Research Methods

Validity

How true a study or theory is an explanation of behaviour Internal validity: Whether the research was designed ‘well’. Research with high internal validity, must be designed very carefully. Can be lowered through the interference of extraneous variables. Face...

read more

Features of Science

Objectivity When the researcher is not being affected by their own expectations, keeping a distance from it. How to ensure objectivity: Data should be collected systematically under controlled conditions e.g. lab Research method should be fully standardised so less...

read more

Features of a Scientific Report

TITLE: normally phrased as a question. Refers to the aim ABSTRACT: brief summary of aims and hypotheses, previous research, results, methods and conclusion. 150-200 words. Written at the end but on front page INTRODUCTION: includes past research (theory and studies)...

read more

Data Handling and Analysis

Quantitative data Data in numerical form which can be put into categories, or in rank order, or interval data, and is used to make graphs and tables of raw data - e.g. correlations, experiments, closed questions easily summarised into graphs or statistics = identify...

read more

Measures of Central Tendency:

Mode Most common or most frequent value (used with nominal data) + Easy to calculate + Can be used with nominal data - Doesn’t tell us anything except which thing happens most - Multimodel distributions can be uninformative Median Middle number when data is in rank...

read more

Measures of Dispersion or Spread of Data

Range The difference between the highest and lowest values + Easy to calculate - Affected by extreme values Standard Deviation The average distribution that each piece of data is from the mean for the group + Takes each piece of data into account so very sensitive +...

read more

Presentation of Quantitative Data

Bar charts Used to represent data which is divided into categories (discrete data) e.g. yes or no Line graphs Used to represent data in numerical form (continuous data) e.g. the age of a person Histograms Represent continuous data. Bars represent each score rather...

read more

3 Types of Measurement:

Nominal level: category data e.g. yes/no Ordinal level: data that is a score or ranked on a scale e.g. 1st 2nd Interval data: standard unit of measurement e.g. seconds, KG Why are statistical tests important? Tell us the probability of the results being due to chance...

read more

Type I and Type II Errors

The significance level is 5% or 0.05 to provide a good balance between being too strict or lenient about whether the results of research are significant OTHER THAN WHEN GIVEN OTHERWISE. However, 0.05 gives best chance of avoiding these 2 errors Type I – false...

read more

Assessing Which Statistical Test to Choose:

1.) What kind of data do I have? Nominal level (non-parametric): category data e.g. yes/no Ordinal level(non-parametric): data that is a score or ranked e.g. 1st 2nd Interval data (parametric)– standard unit of measurement e.g. seconds, KG Criteria of parametric data...

read more

Write a Debrief

start with ‘dear participant’ thank you for taking part in the study disclose the full aim of the study refer to previous research if given in Q remind pt of right to withdraw data reassure pts of confidentiality (no personal data published) state researchers contact...

read more

Write Standardised Instructions

explain why or how to conduct a pilot study use a methods section (inc subheadings: design, procedure, pts, materials) write a results section (inc table of results, graph, selection of statistical test) evaluate the limitations of a study and make suggestions for...

read more

Ethics

The rights and wrong about how we conduct research, which is governed by ethical guidelines set by BPS (British Psychological Society) Fully informed consent Participants should have knowledge of aims + procedures of research so they can decide if they want to be...

read more

Reliability

A measure of consistency and the ability to repeat experiment and get similar results on another occasion Internal reliability: Whether a measure is consistent within itself when tested – eg a questionnaire generating similar results with all participants. Tested...

read more

Research Methods

Aim: An intention of investigation Hypothesis: A predictive, operationalised statements of expected outcome Null hypothesis: Predicts IV has no effect on DV Alternative hypothesis: Predicts that there will be a significant effect on DV because of the IV Directional...

read more

Types of Variables

Dependent variable (DV) = measured Independent variable (IV) = manipulated Controlled variable (CV) = kept constant Extraneous variable (EV) = anything other than the IV that could affect the DV – individual differences Confounding variable = EVs have that already...

read more

Experiments

Choice of experiment is dependent on: - How much control we have over IV - How much control we have over extraneous variables - Decision between reliability OR validity In an experiment: - One variable is kept constant - Another measured to see if it changes (IV)...

read more

Experimental Design

- Allocating participants to conditions - Independent measures, repeated measures, matched pairs Repeated measures Participants take part in both conditions + Any difference between conditions likely to be due to IV not pts variables + Controls individual differences...

read more

Independent Measures

Divided randomly into 2 groups + each does a different condition of IV + Each pts sees only ½ of study = harder for them to work out aim of study = reduces demand characteristics + Avoids practice & order effects = pts only does 1 condition = cannot be affected by...

read more

Self-report Studies

Questionnaires Self-report method in which a series of answers is given in a written format, either by making a choice/ answer (closed question) or an extended answer (open question) + Collect large amount of data quickly from large sample (compared to techniques e.g....

read more

Observation

Naturalistic observation Observation of behaviour in a natural setting, with no investigator interference + High in ecological validity + Used to generate ideas for experimental research / validate experimental findings - No manipulation of variables = cannot infer...

read more

Types of Sampling Procedures

Event sampling= recording the number of times a certain behaviour occurs in a group Time sampling = recording behaviours in a given time frame e.g. recording every 30 seconds Correlational analysis Statistical analysis based on a relationship between co-variables...

read more