PSYCH 310 Exam 1 -- Jones

What are the four sources of knowledge?

- Authority

- Personal experience

- Tradition

- Intuition

Authority (source of knowledge)

I believe it’s true because Dr. Jones says it’s true

Personal experience (source of knowledge)

I believe it's true because I've experienced it

Tradition (source of knowledge)

I believe it because it's always been that way

Intuition (source of knowledge)

I believe it bc i feel it

confounding variable

a variable that is significantly related to your IV and DV but may distort their true relation

Empiricism

I believe it is true bc I can measure it

Reasoning

I believe it is true bc it is logically derived

Science is a continual interaction between these sources of knowledge

Reasoning and empiricism

What are the four objectives of science

Describe, explain, predict, control

What are the 5 tenets of science

Determinism, empiricism, replicability, falsifiability, parsimony

definition of research and why we do it

the systematic investigation into a study of materials and sources in order to establish facts and reach new conclusions

the scientific method

• Assume a natural cause for the phenomenon 

• Make an educated guess about the cause 

• Test your guess 

• Revise your hypothesis 

• Re-test your guess 

• Make a condition

What things do critical thinkers do

• Avoid oversimplification 

• Consider alternative explanations 

• Tolerate uncertainty 

• Maintain an air of skepticism but be open-minded

N of one fallacy

drawing conclusions/ generalizations from anecdotal evidence

the difference between descriptive and explanatory research

Descriptive: fills in the research community's understanding of the initial exploratory research

Explanatory: attempts to connect ideas to understand cause and effect

the difference between quantitative and qualitative research, and be able to recognize examples

Quantitative Research:

• Uses numerical data and statistical analysis

• Identifies patterns, trends, and relationships

• Provides objective and precise results

Qualitative Research

• Analyzes non-numerical data (interviews, observations)

• Focuses on understanding meaning, context, and subjective experience

Basic research

to enhance the general body of knowledge rather than address a specific, practical problem

Applied research

done with a practical problem in mind, and the researchers conduct their work in local, real-world context

the steps of conducting research

• Formulate hypotheses 

• Select appropriate  IV and DV 

• Limit alternative explanations for variation 

• Manipulate Ivs and Measure DV’s 

• Analyze variation in DV’s 

• Draw inferences about the relationship

Research vs personal experience

• Experience has no comparison group

• Experience is Confounded 

• Research is better than experience 

  • Found that venting one’s anger does not help one feel better 

• Research Results are Probabilistic 

  • Its findings do not explain all cases all of the time 

Availability heuristic

things that pop up easily in our mind tend to guide our thinking 

Present/present bias

when we fail to look for absences, and easily notice what is present/ failer to consider proper comparison group

Confirmation bias

the tendency to only look at information that agrees with what we already believe

Bias blind spot

the belief that we are unlikely to fall prey to other biases

When should we trust what authority figures tell us?

- if the authority systematically and objectively compared different conditions like a researcher

- if they've read good research and are interpreting it for you

- if they're basing their conclusions on empirical evidence

Know the basic publication process (including peer review process and reviewed blind)

Scientists publish their research in journals, following a peer-review process that leads to sharper thinking and improved communication

Know the basic layout of a journal article and the purposes of each section

- Abstract

- Introduction

- Method

- Results

- Discussion

- References

Know the difference between independent and dependent variables.

Independent: variable being manipulated in order to measure dependent

Dependent: variable being predicted and measured

Recognize the difference between a measured and manipulated variable, and a conceptual and operational variable

measured: simply observed and recorded (dependent)

manipulated: controlled (independent)

conceptual: abstract concepts, sometimes called constructs

- must be carefully defined

operational: a measured and manipulate-able variable from the conceptual variable by operationalizing it

In terms of operationalization, understand the three levels of hypotheses

Conceptual - State expected relationships among concepts

Research - Concepts are operationalized so that they are measurable

Statistical - State the expected relationship between or among summary values of populations, called parameters

Know the difference between the three types of claims, and be able to recognize examples

Frequency claims: describe a particular rate or degree of a single variable (proportions)

- ex: 2 out of 5 Americans worry daily

Association claims: argues that one level of a variable is likely to be associated with a particular level of another variable (sometimes said to correlate)

- ex: people with higher incomes spend less time socializing

Causal claims: arguing that one of the variables is responsible for changing the other

