Research + Overview

Topic 1/5

Random sampling

• Every member has equal chance of being chosen.

• Best technique for unbiased.

• Very time-consuming + often impossible.

• Not guaranteed everyone will participate.

Snowball sampling

• Can be used if your population is not easy to contact.

• Can use if it is a sensitive topic.

• May ask someone to tell people in their support groups --> through contacts between participants.

• Not very representative of target population

Volunteer self-selecting

• Volunteer when asked to in response to an advert.

• Quick and relatively easy to do.

• Can reach wide variety of participants. Normally a reward SO more likely to continue

• Not always representative of target population (for those who are more eager to participate)

Opportunity sampling

• Taking the sample from people who are available at the time

• Easy in terms of time and therefore money

• Can produce unrepresentative sample (easy for accidental bias)

• Some may refuse to take part therefore a particular type of person agrees therefore bias

Stratified sampling

• Divide group into characteristics (age, socioeconomic status etc...)

• Mathematically choose even group

• Random sample from each group

Random sampling

Putting names in a hat

Volunteer self-selecting

People volunteer because of an advert

Snowball sampling

People volunteer because of their contacts

Opportunity sampling

Sampling from people available at the time

Stratified sampling

Mathematically choosing equally

Experiment

Investigation in which a hypothesis is scientifically tested. It has an independent and a dependent variable

Primary data

Data collected by the researcher themselves for the purpose of their investigation

Secondary data

Data collected by others

Quantitative data

Data in the form of numbers

• Can be transformed into tables, graphs, charts, percentages, fractions etc

• Can be statistically analysed using descriptive statistics or inferential statistics

Qualitative data

Data in the form of words

Advantages of Primary Data Collection

• Better accuracy

• Resolve specific research issues

• Higher level of control

• Up-to-date information

Disadvantages of Primary Data Collection

• More expensive

• Time-consuming

• Not always possible

Advantages of Secondary Data Collection

• Ease of Access

• Low Cost/Free

• Time-saving

• Larger sample size

• Longitudinal analysis

Disadvantages of Secondary Data Collection

• Not specific to your needs

• Lack of control over data quality

• Bias

• Out of date

Advantages of Primary Data Collection

• Better accuracy

• Up-to-date information

Disadvantages of Primary Data Collection

• More expensive

• Time consuming

• Not always possible

Advantages of Secondary Data Collection

• Ease of Access

• Low Cost/Free

• Larger sample size

Disadvantages of Secondary Data Collection

• Not specific to your needs

• Bias

• Out of date

Examples of Primary Data sources

• Interview

• Surveys (self-administered)

• Case studies

• Diaries/Letters/Memoirs

• (add more from booklet)

Internal reliability

This refers to how consistently a method measures within itself

External reliability

This refers to how consistently a method measures over time

Inter-rater reliability

The degree of agreement among raters

Split-half method

Correlating the results of half the items with the other half

Test-re-test method

Correlating the results of the test on one occasion with another

Internal validity

Refers to the test being used --> are the changes in the DV caused by the IV and NO OTHER FACTORS.

External validity

Relates to issues beyond the investigation --> whether findings will generalise to other populations, locations, contexts, and times than the ones investigated.

Ecological validity

Refers to whether the method measures behaviour that is representative of naturally occurring behaviour.

Face validity

Whether the test appears to measure what it claims to --> does it appear to be suitable to its aims at face value.

Criterion validity

Refers to how well findings predict what happens beyond the research.

Population validity

How representative the sample is in comparison to the general population.

Construct validity

Measure if research is accurately assessing what it's supposed to

Ethical issues

• Confidentiality

• RIght to withdraw

• Informed consent

• Competence

• Protection of participant

• Debrief

• Deception

Confidentiality

When carrying out research, the identities of all people involved should be kept confidential.

Debrief

When carrying out research, ensure you explain to p's what the study was about.

Right to withdraw

P's should be able to pull out of the research at any stage - even at the end then can withdraw their results.

Competence

Psychologist should be aware of the ethical issues when conducting research + ensure these are maintained when conducting research.

Informed consent

People who take part in the research should agree/consent to being involved, understanding what the details of the study are before they take part.

Protection of participant

Research should not cause people involved in any physical or emotional damage.

Deception

Sometimes researchers have to deceive (not fully inform) people they are studying in the pursuit of more valid results and to avoid demand characteristics.

Brief

Explains the basic aim of the research, how long it will take and the right to withdraw + confidentiality.

Standardised instructions

Relate to the task the participant is expected to do but also offers at various intervals the right to withdraw.

