Marczyk, DeMatteo, Festinger CH1


Correlational vs. Experimental Research

Correlational research: used to determine if two or more variables are related. Can be used to make predictions especially if the correlation is strong enough. Key point to remember is even if a relationship exists between two variables, it doesn't mean that one variable causes the other. In other words "Correlation does not equal causation."

Experimental research: used to test hypotheses and draw cause and effect conclusions. This approach is used to compare two groups on one measure. The groups used are the experimental group (which receives some treatment or measure), and the control group (which receives no treatment or a placebo).

Null Hypothesis Testing and Type I and II error

Null hypothesis: there is no effect

No effect/ Ho true Effect exists/ Ho false
Reject Ho Type I error correct decision
Accept Ho correct decision Type II error

Type I error- false positive
e.g. Geoff is pregnant (when's the baby shower?)
Type II error- "missed opportunity"
e.g. failing to stop a terrorist from going on a plane

Categories of Research

1.Quantitative vs. Qualitative
Quantitative research: studies using statistical analyses to obtain findings; use of formal and systematic measurement and statistics are key features

Qualitative research: studies which do not attempt to quantify their results through statistical summary or analysis; usually utilize interviews/observations without formal measurements; e.g. case study; qualitative research often used as a source of hypotheses for later resting in quantitative research

2. Nomothetic vs. Idiographic
Nomothetic approach: uses the study of groups to identify general laws that apply to a large group of people; goal often to identify average member of the group being studied or average performance of a group member

Idiographic approach: the study of an individual e.g. case study

Which type to choose? This largely depends on the types of questions being posed in the study, as different fields rely on different categories of research to achieve their goals. E.g. social science research typically uses quantitative and nomothetic approaches

Two Types of Correlation

Positive correlation: both variables change in the same direction-both increase or decrease
e.g. if GPA's increase as SAT scores increase, there is a positive correlation b/t SAT scores and GPA's

Negative correlation: as one variable increases, the other variable decreases (the variables change in opposite directions)
e.g. if GPA's decreases as SAT scores increase, this is a negative correlation b/t SAT scores and GPA's

Prerequisites for Inferences of Causality

  • Must be an existing relationship b/t two events
  • The cause must precede the effect
  • Alternative explanations for the relationship must be ruled out

If the null hypothesis always predicts that there will be NO difference between the variables or groups, then the alternate hypothesis predicts that there will always be a difference between the groups.

Chapter one

-purpose of research: answer questions and acquire new knowledge.
-attempt to reduce the complexity of problems, discover the relationship between seemingly unrelated events, and improve the way we live.
-general goals and methods are similar across all disciplines.
-research can help in: description, explanation, and prediction.
-defining characteristics that are the same across all research: testing hypotheses, careful observation and measurement, systematic evaluation of data, and drawing valid conclusions.

-correlational research
Goal: determine whether 2 or more variables are related to one another.
-variable: anything that can take on different values (weight, time, height).
-if a correlation is strong enough, knowing one variable allows a prediction to be made about the other one.

-experimental research:
-comparing two groups on one outcome measure to test some hypothesis regarding causation.
-in order to find a causation relationship, experimental research is used.
-experimental group: the group that receives the thing being measured.
-control group: gets the placebo.
-other than different meds, groups are treated exactly the same to isolate the effects of the thing they are testing.

Scientific method

-science: methodological and systematic approach to the acquisition of new knowledge.
-scientific knowledge is based on: objective data that was reliably obtained in the context of a carefully designed research study. (empirical evidence).
-defining characteristic of scientific research: scientific method- approach to the acquisition of new knowledge. This distinguishes science from nonscience.
-it is a set of research principles and methods that helps obtain valid results from studies.
*because scientific method deals with general approach to research rather than content of specific research studies.
-biggest benefit: provides a set of clear and agreed upon guidelines for gathering, evaluating, and reporting info in the context of a research study.
-scientific method is characterized by the following:
Empirical approach, observations, questions, hypotheses, experiments, analyses, conclusions, replications.

