PSYC210 Exam

inferential statistics

used to decide about the population based on observations on the sample

Sampling distributions and logic (what do we do?)

1. make a guess about the population frequency distribution - hypothesise what the mean is
2. take a random sample
3. decide if sample came from a pop, like the one you guessed in step 1 (usually based on how close the statistical mean (x w/ dash) is to the hypothesized parameter mean (u)

Central limit theorem sampling distribution

* assume
* normal population distribution with u and o (mean and sd)
* take
* repeated samples of size n
* plot
* x (w/ dash) of each sample

significance level or alpha (a) level

the probability value that defines the boundary between rejecting or retaining the null hypothesis (h0)

* level usual at 0.05 (or sometimes 0.01)

p < alpha → rejection of H0 (null hypothesis)

region of rejection

the proportion of area in a sampling distribution that represents the sample means that are improbable if Ho (null hypothesis) is true

type I error

rejecting the null hypothesis when it is true

p = alpha

type II error

retaining the null hypothesis when it is false

p = B (beta)

understanding the relationship between type I and type II errors

* type I and type II errors are mutually exclusive
* if you have one type, you can NOT have the other
* changes in one type of error have an effect on the other type of error

minimising type II errors

* reducing B and increasing power (1 - B)

so that we can reject the null hypothesis when it is false

increasing alpha

1. reduces the probability of a type II error
2. increases power (1 - B)

(increases the probability of rejecting the null hypothesis when it is false)

degrees of freedom

how many scores in the sample are free to vary - generally all scores except the last one

assumptions of the single sample t test

1. the random sample compromises interval or ratio scores
2. the distribution of individual scores is normal
3. the standard error of the mean is estimated using the s computed from the sample

single sample t test steps

1. calculate the observed t using the estimated standard error of the mean
2. determine the df
3. look up the critical t in the t-table with the appropriate df (and alpha)
4. if observed t __is greater than or equal to__ the tabled value then reject the null

Neurons

densely connected and have many dendrites

axons

conduct electrical signals and are surrounded by myelin

myelin

a major factor in determining the MR signal and contrast

the brain is organized into two types of ‘tissues’

* grey matter (outer portion)
* densely packed cell bodies around the outside of the brain 
* dendrites, cell body
* white matter (inner portion)
* Myelinated axons
* axon, axon terminals

MRI analysis

MRI is:

* noisy
* variable/configurable

analysis is:

* based on stats
* has many options/alternatives
* has more than one ‘right’ way (but many wrong)

MRI

magnetic resonance imaging, noisy and can change depending time and signalling of the machine, Indirect measure of the brain.

\
Cerebrospinal fluid 

the fluid in and around the brain and spinal cord - cushions the brain

MRI machine 

magnet - Creates Bo Field, radio frequency coil. People with pacemakers can not go in it 

Why are H20 protons needed for an MRI to work?

\
The molecules move in the direction of the magnetic field thus creating better photos

Structural MRI

measures the location and density of hydrogen to create an image of the anatomical structures of the brain 

What can you look at in the brain with a structural MRI?

Tissue types, subcortical structure and shape and GM changes

\
Null hypothesis 

There will be no relationship between the 2 variables.

\
T test results 

the further apart the means are the more reliable - how wide the disruption from the top of each peak. if lower than 0.05 then it is probably a difference 

\
Structural MRI limitations 

It is an indirect measure, absolute values are not the same for every scanner, leaves out certain details as cells are microscopic, doesn't distinguish bone from air, contrast is poor for deep brain regions, a single sequence does not show all pathologies 

Diffusion MRI

a noninvasive imaging technique that maps neural connections in the brain by tracking the diffusion of water molecules along myelinated axons - averaged over a 3d picture 

\
How is a Diffusion MRI useful?

info about microstructure by looking at the direction of the water 

\
How many directions of water movement can a diffusion MRI image see?

One direction. As the water can move in lots of directions lots of pictures need to be taken 

\
Structural vs Diffusion MRI 

Structural takes 5 mins for one photo 

\
Diffusion takes total of 5 mins for 100-300 images 

\
Diffusion mri has lower resolution 

corpus callosum

the large band of neural fibers connecting the two brain hemispheres and carrying messages between them

Diffusion MRI images

if water diffuses quickly in the direction of the image then there will be a black mark in that area of the brain.

mean diffusivity

overall displacement of molecules and presence of obstacles to diffusion

\
what does a diffusion MRI measure in scientific terms?

