Textbook Notes (280,000)
CA (160,000)
York (10,000)
PSYC (4,000)
PSYC 2130 (100)
Chapter 2

PSYC 2130 Chapter Notes - Chapter 2: Experiment, Scatter Plot, Natural Environment

Course Code
PSYC 2130
Frank Marchese

This preview shows pages 1-3. to view the full 9 pages of the document.
Study Notes: Chapter #2 Methods of Personality Research and
There are 3 methods of study of personality:
o 1) experimental
o 2) correlational
o 3) case study
The Experimental Methods
Experimental method -> aka. The true experiment. It requires two criteria to be met:
o 1) a factor that is hypothesized to cause the behavior being studied is systematically
varied while
o 2) all other possible causative factors are held constant
Independent variable -> factor held constant in an experiment.
o Ex. Study of TV violence, TV violence is independent variable it’s either present or
experimental subjects) or absent (for control subjects)
Dependent variable -> behavior that is to be observed in an experiment
o It’s expected to be caused by or depend on the independent variable
In simplest experiment, two groups of otherwise similar subjects are used
Subjects in the experimental group are exposed to the independent variable (hypothesized
causal factor or treatment) and subjects in a control group are not
o in all other respects, the groups are treated alike
o hence, of the two groups differ on the independent variable, (the behavior being
measured), the difference must be due to the independent variable
to eliminate effects such as confounding variables (like in TV violence on aggression,
confounding variable could be naturally aggressive subjects) groups in an experiment must be
equivalent in such matters as subjects’ personal characteristics
o usually this is done by random assignment
o Confounding variables -> factors inadvertently allowed to co-vary with group
o Random assignment -> every subject has an equal chance of being placed in each group
Intended result is that differences in subjects’ personal characteristics, such as
“natural aggressiveness” will tend to equalize across groups
Thus, no group has a disproportionate number of subjects with any particular
o Matched random assignment -> a way to enhance our confidence that subjects’
personal characteristics are equally distributed in each group

Only pages 1-3 are available for preview. Some parts have been intentionally blurred.

relevant characteristics (i.e., those that may cause changes in the behavior
being studied) are assessed before the subjects are assigned to groups
then subjects are paired, so that each member of a pair has the same value of
the characteristic and then one member of each pair is assigned to each group
experimental method provides a high degree of control over content, environment and subject
o control in this context means systematically varying, randomizing, or holding constant
the conditions under which observations are made
o it increases probability that treatment groups are equivalent across conditions on all but
the presence of the variable(s) of interest
o such control makes logical demonstration of cause-and-effect relationships more
o presence of these control contributes to the confidence that we have in our conclusion
that the variable under study and not some other extraneous factor, caused the
observed effect
in studies that use groups of subjects, average performance is examined
o in TV violence study, on average, children exposed to a violent TV program were more
aggressive than those exposed to nonviolent TV program
o but the amount of aggression varied, some in experimental group exhibited less
aggression than some control subjects
true experiments can have more than two groups and a no treatment control group is not
always required
instead of just having independent variable present or absent, there can be different amounts
or levels of the independent variable present
o random assignment still necessary
Evaluation of the Experimental Method:
major advantage of experimental method: it increases our confidence that the relationships
observed are, in fact, cause-and-effect relationships
changes in dependent variable can be causally linked to independent variable because all other
relevant variables (influences) are controlled
experiments often conducted in psych lab where tight control over conditions is possible
price paid for such control may be artificiality because context is so different from real life
o ex. Watching TV in psych lab not the same as watching TV at home
o hence why experimental conditions must be similar enough to real-life circumstances
o most experimenters want to generalize what is found in experiment to real life
The Correlational Method
correlation -> co- or joint relationship
questions of the relationship are often asked about personality
o Problems toilet training related to compulsiveness in adulthood?
Correlational method makes observations of all subjects under the same conditions

Only pages 1-3 are available for preview. Some parts have been intentionally blurred.

o (note the contrast with the experimental method where conditions under which
subjects are observed are systematically varied)
In correlational study, pair of observations is collected for each member of group subjects
Knowing that two variables are correlated is usually not sufficient, we also want to know:
o 1) the strength of the relationship
o 2) the way the variables relate
The magnitude (Strength) of a correlation tells us how well one variable can predict the other
o Higher magnitude of correlation, the more accurate the prediction
two variables can be related directly or inversely, referred to as direction of correlation
direct or positive correlation -> between X and Y, means that high scores on X tend to be
associated with high scores on Y and low score on X tend to be associated with low scores on Y
o ex. IQ scores on parents and children brighter parents tend to have brighter children
inverse or negative correlation -> high scores on X are associated with low scores on Y, and low
scores on X go with high scores on Y
o age and quickness of reflexes are negatively correlated
correlation of scores can be visually represented by plotting them on a scatter diagram
o magnitude of correlation is reflected by how closely the points in the scatter diagram
conform to a straight line, the line of perfect correlation
o knowing person’s score on variable enables perfect prediction of the person’s score on
the other variable
o with high or strong (but not perfect) correlations, there is some scatter (deviation)
around the line of perfect correlation, but points tend to fall within a narrow ellipse,
making predictions of one variable from the other reasonably accurate
o lower or weaker the correlation, more scatter there is
o where no systematic (linear) relationship exists between the variables, the points are
scattered all over, making it impossible to predict one variable from the other
o bottom left to top right = positive, top left to bottom right = negative
correlation coefficient -> (abbreviated r) is a numerical index of correlation between two
o correlation coefficients range from +1.00 to -1.00
o 0 means no relationship
Evaluation of the Correlational Method
Method involves making observations without controlling the subjects’ behaviors or varying the
circumstances under which the subjects are observed
o Natural environment of situation is preserved, which may bring research closer to real
life than experimental method
Collecting data on variable as it naturally occurs as is done in correlational studies may allow
researcher to examine variable over broader range than in experiments
o Ex. In studying effects of stress, not ethical to induce more than brief, mild stress in
research subjects, but in eternally induced stressful situations
Correlational studies allow researchers to examine a large number of variables simultaneously
o Important because in real life, people’s behavior are always influenced by multiple
You're Reading a Preview

Unlock to view full version