Week 2/3 Flashcards
2 branches of statistics
Descriptive statistics - Organise, summarise, and communicate numerical information
Inferential statistics - Use representative sample data to draw conclusions about a population
Population
a collection of all possible members of a defined group
Could be any size
Sample
A set of observations drawn from a subset of the population of interest
A portion of the population
Sample results are used to estimate the population results
Operationalisation
Refers to the logical connection between the measure and the theoretical construct, or to the process by which we try to derive a measure from a theoretical construct.
Starting off with a vague concept and narrowing it down to come up with a precise way to measure it
Psychological measurement examples
Examples – age, intelligence, memory for an event, happiness levels, how often someone drinks alcohol
Theoretical construct
A thing you’re trying to take a measurement of
e.g. age, opinions, motives for drinking alcohol
Measure
Refers to the method or the tool that you use to make your observations
Variable
What we end up with when we apply our measure to something in the world. That is, variables are the actual “data” that we end up with in our data sets.
Types of variables - Continuous
Can take on a full range of values (usually decimals)
How tall are you?
Types of variables - discrete
Variables that can only take on specific values
e.g. Number of students
Can assign discrete values to things we’d normally consider words.
e.g. Political party
Classification of variables - Discrete
Nominal: category or name, frequency of belonging to a category – e.g., handedness
Ordinal: ranking of data; clear order to data but distance between points may vary – e.g., place in a race, 1st, 2nd, 3rd place etc
Classification of variables - Continuous
Interval: used with numbers that are equally spaced; Order to data points, fixed distance between points and negative values – e.g., temperature, 1º is always the same, negative temperatures possible
Ratio: like interval, order to data points, fixed distance between points, but has a meaningful 0 point (absence of the thing you are measuring); no negative values – e.g., height, always measured in cm, no negative heights
Generally described as scale variables
Examples of variables
Nominal: name of biscuit
Ordinal: ranking of favourite biscuits
Interval: temperature of biscuits
Ratio: how many biscuits are left?
Likert scales
(1) Strongly disagree
(2) Disagree
(3) Neither agree nor disagree
(4) Agree
(5) Strongly agree
Independent variables
For a true experiment: must be manipulated – meaning you changed it
Generally dichotomous variables (nominal) like experimental group versus control group
Variable you manipulate or categorise
For quasi experiment: used naturally occurring groups, like age; year of study
Still dichotomous, but you didn’t assign the group
when IVs are categorical, the groups are called levels
If political party is an IV, levels could be Conservative or Labour
+Dependant variables
The outcome information, what you measured in the study to find differences/changes based on the IV
Generally, these are interval/ratio variables, but you can use nominal ones too
Independent/dependent variables examples
Independent variable – Whether participants have 1 or 3 drinks
e.g. Group A – 1 drink
Group B – 3 drinks
Dependent variable – Participants’ reaction times on a driving simulator after 1 or 3 drinks
e.g. reaction time (ms)
Test-retest reliability
This relates to consistency over time.
If we repeat the measurement at a later date do we get the same answer
Inter-rater reliability
This relates to consistency across people. If someone else repeats the measurement (e.g., someone else rates my intelligence) will they produce the same answer?
Parallel forms reliability
This relates to consistency across theoretically-equivalent measurements. If I use a different set of bathroom scales to measure my weight does it give the same answer?
Internal consistency reliability
If a measurement is constructed from lots of different parts that perform similar functions (e.g., a personality questionnaire result is added up across several questions) do the individual parts tend to give similar answers.
Reliability
A reliable measure is consistent
Measure your height today and then again tomorrow
Standardised tests are supposed to be reliable
Validity
A valid measure is one that measures what it was intended to measure
A measuring tape should accurately measure height
A valid study is one that measures what it was intended to measure
Internal validity
Refers to the extent to which you are able draw the correct conclusions about the causal relationships between variables.
External validity
relates to the generalisability or applicability of your findings.
Construct validity
Does your measurement measure what you think it should?
Ecological validity
can the conclusions be extrapolated to the real world?