- ex: music lessons enhance IQ

internal validity

how pure a test is; how well it ensures that a test is only looking at the relationship b/w A and B and not other variables

external validity

how well the measure generalizes out

content validity

a measure must capture all parts of a define construct (capture all the reasons something is a good gym)

statistical validity

the extent to which a study's statistical conclusions are accurate and reasonable

What is power

The probability of NOT missing a significant effect

How do you increase power

maximize treatment
increase sample size
control environment

Know the difference between Type I and Type II Error

Type I: false positive -- finding an association between to variables when no association exists

Type II: false negative, miss - error made if you don't have sufficient power for a study and miss finding a real effect/result that is actually there

Know what elements are necessary when making a causal claim

Covariance: the extent to which two variables are observed to go together determined by the results of the study

Temporal precedence: means that on variable comes first in time before the other variable

Internal validity: a study's ability to eliminate alternative explanations for the association

Face validity

whether the measure seems to be a reasonable measure of the construct

Construct validity

How well the construct is operationalized: what is gym

content validity

when you make sure you capture all the dimensions of the variable you are going to measure (gym example)

Understand the role of the IRB

Institutional Review Board

- this group reviews and approves studies at a university before the study is conducted

- interprets ethical principles and ensures research using human participants is conducted ethically

Know the 5 General Principles of the APA Ethics Code

- beneficence and nonmaleficence: take precautions to protect participants from harm and to ensure their well-being

- justice: treat all groups fairly

- fidelity and responsibility: establish relationships of trust

- respect for persons: people should be treated as autonomous agents

- integrity: teach accurately and truthfully

Understand the importance of confidentiality, informed consent, and avoiding multiple relationships.

limits of confidentiality -- suicidal ideation, homicidal ideation, suspected abuse of children, the elderly or disabled, court order from a judge

- informed consent: each person learns the project, its risks and benefits, and decides whether to participate

special populations in research that require extra protection

children, pregnant women, prisoners, etc.

Understand plagiarism

representing the ideas or words of others as one's own

What is deception in research

deception: withholding some details of the study from participants

what is the necessity of deception

to observe participants without them knowing it's a study so we can see their natural behaviors

what is debriefing and what is its purpose

takes place after deception to describe the nature of the deception and why it was necessary

- attempts to restore an honest relationship with participant

Data fabrication

inventing data to fit a hypothesis

what is data falsification

when results are influences by selectively deleting observations or influencing subjects to act in the hypothesized way

Know the basics of conducting ethical animal research

the three R's

- Replacement: researchers should find alternatives to animals in research when possible (computer simulations)

- Refinement: researchers must modify procedures and other aspects of animal care to minimize or eliminate animal distress

- Reduction: researchers should adopt experimental designs and procedures that require the fewest animals possible

Understand the difference between qualitative and quantitative (nominal) variables

Qualitative variables are categorical and describe qualities or characteristics.

• eye color or gender

Quantitative (nominal) variables are numerical and represent quantities or amounts.

Understand the difference between nominal, ordinal, ratio, and interval variables

nominal: names

ordinal: rank order of quantitative variables

interval: the numerals of a quantitative variable that meets two conditions: the numerals represent equal distance between levels, and there's no true 0

ratio: when the numerals have equal intervals and there is a true 0 (means none)

Pros and Cons of: Self-report vs. observational measures vs. physiological measures vs. open ended questions

self-report: operationalizes a variable by recording people's answers to questions about themselves in a questionnaire or interview

observational: operationalizes by recording observable behaviors or physical traces of behaviors

physiological: operationalizes by recording biological data, such as brain activity, hormone levels, or heart rate

pros and cons of open-ended questons:

- pro: good amount of info, allows them to respond how they want

- con: how to code the info in a meaningful way, much more time consuming

fixed alternative

Multiple choice, yes/no, T/F

Likert

rating ATTITUDE or OPINION of participants

Rating scale

rating FREQUENCY or AMOUNT of behavior

socially desirability responsing

giving answers that make them look better than they really are because they're shy or embarrassed

- can be avoided by anonymity

response sets

response sets: aka non differentiation -- type of shortcut respondents can take - rather than thinking carefully about each question, they answer all of them the same

- can be avoided by forced-choice questionsor attention tests

Test-retest reliability

if the test is taken twice, how close are Time A and Time B scores?

interrater reliability

whether two observers give consistent ratings to a sample of targets  

Internal validity

a study participant gives a consistent pattern of answers, no matter how the researcher phrases the question

- to see how well the items group together

- look at Cronbach's alpha to show how strong your scale is

Criterion Validity

how well your measure is correlated with a relevant behavioral outcome collect data that shows a measure is correlates with expected behavioral outcomes 

Convergent validity

how similar your measure is with other measures

Divergent validity

how dissimilar your measure is with other measures

reliability vs validity

Reliability refers to the consistency of a measure (whether the results can be reproduced under the same conditions).

