Final exam

Descriptive Research Design

A research design that aims to describe and explain a phenomenon, without manipulating or controlling any variables. It seeks to provide a detailed and comprehensive understanding of the subject being studied.

Correlational Research Design

A research method that examines the relationship between two or more variables without manipulating them. It helps to identify patterns and predict outcomes.

Experimental research design

Type of research design where the researcher manipulates an independent variable to observe its effect on a dependent variable. It involves random assignment of participants to groups and control of extraneous variables.

We use correlation coefficient to make 2 statements about their association:

Magnitude and direction

Correlation Coefficient

A measure of the strength and direction of the linear relationship between two variables.

Correlational Research

Involves the measurement of two or more relevant variable and an assessment of the relationship between or among those variables.

Height and brain size

Hours of studying and grade on the exam

Limitations of Correlations

* Can’t Infer causality
* Relationship could eb due to other variables
* may be insensitive to nonlinear relationships

3 conditions for Cause and Effect Relations

* Direction
* Association
* Isolation

Direction

Temporal Ordering ( cause preceded the effect)

Association

Covariation ( cause and effect are associated)

Isolation

Rule out Third Variables ( no plausible explanation for the effect other than the cause)

Third- Variable Problem

A phenomenon where a third variable influences both the independent and dependent variable, creating a false association between them.

Reasons we use correlations

* Prediction


* Shows Relation across a whole range of scores
* Measure variables ‘ as they are’

Factors affecting significance

* Alpha
* Magnitude
* Sample size

Factors that distort correlations:

* Reliability of measures
* Restriction of range
* Outliers

Outliers: Factors that distort correlation

* ON-line outliers tend to inflate the correlation
* Off-line outliers tend to deflate the correlation

If you wanted to know if SAT predicts college performance better than high school GPA does, you can?

do significance of test correlations

If you wanted to know if SAT predicts the same or different variation in college performance as does high school GPA, you can do?

Partial correlation or regression

Characteristics of Archival research include?

* Analysis of existing information
* Requires a translation of existing records into IVs and DVs
* Subject to all the standard threats to internal validity and the standard concerns over non-experimental research
* rely entirely on information gathered for other purposes
* need to be creative and resourceful
* lot of info to search through
* Alternative interpretations always possible

Archival Research

Research method that involves the examination of primary sources, such as documents, records, and artifacts, to understand past events and people.

What are advantages of Archival Research ?

* Economical
* Analyze over time
* collected from naïve participants
* Large scale social/ natural phenomena
* Available to be double checked
* experiment may not be possible
* %%Typically strong external validity%%

Disadvantages to Archival research?

* Limited to what was recorded: risk of making incorrect inference
* you have no say as to what questions or how they were asked
* Effort involved in finding relevant information
* Can be incomplete- can have gaps or be biased

Statistical Archives

* Census and other sources of statistical records
* Data are plentiful

Survey Archives

* data collected specifically to address various topics, including attitudes and beliefs
* Almost always self-report data

Small N Research

Research method that involves studying a small number of cases in-depth to gain a deep understanding of a phenomenon. Typically used when studying complex or unique cases where large sample sizes are not feasible or necessary.

Small N research designs are used?

clinical Psychology, Neuropsychology and animal learning

Two major types of small N research designs

* Case Study
* Single- subject experimental designs

Case Study: Thorndike Cats

Flashcard:

Experiment by Thorndike in which cats were placed in a puzzle box to study their ability to learn. The cats learned to escape the box by trial and error, gradually reducing the time taken to escape. This experiment led to the development of the Law of Effect, which states that behaviors followed by positive outcomes are more likely to be repeated.

Case study: Phineas Gage

Flashcard: Phineas Gage
Description: A railroad construction foreman who survived a severe brain injury in 1848. The accident damaged his frontal lobes, which affected his personality and behavior. His case became famous in the field of neuroscience for demonstrating the link between brain damage and behavior.

Iconic Memory: Sperling

\
Flashcard for Iconic Memory: Sperling: A type of sensory memory that stores visual information for a brief period of time. It was studied by George Sperling in the 1960s, who found that participants could recall a matrix of letters flashed on a screen, but only for a fraction of a second before the memory faded.

Why small N?

* There are concerns about individual- subject validity

Individual-subject validity

The extent to which a test accurately measures a specific trait or characteristic of an individual, independent of other factors.

Why small N more examples

* Specific subjects difficult to access
* patients
* rare species
* Time-consuming Interventions

Case study method

* Intensive description and analysis of single individual or event
* clinical observations, self report and experimental results

Advantages: Case Study

* Rich Source of ideas for hypotheses
* Opportunity for clinical innovation
* Method for studying rare events
* Possible challenge to theoretical assumptions

Disadvantages: Case Study

* Problem of generalizing findings from a single individual
* %%Limited external validity%%
* Difficultly to draw cause-and-effect conclusions
* %%limited INTERNAL VALIDITY%%

\

Single- Subject Experimental Designs

Flashcard: Single-Subject Experimental Designs are research designs used to evaluate the effectiveness of interventions on a single individual. These designs use repeated measures to assess the impact of the intervention, and require a baseline phase and at least one intervention phase. Examples include ABAB, multiple baseline, and changing criterion designs.

There are Many examples of single-subject experimental designs within ________?

Applied behavior analysis

Single-Subject Design: Baseline

* Describe behavior before treatment
* Predict future behavior ( with no treatment)
* Average of baseline

ABAB design

\
A research design where a baseline phase (A) is followed by an intervention phase (B), followed by the withdrawal of the intervention (A) and then reintroduction of the intervention (B). The design is used to evaluate the effects of an intervention by comparing the behavior during the baseline and intervention phases.

