Sampling Methods

• Target population can’t be tested, so sampling techniques recruit representative (of target population characteristic) sample; ensuring conclusions validly generalise back to explain target population behaviour, e.g. population validity
• Sample gathered is unrepresentative, an over-/under-representation of a particular participant in sample (sampling bias), e.g. Attitudes towards a no-smoking policy are gathered from participants recruited from an outside office smoking area
• Random Sampling: Every member of target population has equal chance of taking part in research; like names being drawn out of a hat, random sample can be created using computer selection or lottery method
• Random Sampling - Strength: Most representative, unbiased sampling technique of ‘normal’ population; researcher doesn’t influence who is chosen, therefore, results can be generalised to everyone
• Random Sampling - Weakness: Very hard unless you have small population; possible to select unrepresentative sample randomly too, consent is still to be obtained and if some participants refuse sample may end up being unrepresentative
• Opportunity Sampling: Participants selected from those available and Strength: Ethical, no pressure to take part, alternative participants easy to get, and quick (get large samples for reliable results); if population is not listed, it is difficult to access other ways
• Opportunity Sampling - Weakness: Unrepresentative sample was drawn from who is available at time (similar traits, behaviours), researcher may consciously or unconsciously show bias in sample selection, limiting generalisability
• Stratified Sampling: Proportional representation of the target group, e.g. if the target group is 60% male and 40% female our sample will have same proportion of males and females and Strength: Likely to be very representative of target population
• Stratified Sampling - Weakness: Time-consuming and difficult to establish correct proportions from target to sample and if all key features of target population are not identified then sample may be unrepresentative
• Volunteer/Self-selected Sampling: Participants select themselves, e.g. respond to advert and Strength: Well-motivated, likely give useful feedback, less likely to drop out and participants researchers may not normally have access to; easier than a random sample
• Volunteer/Self-selected Sampling - Weakness: Volunteers have high motivation so behave differently to other participants, so not representative and limiting generalisability; demand characteristics want to help