Validity refers to the accuracy of a measure (whether the results really do represent what they are supposed to measure).

Know the ways psychologists might measure behavior in an observational study

• Observational Measures 

  • behavior r is observes 

  • Then it is coded by researchers 

• Physiological measures 

  • Objective measurements are taken 

  • Biomarkers, EEG, brain scans, BMI, heart rate

Know the concept of a p value

the strength of

Know the difference between a scale, an inventory, and a test, and be able to recognize examples of each

Scale: how variables are defined or organized

Inventory: any checklist, questionnaire or personality measure

Test: an objective and standardized measure of an individual's mental and/or

Why does question order matter and what are order effects?

- matters because being exposed to one condition changes how participants react to the other condition

- order effects: happen when exposure to one level of the independent variable influences responses to the next level

- in a within-group design is a confound

- practice effects: a long sequence makes the participants bored or tired toward the end

- carryover effects: some form of contamination carries over from one condition to the next

Know how negative wording, leading questions, and double barreled questions may affect survey results

- negative wording: negative phrasing can cause confusion and reduce the construct validity

- double-barreled question: asks two questions in one - have poor construct validity because people might only respond to one part of the question

- leading question: one whose wording leads people to a particular response

Understand the pros and cons of open-ended questions vs. forced-choice questions

open-ended

pros: spontaneous, rich information

cons: responses must be coded and organized, which is time consuming and difficult

forced choice

pros: easy to code and efficient

cons: wording and order of questions are much more important

Know how to avoid survey issues

- be careful with question wording

- avoid double-barreled, leading, and negative wording questions

Understand some accuracy limitations of self-reporting

- can be inaccurate unintentionally

- people may not be able to accurately explain why they acted as they did

Why might an observational study design be better than a self-report measure in some cases?

- people can't always accurately report the reason behind their behaviors

- people's memories about events in which they participated are not very accurate

Observer bias

researcher expectations influence their interpretation of a group's behavior

observer effect

researcher behavior influences the behavior of the group

reactivity

a change in behavior when study participants know another person is watching, better or worse

ways to prevent observer bias and effect

- train observers well, develop clear rating instructions, use multiple observers, use a masked design

ways to avoid reactivity and effects

blend in -- make unobtrusive observations,

use a one-way mirror

wait it out

measure the behavior's results

Bias sampling

unrepresentative
easy to get, cheap, fast, convinent

unbiased sampling

Representative
random
takes more work, time and/or money

simple random sample

use a basic from of random selection from a population to get your participants

probability sampling

technique for which you can specifiy the probaibility that a given partivipant will be selected from a population
make broader genralizations

non-probablilty sampling

it is impossible to specify the probability of selecting any one individual
the sample may or may not be representative of the population
limited external validity but can test specific theories

systematic sampling

pop divided by sample size to provide you with number K, then from a random starting point you select ever kth individual

cluster sampling

take a group of schools or countries from a state and then sample those groups/ use all individuals in those clusters

mulitstage sampling

take a group of clusters, and then take a random sample from those clusters/ not all individuals used

stratified random sampling

recruiting a certain percentage of participants from different groups for a reason

convenience sampling

using whatever participants are easily avaliable

purposive sampling

convinence sampling in which the goal is to select participants with particular characteristics

quota sampling

convenience sampling in which the goal is to select participants with particular characteristics until you have enough

snowball sampling (or referral sampling)

involves including participants in the sample who have been referred by other participants

random assignment vs random sampling

sampling involves selection of overall participants
assignment involves selection to groups

Choosing a sample size

how much money, time, resources, person power, expected effect size, type of analysis,variability of the data, number of conditions, diminishing returns

Bivariate correlations measure

an association that involves exzactly two variables (at the same time in the same group of ppl)

use r to describe
use t when their are two categorical levels
use Anova (f test) when ther are three or more categorical levels

how to avoid afects of outliers in our results

data transformation ( taking square roots of values)
changing score (next highest plus one or the mean plus two SD)
remove cases