Withdrawal design Issues

* If behavior's does not reseverse to baseline levels when treatment is withdrawn researchers cannot conclude treatment causes the initial behavior change
* Difficult to detect clear discontinuity in behavior following treatment if baseline is unstable

Single- Subject Design Issues

* Potential for ambiguity in interpretation

Ethical Issues ( ABAB)

* Is it ethical to remove a treatment that appears to be beneficial

Sampling

The process of selecting a subset of individuals or items from a larger population in order to gather information about the population as a whole.

WEIRD samples

Samples that are not representative of the global population as they are Western, Educated, Industrialized, Rich, and Democratic. These samples are often used in psychological research, leading to limited generalizability of findings.

Having a sample that is representative of the population helps to increase ?

External Validity

External Validity

External Validity: The extent to which the results of a study can be generalized to other settings, populations, and conditions beyond the study's original context.

2 Categories of sampling

* Probability
* Non-Probability

Probability Sampling

* Every element in a population has a known chance of being included in sample
* Random selection
* Allows one to generate probability of sample estimates deviating from population values

Standard Error ___ as Sample Size Increases

Decreases

As population size goes up, SD ______

goes up

As variability of score goes up, standard error ______

goes up

Simple Random Sampling

All elements have an equal probability of being selected

Nonprobability sampling

* no way to know likelihood of element being included in sample
* Elements are not randomly selected

Nonprobability sampling is typically ? and ?

Cheaper and more convenient

In most cases, ?, is obtained with probability sampling

Higher External Validity

Types of nonprobability samples

* Convenience
* Quota
* Purposive
* Snowball

Convenience Sampling

* using participants that are readily available
* people on the street

Quota Sampling

Specifying X number of people in sample to contain a particular characteristic ( gender, race, ses)

Purposive sampling

* One or more specific predefined groups being sought
* Researcher may try to choose those who are typical of population

Snowball Sampling

Begin by identifying someone who meets the critia for inclusion in your study. then asking then to recommend other potential participants

Self-selection Bias

Sample participants include only those who are highly motivated or have some particular interest in replying

Halo Bias

tendency for positive impressions of a person, company, country, brand, or product in one area to positively or negatively influence one's opinion or feelings in other areas. 

Observational research is high in?

External Validity

Social desirability bias

People wanting to make themselves look good

Advantages and Disadvantages: Observation

Advantage: Nonreactive measures

Disadvantages: limited in ability to answer causal questions

Observation (as a design)

* Physical trace
* Naturalistic Observation
* Participant Observation

Physical Traces

Relies on physical pieces of data not produced specifically for research

Naturalistic Observation

* Selection, recording and encoding of a set of natural behaviors or other naturally occurring phenomena
* Setting can be structures or unstructured and still be considered systematic observation

Observer Drift

becoming less reliable over time

Cognitive dissonance

the more difficult a goal is to obtain the more we will value it later

Quantitative data analysis

Data summarized using descriptive measures such as frequency counts, means, and standard deviations

Qualitative data Analysis

\-Researches code behaviors according to specified criteria

Open-Ended Self Report

Respondents are unconstrained in verbal or written answer to question

Closed-Ended Self report

* Given 2+ alternatives, select option closet to their belied/attitude

Informant Reports

Ratings by peers, Parents, Teachers, Supervisors, Co-workers

Realistic Accuracy Model (RAM)

outlines a four-stage process necessary to achieve accurate personality judgments. 

Relevance ( RAM)

Person must do something relevant to dimension being judged

Availability (RAM)

Observer has to be able to see it

Detection (RAM)

Observer has to actually see it

Utilization

Observer must remember the action and interpret that piece of information correctly

Types of Sensitive questions

* Intrusive
* Disclose poses a threat
* Elicits responses that’re socially unacceptable

Summated Rating Scalee

* Likert Type
* Very common
* multiple items

Acquiescent Response Style

* General tendency to agree with all statements regardless of content
* Need to include reverse-scored items to deal with

Technology: Sacrificing ? to increase ?

Internal & external

Event Sampling

* Sample events or experiences
* often we use tech to record thoughts, feelings, behavior

Event Sampling Strategies

* Sampling at random
* Event-Contingent sampling

Sampling at random

* Signaling device beeps at random periods throughout the day
* Participants are asked to record thoughts feelings or behaviors

Event-Contingent sampling

* Answer a short questionnaire after an event of interest occurs
* Timing of response is determined by the participant

Advantages: Event Sampling

* Smaller number of subjects given large number of observations for each
* Shorter retention interval to promote memory accuracy
* Data collect themselves

Disadvantages; Event sampling

* Subject compliance is needed
* Guarantee that subject is telling the truth
* Technological problems

Mechanical Turk

* Online environment managed by amazon
* requesters provide surveys/experiments
* Workers choose and fulfill study requirements for relatively little compensation

Converging operations

* to balance differences in approaches and designs, best to understand behavior using multiple studies
* Idea is that measuring and operationally defining behavior multiple ways will still converge upon same result

Major section of APA

* Title page
* Abstract
* Introduction
* Method
* Results
* Discussion
* Reference

General APA Guidelines

* Typed, double spaced, 1 Inch margins
* TNR 12
* number of page in top right

In-text citations

include authors name and year of publication

DOI

* Digital Object Identifier

Introduction Purpose

* describes the problem under study
* presents background literature on it
* shows why it warrants further investigation

Introduction begins on?

page three before final formatting