Debrief

Outlines the full aims of the investigation and given this info allows the participant to withdraw their results if they wish to.

Descriptive statistics

Used to summarise + present results of an investigation. Needed so the reader can quickly see the overall pattern of the results.

What do you call 'mode, median, mean'?

Central tendency

Types of data

• Primary

• Secondary

• Qualitative

• Quantitative

Levels of data

• Nominal

• Ordinal

• Interval

• Ratio

Nominal

• Named categories

• No true mathematical value

• Basic form of data

• Chi Squared

Ordinal

• Ordered data e.g place in a race

• Understand the relationship between places (1st is better than 2nd)

• No true mathematical value (don’t know how long race was)

• Typically scales

Interval

• The distance between each of the values is exactly the same

• e.g temperature of water

• True mathematical values

• Relationship between data is known e.g -2 → -4 = same distance as 34 → 36

• Can go below 0

Hypothesis

An empirically testable proposition about some fact, behaviour

Design

How participants are allocated to the different groups in an experiment. Types of design include repeated measures, independent groups, and matched pairs designs.

Null hypothesis

States that there is no relationship between the two variables being studied (one variable does not affect the other)

Alternative hypothesis

States that there is a relationship between the two variables being studied (one variable has an effect on the other)

Participants

A person who takes part in an investigation, study, or experiment, such as by performing tasks set by the experimenter or by answering questions set by a researcher.

Independent variable

• What the experimenter controls/manipulates

• The thing that changes between the conditions the participants are placed in

Dependent variable

• The thing that is measured

• The results of the experiment

Operationalising variable

When a variable has been turned into something that can be measured/ made testable

Aim

Gives us an idea of what the researcher is hoping to achieve

To investigate...

Hypothesis

A testable statement made at the beginning of an investigation

'no significant difference'

Null hypothesis

‘a significant difference’

Non-directional (two tailed) hypothesis

‘significantly smaller/bigger/slower/less/more’

Directional (one-tailed) hypothesis

What is a mean?

Arithmetic average of a set of scores

What is a median?

• Central number in a set of scores

• Calculated by putting all scores in numerical order

What is a mode?

Most common score/piece of data

Advantages of mean

Very sensitive- affected by extreme values

Advantages of median

Not affected by extreme scores

Advantages of mode

• Know patterns

• Useful when knowledge about frequency is important

Disadvantages of mean

Can be too sensitive

Disadvantages of median

• Not all scores used

• Not as sensitive as mean

Disadvantages of mode

Rarely useful in small sets of data when there are often several modes therefore unreliable.

Null hypothesis

The hypothesis of no difference

H0

Non-directional/Two-tailed hypothesis

Does not predict the direction of the results, just says there will be a difference

Directional/one-tailed hypothesis

Predicts the direction of the results

Strengths of Quantitative data

Reliable as it is easy to analyse and compare

• Techniques used to collect it are replicable e.g.

  • standardised procedures, correlational analysis

Can highlight trends and patterns which is useful when researchers wish to apply general laws of behaviour

Chi Squared

Inferential statistical test that uses nominal data

What inferential tests would be used with ordinal data?

• SRCC (relationship)

• Mann Whitney U (difference- independent measures)

• Wilcoxon (difference- repeated measures)

What inferential tests would be used with interval data?

• SRCC (relationship)

• Mann Whitney U (difference- independent measures)

• Wilcoxon (difference- repeated measures)

Ratio

• True value of 0

• e.g Height- cannot go into minus numbers

• True mathematical values

• Relationship between data is known

Descriptive statistics

A set of methods used to summarize and describe the main features of a data set.

These methods provide an overview of the data and help identify patterns and relationships

Variance

Measure of dispersion that calculates the average difference between each score in the data set and the mean.

Bigger values indicate greater dispersion

Advantages of variance

Takes into account every score (unlike the range)

Not distorted by extreme scores

Can tell us the dispersion of scores from the mean (so groups of data can be compared)

Disadvantages of variance

Calculation is not as easy as the range

During the calculation, units are squared SO does not use same units as mean

Standard deviation

Calculates the average difference between each score in the data set and the mean

Represents this in the same unit as the mean itself

Bigger values indicate greater dispersion

Advantages of Standard deviation

Shows how much data is clustered around a mean value

It gives a more accurate idea of how the data is distributed

Not as affected by extreme values

Disadvantages of Standard deviation

It doesnt give you the full range of the data

It can be hard to calculate

Only used with data where an independent variable is plotted against the frequency of it

Assumes a normal distribution pattern