Average direction of axons in voxel(3d chunk of the brain) and axonal integrity (how much overall does the water diffuse)

Tractography

a method for tracing white matter pathways in the brain to investigate connectivity

\
Why do Diffusion MRIs focus on White matter not gray matter?

grey matter is mainly unorganised cell bodies where the water does not flow in a specific way

regression analysis

Statistical method used to determine what the relationship between variables and the strength of the relationship. - fits a line that best fits the data 

Y = a + (b x X) for regression analysis

Y = Y axis

a = intercept (where the line crosses the Y axis

b = slope of the line 

X = X axis

Diffusion MRI limitations 

Doesn't measure -size/density directly 

* Single fibres 
* difficult to deal with crossing fibres

\
Difficult to do in pulsatile regions 

\
More restricted by scanner hardware 

\
And may distort images

What type of data does qualitative research use?

quotes, images and non numeric data 

Who studied the differences between adult and student binge watching tv?

Rubenking and Bracken (2018)

Who had a higher rate of binge watching in the rubenking and bracken study?

Students ( age had a significant negative relationship with binge watching)

Who researched the psychological factors involved with binge watching behaviours 

Steiner and Xu (2020)

What were the main themes in the Steiner and Xu study?

Relaxation, catching up, sense of completion, cultural inclusion and improved viewing experience.

Does qualitative research usually have a specific hypothesis?

no

What intentional properties does qualitative research give to data?

meaning

what is ontology?

views on human reality

What is strong realism?

the school of thought that there is one true reality - used in quantitative research

What is strong relativism?

peoples realities differ due to perception - qualitative research

What is epistemology?

The study of knowledge (how we know what we know)

What is positivism?

used in Quantitative research. Knowledge and meaning is waiting to be discovered and is true until disproven

What is social constructionism?

Used in qualitative research. Knowledge is being generated by trying to explain the human world 

Which interview structure is used in qualitative research?

semi-structured - open ended questions - subjective answers - verbal data 

what is a discourse

patterns of language about 'how things are' - not fixed can change 

\
Who studied femininity and drinking culture using focus groups of women in their twenties?

Lyons and Willott (2008)

Which studies started modern ethics talks?

Stanford prison study - Harm 

\
Milgram electric shock studies - deception 

What are ethics committiees used as?

a check point for being fully prepared

What are the four ethical principles?

Cultural sensitivity, informed consent, protection from harm and confidentiality.

What is reflexivity?

analyzing and critically considering our own role in, and effect on, our research - environment plays a role in how we react to info.

How is sampling different in qualitative research compared to quantitative research?

qualitative research uses snowball sampling and participants must have some common experience.

What are the types of informed consent someone can give?

signed, proxy - signed on behalf of someone, Passive consent (doesn't say no) - used with children 

What is photo elicitation?

photos as interview prompts

What is research led photo elicitation?

the interviewer shows pre-selected photos.

What is participant led photo elicitation?

asking participants to take photos.

What is participatory photo elicitation?

participants lead the study

what is qualitative research

looking for meaning in the world around us using non-numeric data

Qualitative data

* quotes or images
* capturing the original quality of the data
* non-numeric
* primary involves the ‘human experience’

Generating a QUAL research question

1. state the goal
2. define the pop
3. define the setting
4. identify the primary topic
5. be precise enough to be feasible

Qual - Thematic Theme Analysis

* generated by systematic searching within your Qual data
* usually involves a central organizing concept/idea (thematic solar system)
* supported by example quote or images
* is reflexive
* not only the approach to QUAL analysis

two types of interview questions

Closed

* questions imply fixed answer choices

\
Open-ended

* questions invite expansion

Research interview data - Structured and semi structured

Structured interview

* specific (often closed ended) questions → fixed answers → numerical data (QUAN) (database)

\
Semi- structured interviews

* open-ended questions → subjective answers → verbal data (QUAL) (transcription)

One-on-One interviewing

* most common source of QUAL data
* smaller samples = better in QUAL research
* small possible sample = a case study (n=1)
* case studies allow exploration of the one case in depth
* *most* 1-on-1 interview studies have more than one participant

de Visser and Smith (2006): Aim

Three key issues

* relationships between different discourses of masculinity
* health-related behaviour in the performance of masculine identity
* meanings of masculine behaviour and masculine identity of young men

de Visser and Smith (2006): Key concept

“Hegemonic masculinity’ = expected patterns of behaviour among men:

* playing or watching sport
* suppress emotions
* drinking alcohol
* ‘predatory’ sexuality
* interpersonal violence

de Visser and Smith (2006): Purpose

Research questions:

* how do mean come to identify with a particular discourse of masculinity (broad focus)
* what does it feel like for a man to reject hegemonic masculinity and manage an alternative masculine identity (narrow focus)

de Visser and Smith (2006): Participants

Sample = one participant (case study)

