the study are uninformed about the treatment, if any, they are receiving. The participants and the researcher are uninformed about which group receives the treatment and which does not. Controls for subject response bias and placebo effect. Controls for experimenter and subject bias as well as placebo effect.

2. What Would You Answer? 2. What Would You Answer? In a drug study, neither the participants nor the person distributing the pills knows who is receiving the new drug and who is receiving the placebo. This type of research design is said to be a(n) ______ study. correlational confounding double-blind single-blind illusory

What is the placebo effect? A placebo is an inert treatment…like a pill without any medication inside. The placebo effect causes experimental results simply from expectations or assumptions that medication is being taken.

Let’s look at the research on the placebo effect… Athletes have run faster when given a supposed performance-enhancing drug. (McClung & Collins, 2007) Decaf-coffee drinkers have reported increased vigor and alertness—when they thought their brew had caffeine in it. (Dawkins et al., 2011) People have felt better after receiving a phony mood-enhancing drug. (Michael et al., 2012)

What is the difference between an independent and dependent variable ? independent variable (IV) dependent variable (DV) In an experiment, the factor that is manipulated; the variable whose effect is being studied. In an experiment, the outcome that is measured; the variable that may change when the independent variable is manipulated. IV given only to experimental group. DV measured in both groups.

AP ® Exam Tip 2 AP ® Exam Tip The identification of independent (IV) and dependent variables (DV) is the single most likely concept to be tested on the AP® exam. Experiments are critical to psychology, and independent and dependent variables are critical to experiments. Remember to use operational definitions to quantify variables on the FRQ section of the exam.

TRY IT Consider these hypotheses from Module 5. Identify the IV and the DV in each instance. Music helps plants grow. Ginger tea helps reduce hyperactivity in teens Eating junk food causes weight gain.

3. What Would You Answer? 3. What Would You Answer? In an experiment to test the effects of room temperature on test performance, the independent variable is the scores on the test before the experiment begins. the scores on the test at the end of the experiment. whether the teacher was male or female. the temperature of the room. the style of the test (multiple choice v. essay).

What is a confounding variable? A factor other than the factor being studied that might influence a study’s results. The key is that some unique factor must be present in one of the groups (experimental or control), but not in the other. A variable cannot be confounding if it occurs to the same degree in both groups. Random assignment is one method used to prevent confounding variables.

What are some examples of confounding variables? age intelligence level ethnicity sex political beliefs

What is experimental validity? The extent to which a test or experiment measures or predicts what it is supposed to. For instance… if you take a driving test and pass it, we should expect to see accurate driving skills from you. The driving test would be considered a valid measure of your ability to drive.

4. What Would You Answer? 4. What Would You Answer? Researchers surveyed 800 high school students enrolled in AP® Psychology to determine whether students with higher scores on anxiety scales had lower scores on standardized tests. Students with higher scores on anxiety scales were indeed found to have lower scores on standardized tests. Explain how each of the following terms or phrases applies to the situation described above: random sampling generalization correlation does not mean causation

Learning Target 6-1 Review Explain what it means when we say two things are correlated, and describe positive and negative correlations. Correlation is the degree to which two variables are related, and how well one predicts the other. In a positive correlation, two factors increase or decrease together. In a negative correlation, one variable increases as the other decreases.

Learning Target 6-1 Review cont. Explain what it means when we say two things are correlated, and describe positive and negative correlations. A correlation coefficient is a statistical measure that describes the strength and direction of a relationship between two variables, from +1.0 through zero to -1.0 The relationship may be displayed in a scatterplot, in which each dot represents a value for the two variables.

Learning Target 6-2 Review Explain illusory correlations and regression toward the mean Illusory correlations are random events that we notice and falsely assume are related. Regression toward the mean is the tendency for extreme or unusual scores to fall back toward their average.

Learning Target 6-3 Review Discuss why correlations enable prediction but not cause-effect explanation Correlations allow prediction because they show that two variables are related. Correlation can indicate the possibility of a cause-effect relationship, but it does not prove the direction of the influence, or whether an underlying third factor may explain the correlation.

Learning Target 6-4 Review Describe the characteristics of experimentation that make it possible to isolate cause and effect. To discover cause-effect relationships, psychologists conduct experiments, manipulating one or more variables of interest and controlling other variables. Using random assignment, they can minimize confounding variables, such as preexisting differences between the experimental group and the control group.

Learning Target 6-4 Review cont. Describe the characteristics of experimentation that make it possible to isolate cause and effect. The independent variable is the factor manipulated to study its effect; the dependent variable is measured to discover any changes occurring in response to the manipulation of the independent variable. a double-blind procedure is used to avoid the placebo effect and researcher or subject bias. An experiment has validity if it measures what it is supposed to measure.