PSYC2012

What is the difference between an inquiry and a critical inquiry

An inquiry involves asking questions with the aim of discovering something knew - we do this in everyday life, whereas a critical inquiry is a form of inquiry that involves error detection and self correction - use the scientififc method

What is a research question

A research question is a focus for a critical inquiry and should be braod in that it doesnt need to specifiy details however should be specific enough to guide research

what is a hypothesis

A general claim about the world

what is a prediction

a more precise version of the hypothesis taking into account the details of the context

what is a theory

a set of ideas intended to explain facts or events

what is a variable

anything that varies

what is a constant

something that doesnt vary

what is the dependent variable

the outcome or response variable measured by the researcher

what is the independent variable

a potential cause of the depedent variable, manipulated by the researcher

what is a construct

an ab stract concept used to describe and explain mental processes, behaviours, or traits that cannot be directly observed

what is operationalisation

translate the experience of pain (construct) into a variable that can be analysed

operationalisation refers to the specification of procedures designed to represent a concept

what is measurement?

the assignement of numerals to objects or events accoriding to rules

features of nominal measurement

same vs different (eg Bpsych vs Barts)

features of ordinal meausrement

categorical, same vs different, greater vs less than (hierachy) eg 1st or 2nd year uni

features of interval meausrement

continous data, same vs different, greater vs less than, equal intervals eg temperature

features of ratio measurement

continous data, same as interval measurement but has an inherent 0 (distance, mass)

what is psycometric validity

the appropriateness, usefulness, meaningfulness of test scores and their interpretation

what is face validity

the degree to whihc a psycholigcal assesment appears to measure what it is intending to measure

what is convergent validity

high correlations with other instruments designed to measure the same construct

what is divergent validity

low correlations with other instruments deisgned to measure the same construct

what is criteria validity

the degree to which a test correlates with one or more criteria

what is construct validity

scores or outputs accurately represent the content area they are trying to represent

what is reliability

the degree of stability of measurement outputs across time and contexts

what is internal consistency

the degree of consistency in responses to scales measuring the same construct

what is test-retest reliability

the stability of scores across time - requires data collected on multiple occasions

what is inter-rater reliability

the relation between two or more independent judges of an item, scale, instrument or construct

what is a distrubutiuon?

a set of observations often represented by a frequency table or a histogram

what is central tendency?

what value best represents the centre of the distribution

what is dispressin?

how spread out the observations are

what is the mode?

the score with the highest frequency

what is the median?

the score that divides the distrubtuion into two equal parts

what is the mean?

the sum of scores divided by the number of scores

what is the formula for the median

N+1/2 where N = number of scores eg 150+1/2 = 75.5 -> avergae the 75th and 76th score = 5

why can means misrepresent data?

Because they are more sensitive to extreme values than modes and medians

what is range?

the difference between the largest and smallest score

what is the interquartile range?

the difference between the upper quartile (75%) and the lower quartile (25%) (Q3 - Q1)

how can we capture a variable?

deviation scores - how much a score deviaties from the mean (X - mean)

what is population variance?

the sum of the squared deviation scores divided by the number of scores

what is the standard deviation

the square root of the variance

what is a z score

a standardised score that indicates har far above or below a score is from the mean

Z = (X - deviation score)/ standard deviation

standard distribution skews

what are some properties of the standard normal distrubtution

- mean = 0 and sd = 1

- the total area under the curve is 1

standard normal distrubution

z score formula

standard deviation formula

what is a. population?

all cases with the target characteristic (eg people with chronic pain)

what is a sample?

a sample is a subset of the population (10 people with chronic pain were required from the clinic)

what is a null hypothesis

an assumption that the intervention had no effect/association

- denote by Ho

- we are seeking evidence against our null

what is an alternate hypothesis

when there is an affect or association

what is a p-value

the probability of obtaining the observed results if the null hypothesis is true

- if this probability is small (<0.05) we reject the null

- if this probability is big (>0.05) we obtain the null

what is the sampling distribution of the mean

The sampling distribution of the mean is the distribution of the means from all possible samples we could have obtained

- the mean of all the sample means = the population mean

- distribution of all the sample means = the sampling distribution of the mean

variance of the sampling distrubtuion of the mean

- will be smaller than the population variance becuase a sample will always better estimate the population mean than any other score will

what is the standard error

the standard error is the same as the standard devaition of the sampling distrubtuion of the mean found

what is the central limit theorum

- the shape of the sample distribution of means

- no matter what the shape of the original distribution as N increases the sampling distribution of the mean approximates a normal distribution

z test for a single mean (one sample z test)

- finding where our sample sits on the distribution of hypothetical sample under the null hypothesis

- if we assume the population variance is known we run a one sample z test

- formula = deviation of a sample mean/standard error

one tailed vs two-tailed test

non-directional HA = two tailed

directional HA = one tailed test

what is qualitative analysis

the analysis of non-numeric data (a phenoememn, a subjective experience)

when do we use qualitative analysis?