Empirical approach: evidence based approach that relies on direct observation and experimentation in acquisition of new knowledge. Results and conclusions are based on actual evidence not just “hunches.”

Observations: refers to 2 distinct concepts-being aware of the world around us and making careful measurements.
-often give rise to the questions that are addressed in scientific research.
-also refers to the process of making careful and accurate measurements.
-don’t want to make biased observations.
Important aspect of measurement: operational definition.
Define key concepts and terms in the context of their research by using operational definitions.
-by using these, we make sure everyone is talking about the same phenomenon.
-also important for future replication of the experiment by others.

-important to formulate questions that can be answered through available scientific methods and procedures.

-must make a prediction. They are then tested.
- 2 types of hypotheses: null hypothesis and the alternate (or experimental) hypothesis.
-null: always predicts there will be no difference between the groups being studied.
-alternate: predicts there will be a difference between groups.
-must be able to determine that the hypothesis can be wrong.

-key aspect of conducting an experiment is measuring something in an accurate and reliable manner.

Accuracy vs. reliability
Accuracy means the measurement is correct.
Reliability is the measurement is consistent
Can be reliable but not accurate.

-uses statistical techniques. They help minimize the likelihood of mistakes.
-key decision to make with the use of stats is whether to reject the null hypothesis.
-rejecting the null hypothesis: IS a difference between the 2 groups.
-can be rejected or not rejected but can NEVER be accepted.
-no not reject: unable to detect difference between the groups.
It doesn’t mean that there is no difference between the 2 groups, but we are unable to detect the difference in our study.
-most seek to reject b/c it means the thing being studied had some effect.
-2 mistakes can be made when attempting to decide whether to reject the null or not:
Type I: when its concluded that there is a difference between groups when in fact there is not. (aka false positive).
Type II: when it is concluded that there is not a difference and in fact there is. (aka false negative).
-although a difference may have occurred by chance (type I) and there is not actually a difference.
-with type II, there is a nonsignificant statistical result when in fact there is a difference between groups.
-most allow a 5% chance of erroneously rejecting the null (making a type I error). In other words, we will reject the null with a less than 5% chance we are wrong.
-there is an inverse relationship between type I and II: by decreasing the probability of making a type I error, you are increasing the probability of making a type II error.
-thus if the 5% is reduced to 1% for making a type I error, then there is an increased chance of making a type II error by failing to detect that an actual difference exists.


-conducting an experiment again with another group of participants to see whether the same results were obtained.
-this reinforces that the first study was accurate and the results were not obtained by chance.
-establishes reliability, consistency and proves results are “generalizable” to other people in the population.

Goals of scientific research
3 main ones: description, prediction, and understanding/explanation.

-important b/c it can provide info regarding the average member of the group.
-an example of descriptive research is correlational research.

Quantitative vs. qualitative
Quan: studies that make use of their statistical analyses to obtain their findings.
Key features: formal and systemic measurement and the use of statistics.
Qualitative: normally interviews and observations without formal measurement. E.g. a case study.
Often used as a source of hypotheses for later testing in quantitative research.

Nomothetic vs. idiographic
Nomothetic: study of groups to identify general laws that apply to a large group of people.
-goal is often to identify the average member of the group or the average performance of a group member.
Idiographic: study of an individual. E.g. aforementioned case study.

-the choice of which research approach to use depends on the types of questions being asked .
-different fields of research rely on different categories of research to achieve their goals.
e.g. social science research relies on quantitative research and the nomothetic approach. In other words, they study large groups of people and rely on statistical analyses to obtain their findings.

-prediction based research often stems from previously conducted descriptive research.
-a prediction is being made based on existing knowledge of something else.

-of research does not provide a true understanding of phenomenon. Many believe this is possible only when the causes of something can be identified.

3 prerequisites for drawing an inference of causality between two events:
1. there must be a relationship (correlation) between the 2 events. E.g the events must “covary”- as one changes, the other must change.
2. one event (the cause) must precede the other event (the effect). Sometimes referred to as a “time-order relationship.”
3. alternative explanations for the observed relationship have been ruled out

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