Hypothesis testing
Process of drawing conclusions about whether a relationship between variables is supported or not supported by the evidence
Null hypothesis
No effect
Alternative hypothesis
Predict that there will be an effect
Two-tailed hypothesis
predict effects will be found but you don’t specify the direction
e.g. Reaction times will differ between participants drinking one and three alcoholic drinks
One tailed hypothesis
predicts the direction
Participants will respond quicker after drinking one alcoholic drink than after drinking three alcoholic drinks
Experiments
studies in which participants are randomly assigned to a condition or level of one or more independent variables
able to make causal statements
Control the confounding variables
Quasi experiments
we still have an experiment but we can’t randomly assign participants to the IV –e.g., handedness
Between-groups design
Different people complete the tasks, and comparisons are made between groups
Within groups design
The same participants do things more than once, and comparisons are made over time
Correlational studies
Correlational studies do not manipulate either variable
Variables are assessed as they exist
Cannot determine causality
Categorical analysis
Looking at the frequency of occurrence across one or two categorical variables
Involves looking at the frequency at which participants ‘belong’ to particular categories
In the analysis, you look at the observed frequency and see whether this differs from the frequency that you expect to see by random chance
Correlational analysis
Video game playing and aggression are related
No evidence that playing video games causes aggression
Informed consent
researchers describe their research project and obtain participant’s consent to take part in the research based on their understanding of the project’s methods and goals
Whenever children or individuals with impairments are asked to participate, consent from them must be obtained wherever possible, as well as consent from the participant’s parent or guardian (dual consent)
If a participant cannot provide consent or has an impairment in communication or understanding that prevents them being able to consent, then a written consent form signed by a parent or guardian who is in a position to understand the participant’s reaction must be obtained (dual-consent by proxy)
In cases such as this, it is also advisable for the researcher to seek approval from a disinterested advisor who is familiar with ethical issues in research
Deception
deliberately misleading participants about any aspect of the research
In some instances, it would be ok to deceive our participants, acknowledged by the BPS code of conduct
This would be included in the ethics application where one would explain the deception and why its necessary
Deception should be avoided, however in some studies this would be impossible to achieve since lots of psychological processes can be modified by individuals if they’re aware they’re being studied
Debriefing
explaining to participants the nature, results, and conclusions of the research they participated in and correcting any misconceptions
Debriefing occurs after the completion of the study
It is an opportunity for the researcher to deal with issues of withholding information, deception, and any potential harmful effects of participation
The researcher should consider what the most appropriate form of debriefing is given the nature of the research being conducted
Internet research
Individuals conducting research on the internet should consider the potential implications of participation without having fully read the relevant information
Yet another potential problem concerns the researcher’s inability to confirm the identity of online participants:
E.g. if someone checks a box saying “I am over 18” because the research specifically requires that only over-18s can participate, then there is no way of verifying whether this person is actually over 18
A person can easily maintain anonymity by using a pseudonym that cannot be traced back to reveal their identity
The exchange of information in open, public internet forums does not fall under the heading of research that requires informed consent and can be legitimately studied as long as there is no potential harm to participants
When deception is used you have an obligation to debrief your participants, however, debriefing may be more difficult in internet research
Designing Ethical Research and Applying for Ethical Approval
Cost benefit approach – Does the potential of psychological distress or physical harm outweigh the benefits of the study?
Study design – Making sure informed consent is collected, no deception if avoidable, no risk if avoidable, full debriefing
Potential issues and safeguards included – Contact details in case any issues arise, outlining potential issues that could arise in the experiment but reassuring that the researchers are prepared to handle these issues in a safe and ethical way
Role of ethics committee – They are an
independent and objective committee who will look at the ethics application independently and objectively and assess whether or not it is feasible to go ahead
Build time into research process – Make time to write consent forms, info sheets, debrief sheets etc., being available to wait for decision making from ethics committee
Research fraud
occurs when a researcher intentionally produces research which is inaccurate or untruthful
Ethics
a branch of philosophy concerned with the way in which we formulate codes and principles of moral behaviour
Morals v ethics
personally defined, are related to your own character – your moral values or principles – and generally don’t change much (although they sometimes do)
Ethics are related to the system in which we live