- when the research question demands it

- when we want to evaluate the process of implementing an intervention or to examine the experience of the people experiencing the intervention

when should i use qualitative analysis

usually conducted on its own or as part of a triangulation of research known as mixed methods research

- tends to be conducted in naturalistic settings rather than experimental

what is the philosiphical division in research methods

qualitative and quantitative methods of research have a history of philosophical division between them. qualitative methodologists have often labelled quantitative methodologists as "positivist" and themselves as "constructivists"

what is inductive reasoning?

qualitative research tends to be more inductive than deductive meaning it involves observation -> conclusion, where as decutive research has hypotheses-> data collection and analyses -> conclusion on hypothesis

what are features of qualitative research?

goals = aim to understand phenomena in rich detail

sampling = small, non random sample

variables = examine variables holistically

analysis = search for patterns and themes

less concerned with generalisability

build theory as you go

what are some limitations of qualitative research

- soft, because its not mathematical

- relies on the skills of the research

- high susceptibility to social desirability and confirmation bias

- methodology is less well understood

- less rigour

what is data saturation

continuing collecting data until no new information is being provided by participants

types of qualitative data collection

structured interviews, semi structured interviews, in depth interview, focus groups, observational methods

what is a structured interview

- a set of questions (around 20) asked in the same order and same way to each partipant

what is a semi-structured interview

- around 6-8 questions that vary based on the partipants response

what is an unstructured interview

around 1-3 question areas, an open statement

what is the role of the interviewer

to be objective (behave consistently and authentically) and interactive (acknowledge own subjectivity and interact in an interactive process

where to interviwew

hospital, in persons home, telephone

steps for interview process

preperation, beginning interview, warm up questions, interview questions, ending the interview

what is a focus group?

A focus group is a group of around 6-10 people who freely talk, guided by a facilitator on the themes considered important to the investigation

- partiapnts are selcted from a target group whose opions and ideas are important to the researcher

- may be selected to have variety

- usually recorded, researcher takes notes

- aim to promote confidentiality, freedom of expression, non judgement

what are some limitations of quantiative research

- ignores nuances and complexities of a construct

- doesnt say what aspects of the intervention are effective

- by treating the group as a homogenous group, overlooks individual and organsiational factors of the construct that cant be captured through scores alone

an example of a qualitative research question

How do healthcare workers experience and perceive the impact of an app-based mindfulness intervention on their burnout and overall well-being?

- acknowledges the parts of the intervention and the experience of burnout

- shows the features of the intervention that are sucessful

- state what type of data collection you're using

what is reflexivity in qualitative research?

a recognition that neutrality can never fully be attained and that research is influenced by the researcher

a set of continuous, collaborative and multi-faceted practices through which researchers self-consciously critique and appraise how their subjectivity and context influences the research process

what is the difference between a z-test for a single mean and a t-test

a z-test = comparing the mean of a single sample to a known value when you know the population variance.

A t-test is when you don't know the variance

- use of degrees of freedom estimates

what are biased and unbiased estimators?

the sample mean is an unbiased estimator of the population mean, the sample variance is a biased estimator of the population variance

what are degrees of freedom?

the number of observations minus the number of things being estimated

- N observations used to estimate one mean

what is the formula for the estimation of population variance

when should you do a z test vs a test

z test = when the population standard deviation is known

t test = when the population standard deviation is not known (estimated)

how to find estimated standard deviation

1. find sums of squared deviations

2. square root of the sums of squares divided by the degrees of freedom

what is the formula for standard error

estimated standard dviation/ square root of n

what is the t test formula

sample mean - mean/standard error

how to write a statistical conclusion

mean pain interference scores of a sample of people who completed a pain management intervetnion (M = ?, SD = ?) were signficantly lower than the normative mean for pain interference (M=7), t(9) = -2.68, p = 0.013

what id the alternative hypotheiss is non directional?

doesn't change our conclusion, still reject the null hypothesis

what is standard error?

standard error is how much on average we expect each sample mean to vary from another sample mean of the same sample size

what is the difference between a point estimate and an intervale estimate

a point estimate = sample mean

interval estimate = sample mean +/- errpr

what is a confidence interval?

sample mean +/- 2 standard errors

- usually 95%, 95% correspendods to a two tailed signficance test with alpha=.05

- sample mean +/1 (crititcal t (the value that cuts of .o5 x standard error)

what is a related or paired samples t-test

the data points are paired because they come from the same sample measured under the same conditions at two different points in time. (pre and post intervention)

- same formula except you use difference scores

X1 - X2 - find the diffrences mean and the difference sums of squares

what happens if you swap how you define the difference scores

same variability, variacance, standard deviation, standard error will be the same, p value will be the same whetehr you do X2-X1 or X2-X1

what is a matched sample?

two samples from which each individual in one sample is matched to an individual in another sample

what are the advantages of a repeated measures design

reduces error variance by reducing indiviidual differences

each person acts as their own control

what are the disadvantages of a repeated measures design

carry over effects, not always possible

what is within-subjects counterbalacing

each partipant tries the drug in an ABBA order

- drug followed by placebo, then placebo followed by drug

- if you have two or more treatments in a within subjects design you have to consider order effects

what is a type 1 error?

rejecting the null hypothesis when it is true (alpha)

what is a type 2 error

retaining the null hypothesis when it is false (Beta)

what is power

1 - beta (probability of rejecting null when it is false)

correct decision

retaining null when it is true = 1 - alpha

what is an independent samples t-test

used to examine whether there is a difference, on average, in scores between two participant groups

what assumptions do we need to make about a dataset?

1. the two groups are independent and randomly sampled

2. the dependent variable is meausred on an interval scale

3. the dependent variable is normally distrubuted - if groups have equal n not much of a problem

4. there is homogeneity of vairnace in the two groups - only a problem when n is not equal between groups