research & stats I w1

What is research?

detailed study of a subject in order to discover (new) information or reach a (new) understanding” - Cambridge english dictionary

• getting to an answer of a question

• Putting that information out into the world

Why we do research?

• to understand different phenomena - why it happened, how it happened

Methods for answering questions

• intuition - generate research questions

• Authority - consult existing literature

• Rationalism - use logic to design the study

• Empiricism - collect data & analyse and identify findings

• All above - reconsider the question. Ask a new question

Research process

1. Generate research question

2. Consult existing literature

3. Design research

4. Collect relevant data

5. Analyse and identify the findings

6. Reconsider the question

What influnce does research have?

• political lections and campaigns

• Medicines and vaccines

• Educational curricula

• Adverts on social media

• Transport timetabling

• HR policies

• Online shopping

• Space Travel

• health campaigns

Etc etc

Research - why learn about it?

• We often take research at face value. We must learn about it so we can evaluate:

• look at the quality of the research

• Quality of the evidence

The replication crisis

• many published research cannot be replicated

• Not just psych, cancer research has had the same issue

• Published In 2015, attempt to replicate 100 studies. Only 36% were positive replications when compared to the original studies

Positive replication

finds the same result as original study

Negative replication

find diff results than original study

Why replication difficult?

• original has use of Questionable Research Practices - cut out, change small things, edit methodology for bias

• Bias in publishing problem - file drawer problem, easier to publish ”significant, novel or interesting” findings. More research in drawer than not

• Failure to report sufficient methodological details in papers. Methodology not enough detail. Cant replicate bc they haven’t done things the same way as the researchers did

Replicability

obtaining consistent results across studies aimed at answering the same scientific question, obtaining own data

Open research

• related to replicability

• Making research transparent

• A lot of research funded through taxation - let tax payer see where money goes

• Keep all open so everyone can see what we’Re doing, making research accessible to everyone

• Make repicability easily

Open Research Principles

• REPLICATION,

• OPEN ACCESS,

• PRE-REGISTRATION (before study, make public questions, hypothises and methodology which cant be changed),

• OPEN DATA (let ppl access your data),

• OPEN MATERIALS (making study materials publicly available (access to survey questions, help w replication

Scientific method

• based on existing knowledge and theory

• Generate hypothesis

• Test hypothesis in controlled & systemic ways

• Data collected can be analysed using stats

Quantitative

• measuring in a numerical, objective way

• May have larger groups

• Surveys

• Nomothetic approach (seeking general truths, generalisable knowledge, similar patterns, prediction of behaviour)

• Problem - average individual may not exist!

• Positivism - reality is objective and measurable

• Scientific method

• Can never fully be certain of anything. Lots of evidence doesnt mean is true

Qualitative

• experiences, quality, depth. Often fewer individuals

• Interview methods, analysing drawings

• Idiographic approach (looking at the unique experiences of individuals)

• Problem - may not be useful generalisable

• Constructivism - no objective reality, what we experience is based on what we construct

post-positivism

we don’t know everything and we can’t know everything. All we can do is get the best approximation of reality.

• quant is post-positivist

• To get as close to truth/reality, we need FALSIFIABLE and TESTABLE theories

Paradigms

• fundamental frameworks. Set of things we accept as true, theories and methodological beliefs

• Underlying assumptions, accepted theories methodologies and standards to define what is valid/what isn’t

• Ex: quantum physics - light can be both a wave and a particle - when observing a phenomena, you may gain different results

To consider in research

• objective

• Reliable

• Valid

• Generalisable

No theory can be proven. But best theories are:

• close approximations of truth

• Srvive logical and empirical testing

• Testable and falsifiable. Need to be able to be proven as false

Dependent variables

what we measure. The outcome. Ex: heart rate, flame and height in bunsen burner. The effect of independent variable

Independent variables

that which we manipulate to see results. Ex: smokrs vs non-smoker. Gas in bunsen burner

Hypothesis

Predictive statement regarding an outcome. it can be tested

How accuracy of theory is decided

We have enough evidence to reject a theory.

Or we dont have enough evidence to reject the theory.

Variables

• characteristicc of property that can differ and be measured