Correlational research
This presentation is the property of its rightful owner.
Sponsored Links
1 / 69

CORRELATIONAL RESEARCH PowerPoint PPT Presentation


  • 66 Views
  • Uploaded on
  • Presentation posted in: General

CORRELATIONAL RESEARCH. Asks what several events have in common Asks whether knowing one event can allow prediction of another event Does not imply causation. -When research shows that two traits are connected together -If one trait is there, the other is too. Correlation.

Download Presentation

CORRELATIONAL RESEARCH

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Correlational research

CORRELATIONAL RESEARCH

  • Asks what several events have in common

  • Asks whether knowing one event can allow prediction of another event

  • Does not imply causation


Correlation

-When research shows that two traits are connected together

-If one trait is there, the other is too

Correlation

Module 4: Research Strategies


Positive correlation

  • When one trait is strong, the other is too

Positive Correlation


Negative correlation

  • If one trait is strong, the other is weak

Negative Correlation


Zero correlation

  • There is no relationship at all between the two traits.

Zero Correlation


Correlational research

  • However, correlation is NOT causation

    • One trait does not cause the other

Hair color does not CAUSE eye color

Blue

Green

Brown

Eye Color

Blonde

Brown

Red

Hair Color


Experiment

Experiment

  • A research method in which the researcher manipulates and controls certain variables to observe the effect on other variables.

  • Hypothesis- a testable prediction about the outcome of research


Activity

  • Design an experiment for each of these ideas.

    • Playing sports makes a person more/less aggressive

    • Women are more/less friendly than men

    • Teenagers have more/less emotional problems than adults

    • People become friends with others who are similar/different from themselves.

Activity:


Correlational research

Experimental Research – highest constraint

“True Experiment”

Control:

Systematic methods

Reduce threats to validity

Limit Extraneous variables (confounds)

 RANDOM ASSIGNMENT

  • Measurement procedures carefully designed

    and precisely followed


Variables

Variables


Correlational research

Variable - A behavior or cause of behavior that is studied through experiments


Correlational research

Independent Variable (IV):

The variable that a researcher changes

Each group is given a different variable

…”I” do the research…it’s what “I” control


Independent variable

Independent Variable

Example 1:

Group 1 gets 100mg of a drug

Group 2 gets 25mg

Group 3 gets a fake pill

Here the IV is DRUG (different amounts)

IV

25 mg

100 mg

Sugar pill


Correlational research

Example 2:

Either give some subjects 20, 60 or 40 watts and test

their performance on a math test

20 watts

60 watts

100 watts

The IV = the amount of light


Correlational research

Dependent Variable:

-The variable that changes because the researcher changed the IV

-The variable that you measure


Dependent variable

Dependent Variable

Example 1:

Group 1 gets 100mg of a drug --- Sleeps for 9 hours

Group 2 gets 25mg – Sleeps for 4.5 hours

Group 3 gets a fake pill – Sleeps for 1 hour

Here the DV is sleep (different amounts)

IV

25 mg

100 mg

Sugar pill


Correlational research

Example 2:

Either give some subjects 20, 60 or 40 watts and test

their performance on a math test

20 watts

60 watts

100 watts

The DV = the different test scores


Correlational research

Dependent Variable:

Reaction time

cancer cells

errors on memory test


Correlational research

Types of Research

= (approach to gathering data)

LOW

  • Nonscientific

  • Naturalistic Observation

  • Case Study

  • Correlational Research

  • Quasi-experimental Research

  • Experimental Research

Level of Constraint

HI

HI Level of Constraint:

More control = more precision


Correlational research

Non Scientific: ex: Historians


Correlational research

CONSTRUCTS: Inferences we make

memory

Super ego

ego

id

personality

Reification of a construct: logical error

when we confuse a fact with a construct


Correlational research

An unexpected (confounding) variable??