* Rahul (pseudonym): 1st year undergrad (19 yrs) studying in London
* Born in the UK (parents Indiana)
* Not ‘rich’ but went to primary school

Research interviews can be:

* structured (diagnostic screening interview)
* unstructured (just having a research topic in mind)
* Semi structured (interview schedule or topic guide)

de Visser and Smith (2006): Method

Semi structured interview about how Rahul spends his free time - prompts about

* drinking
* sexual activity
* exercise and sport

\
Analysis

* made notes on the transcript during systematic re-readings
* clustered potential themes and checked them by re-reading
* entirely focused on what can be learnt from Rahul

de Visser and Smith (2006): Conclusion

* Rahul worked with and against elements of masculinity in creating his identity as different from other men
* provides insights into how hegemonic masculinity might influence health-related behaviours such as drinking

Research interviews

Structured interviews

* closed questions
* very fixed topic and fixed order or questions
* very clear roles - like a being read a questionnaire
* expansion allowed only if pre-defined (branching)

\
Semi-structured interviews

* open ended questions (or probing)
* very open around a topic and question order can vary
* almost equal roles (like seeking view of expert)
* expansion encouraged (on topic)

Focus groups

* applying interview techniques to groups (n=3+)
* a focus group is an informal discussion among selected individuals about specific topics

why use focus groups?

* there are advantages to have interactions between participants. Discuss their experiences with one another (although could be negative)
* if the research topic is about communication styles then a focus group can facilitate that directly
* it can help if the researcher isnt part of the group
* more participants means they are mor likely to be facilitators of new topics

focus group pros

* pre-existing friends can talk about shared experiences
* unknown participants can provide deeper explanation
* a good interviewer steers the balance of talking
* close to a certain type of natural group interaction

focus groups cons

* pre-existing friends can lead to assumptions and tensions
* unknown participants forming new relationships
* who dominates the discussion?
* too many ppl?
* not a natural environment (talking over each other)

ethical principles

1. cultural sensitivity
2. informed consent
3. protection from harm
4. confidentiality

cultural sensitivity

* ethical research challenges ethnocentrism
* ideally allows participants to identify their ethnicities
* QUAL researchers are encouraged to reflect on their own ethnicities (reflexivity)
* liaison with community leaders or community members

cultural sensitivity within interviews

semi-structured interviews are

* often emotive
* often surprising

interviewers always have to

* build rapport
* think on their feet

interviewers sometimes have to

* repair damage
* be more than a neutral listener

informed consent

informing (what exactly is involved)

getting consent

* signed
* proxy
* passive consent

\
in QUAL research might also have to

* seek permission to record the interview or focus group
* explain how the data will be used - quotes
* provide the questions

Deception and Protection from harm

Deception only used when no alternative

* never with children
* never in QUAL research

Deception important in experimental research where reduces the effect

Debriefing

* to disclose any deception
* to offer information about sources of help when relevant

Confidentiality

two important practices

* access to data (only researchers + participants)
* removal of identifiers from transcripts

Dilemmas

* are focus groups ‘internally’ confidential?
* how long do researchers store data?
* can data be reused in other studies?
* do participants ever want to delete data
* quotes with identifiable details

Jones et al (2013)

\
understand the insight of Maori parents, and their children exploring their day-to-day realities, beliefs about asthma management as well as their experiences and challenges in achieving optimum asthma outcomes

using photoelicitation

Kahu and Picton (2022)

using photo elicitation to understand first year student experiences: Student metaphor of life, university and learning

photo-elicitation

photos as interview prompts

three levels of involvement in photo-elicitation

1. researcher led - pre-selected photos as stimuli
2. participant led - taking/collecting and selecting photos
3. participatory - participants directly the focus of the project

forms of sharing the photos

1. limited to use in the interviews
2. in academic publications
3. publicly displayed

Lyons et al (2015)

* participant led media-elicitation
* asked to talk about their facebook profile with an emphasis on photos and materials related to alcohol
* videoed participants and used online screen recording

Lustyik & Smith (2010)

Examines the historical, cultural, and economic structures and discourses that shaped bro’town

Quantitative methods

* surveys
* structured
* repeated measures
* realism
* numeric data
* A/B testing
* central limit theorem

Qualitative methods

* interviews
* themes and discourses
* photo elicitation
* relativism
* focus groups
* media analysis
* non-numeric data

mixed methods

Research in which the investigator collects and analyses data, integrates the findings and draws inferences using both QUAL and QUAN approaches or methods in a single study