Transcript Chapter 6: Research & Statistics

CHAPTER 6
Psychological Research and Statistics
Objectives
Describe the process of psychological research
 Name the different types of psychological
research and some of the methodological
hazards of doing research
 Describe descriptive and inferential statistics
 Name specific research methods used to
organize data

Gathering Data

How do psychologists collect information
about the topic they’ve chosen to study?
Gathering Data

Validity – extent to which an instrument
measures or predicts what it is supposed to
 Algebra
questions would not be a valid measure
of what you learned in Psych class
Gathering Data


Sample – relatively small group out of the total
population
Population – an entire group as a whole
 Sample must be representative of the population
 If a sample is not representative, then it is biased
 How can researchers avoid bias?
Gathering Data

What does correlation mean?
 The degree of relatedness between two sets
of data
 Two
types - positive correlation & negative
correlation
Gathering Data

IQ scores and academic success – positive
correlation (direct relationship)
 The higher your IQ, the higher your grades
Car speed and time it takes to travel somewhere
– negative correlation (inverse relationship)
- as car speed increases, time it takes to reach
your destination decreases
Correlations

Your turn!

Hours in the sun and chance of sunburn
 Positive
correlation
Amount of exercise and % body fat
Negative correlation
Mrs. Bird’s high school GPA and your high school GPA
no correlation
Correlations

A researcher uses statistics to compute their
research findings
 Statistics
= field of mathematics that involves the
analysis of numerical data about representative sample
of population

Correlation coefficient =
 needs
to be near 1 (-/+), the closer results are to -1 or
+1 the better the relatability between the two
variables
Experiments

Why do researchers choose experimentation over
other research methods?
 Researchers
can control the situation.
 Can establish cause and effect, only research
method in which you can
The goal of research is to prove or disprove a
...
Hypothesis
Experiments


Variables – conditions and behaviors that are
subject to variation/change
Two types of variables – independent and
dependent
 IV – manipulated variable in order to view
its effects
 DV – dependent upon the IV – affected by
it, the one the researcher measures
Experiments


Experimental group – consists of subjects who
undergo the experimental treatment –
variables are applied to this group
Control group – consists of subjects who do not
receive experimental treatment
 Why is this group necessary?
Experiments in Psych



Avoid Researcher Bias: researcher’s desire to prove
hypothesis affects results
Avoid Self-fulfilling prophecy: researcher’s desire to
prove hypothesis affects results
Could be very subtle or unconscious, but researcher
will treat one group slightly differenty (body
language, tone of voice)
Avoiding Researcher Bias


Use double-blind = neither researcher nor subjects
know what group they are in, helps reduce
researcher influencing results
Confounding variables = factors that cause changes
in the dependent variable that aren’t the
independent variables

Quasi-Experiment (“sort of” experiment)
For example, imagine that we wanted to do a study to compare student
performance. Imagine further that we scheduled two sections of the
course, let students sign up for which one they wanted, and then taught
one using cooperative learning and the other using standard
lecture. Note that this study includes a manipulated independent
variable, but it lacks random assignment of participants to conditions.
The problem with this approach, of course, is that there might be
differences between the two groups of students other than the style of
teaching to which they were exposed. Perhaps the students who signed
up for the earlier section are more “gung ho.” Or perhaps the students
who signed up for the evening section are more likely to be working
adults. Or perhaps the students in the 1:00 p.m. section tend to be
drowsy after lunch. It is possible that differences in the dependent
variable could have been caused by these differences rather than
differences in teaching style.
So what’s the problem
with quasi-experiments?

No random assignment!
= a sort of experiment!

Other examples: boys vs
girls, old vs. young

Naturalistic Observations

Naturalistic observation – viewing the subjects
of an experiment in their natural habitat
 IMPORTANT: Subjects CANNOT know they
are being watched!
Why is this important??
CASE STUDY

Case study – a scientific biography of a group
or person, very in depth look at a phenomena
 Most use long-term research to gather tons
of data in order to generate new hypotheses
Utilize lots of different tests to collect data
ex) facial agnosia, split brain patients
Surveys

Surveys – an interview/questionnaire that
gathers data on the attitudes, beliefs, and
experiences of large numbers of people
Longitudinal Studies


Longitudinal studies – covers a long period of
time, same subjects followed for long time and
questioned at different intervals in time (ex.
Age 20, 25, 30 35)
Psychologists study subjects over regular
intervals for a period of years
 Allows for examination of consistencies and
inconsistencies as development occurs
Cross-sectional
Cross-sectional studies – individuals are
organized/studied on the basis of age
 Question different groups of people that
represent different stages of development

Avoiding Errors

How can researchers avoid errors while doing research?
 self-fulfilling prophecy - Researchers finding what
they want to find, while overlooking contrary
evidence
 Example experiment – testing a new medicine
 Single Blind – subjects do not know if they have a are
in control group (placebo) or in the experimental
group ( get real IV)
 Double Blind – subjects AND experimenter have no
knowledge of who in is experimental or control group
= best option if possible to design

Smile Break
Statistics

A branch of mathematics that enables
researchers to organize and evaluate the
data they collect
Statistics

Descriptive statistics – listing and
summarizing data in a practical and
efficient way
 Examples
– graphs, averages
Statistics

Frequency distribution – table that arranges
data in a way that allows us to see how often
a particular score occurs
Histogram – similar to bar graphs – always
vertical & the bars always touch
 Frequency polygon – no bars just lines to
visually display data

Frequency Distribution
Histogram
Frequency Polygon
Central Tendency

Central tendency – a number that
describes something about the “average”
score
Used to summarize information into
statistics
Measures
of CT: mean, median mode
Central Tendency

Mean – an “average” score
Most commonly used measure of CT
To find the mean, you add all scores and
divide by the number of scores
Central Tendency

Median – the middle score
The midpoint of a set of scores, so it
divides the frequency distribution into
two halves
Mode
– the most frequent score
Central Tendency

0, 3, 4, 4, 5, 5, 6, 7, 8, 8, 8, 9, 9, 10, 10
Mean – 6.4
 Median – 7
 Mode - 8

Measures of Variance


Distributions show us not only the
“average” score, but also how “spread
out” these scores are.
Variance – provides an index of how
spread out the scores of a distribution are
Measures of Variance


Range – subtract the lowest score from the
highest score
Standard deviation – a measure of distance,
describing an “average” distance of every
score to the mean
 The larger the standard deviation, the more
spread out the scores are
Standard Deviation
Inferential Statistics

Used to determine whether or not the data that
researchers collect supports their hypotheses,
or whether their results are merely due to
chance outcomes, draw conclusions &
interpret data
 probability
& chance
If probability that results are due to chance
is less than 5% ( .05), researchers can be
confident in their findings (less than 1 in 20
chance)
Ethical Guidelines

Read page 59
Define for Homework, Chapter 6
Population
Sample
Experimental group
Control group
Between subject design
Within subject design
Confounding variables
Operational definition
Random Assignments
Experimenter Bias
Placebo effect
Demand characteristics
Counterbalancing
Reliability
Ex post facto
Bimodal
Multimodal
Skewed distribution
Meta-analysis