Correlational research

Confounding Variables


Correlational research

The only thing that should change in an experiment is the independent variable. If something else changes during the experiment, it is a confounding variable


Correlational research

Confounding = confusing; causing problems

Confounding Variables

-Any variable that is different for

the two groups of subject

-It might change the results of the study


Examples of confounding variables

Examples of Confounding Variables:

  • Different environments

    • Room color

    • Temperature, seat comfort

    • Loudness

  • Sample is not random

  • Researcher treats the groups differently

    • Helps one group more

    • Is nicer to one group

  • Subjects know the experiment and hypothesis


Correlational research

examples of confounding variables

testing subjects on a memory test

…temperature in the room is HOT …impact on the tests results

Examining the effects of alcohol

on driving and obeying posted signs…but you don’t test their eyesight


Life expectancy

Life Expectancy


Correlational research

Figure 5-1. (p. 106)Graphical representation of the data in Table 5-3 showing the characteristic pattern of(a) high positive correlation, (b) essentially zero correlation, (c) strong negative correlation.


True experimental research

TRUE EXPERIMENTAL RESEARCH

  • Sample is assigned to groups

  • The surrounding is controlled by researcher


Experimental design

Experimental Design


Correlational research

Schizophrenia and semantics


Confounding variable

  • In an experiment, a variable other than the independent variable that could produce a change in the dependent variable

  • The variable “confounds” the results

Confounding Variable


Experiments control for other confounding variables

Experiments: Control for Other Confounding Variables

Module 4: Research Strategies


Confounding variables environmental differences

  • Any differences in the experiment’s conditions--between the experimental and control groups

  • Differences include temperature, lighting, noise levels, distractions, etc.

  • Ideally, there should be a minimum of environmental differences between the two groups.

Confounding Variables: Environmental Differences


Confounding variables expectation effects

  • Any changes in an experiment’s results due to the subject anticipating certain outcomes to the experiment

Confounding Variables:Expectation Effects


Blind procedure

  • An experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experiment

  • Sometimes called single blind procedure

Blind procedure


Double blind procedure

  • A research procedure in which both the data collectors and the research participants do not know the expected outcome of the experiment.

  • Both groups are ignorant (blind) to the experiment’s purpose or expected results

Double Blind Procedure


Placebo

  • A non-active substance or condition administered instead of a drug or active agent

  • Many times an inactive pill that has no known effect

  • Given to the control group

Placebo


Population

Population

  • The entire group of people about whom you would like to know something.

  • Random Sample- fairly represents a population because each member of the population has an equal chance of being included.


Correlational research

Data and the Nature of Measurement


Research ethics

Research Ethics

Module 4: Research Strategies


Ethics human research four basic principles

Ethics:Human Research(Four Basic Principles)

Module 4: Research Strategies


1 informed consent

1. Informed Consent

  • Participants must be informed, in advance, about:

    • the general nature of the research, and

    • any potential risk.

    • Participants must have the right to refuse participation or withdraw at any time.


2 right to be protected from harm and discomfort

2. Right to be Protected from Harm and Discomfort

  • Studies involving harm or discomfort may be conducted only under certain circumstances, and only with the informed consent of the participants.


3 right of confidentiality

3. Right of Confidentiality

  • Individual data about research participants should never be discussed or released.


4 right to debriefing

4. Right to Debriefing

  • Participants have a right to receive a complete explanation of the research at the end of the study.

  • This is extremely important if the research involves deception.


Ethics animal research

Ethics:Animal Research

Module 4: Research Strategies


Reasons for animal research

  • Interest in animal behavior as a topic of study

  • Data from animal studies may apply to humans.

  • Easier to do some type of studies (genetics) due to the shorter life span of animals

Reasons for Animal Research


Reasons for animal research1

  • Easier to exercise more control over experiments with animals as compared to humans

  • Procedures that are not ethical to perform on humans may be considered acceptable when performed on animals

Reasons for Animal Research


Care of animals used in research

  • Animals used in research must:

    • Have clean housing with adequate ventilation

    • Have appropriate food

    • Be well cared for

Care of Animals used in Research


  • Login