Scientific processes
What is the aim of a study?
The aim of a study is a description of what the researchers are investigating and why
For example, “to investigate the effect of SSRIs on symptoms of depression” or “to understand the effect uniforms have on obedience to authority”.
What is a hypothesis?
Studies seek to test a hypothesis. The experimental/alternate hypothesis of a study is a testable prediction of what the researchers expect to happen.
Experimental hypothesis: A prediction that changing the independent variable will cause a change in the dependent variable.
E.g. “That SSRIs will reduce symptoms of depression” or “subjects are more likely to comply when orders are issued by someone wearing a uniform”.
Null hypothesis: A prediction that changing the independent variable will have no effect on the dependent variable.
E.g. “That SSRIs have no effect on symptoms of depression” or “subject conformity will be the same when orders are issued by someone wearing a uniform as when orders are issued by someone not wearing a uniform”
What is sampling?
Researchers use sampling to select participants for their study.
Population: The entire group that the study is supposed to apply to
E.g. all humans, all women, all men, all children, etc.
Sample: A part of the population that is representative of the entire group
E.g. 10,000 humans, 200 women from the USA, children at a certain school
For example, the target population (i.e. who the results apply to) of Asch’s conformity experiments is all humans – but Asch didn’t conduct the experiment on that many people! Instead, Asch recruited 123 males and generalised the findings from this sample to the rest of the population.
What are sampling techniques?
Random sampling: It involves selecting participants from a target population at random – such as by drawing names from a hat or using a computer program to select them. This method means each member of the population has an equal chance of being selected and thus is not subject to any bias
Systematic sampling: It involves selecting participants from a target population by selecting them at pre-set intervals.
For example, selecting every 50th person from a list, or every 7th, or whatever the interval is
Stratified sampling: It involves dividing the population into relevant groups for study, working out what percentage of the population is in each group, and then randomly sampling the population according to these percentages
For example, let’s say 20% of the population is aged 0-18, 50% of the population is aged 19-65, and 30% of the population is aged >65. A stratified sample of 100 participants would randomly select 20x 0-18-year-olds, 50x 19-65-year-olds, and 30x people over 65.
Opportunity sampling: Approaching participants who are available and asking them to take part.
E.g. Approaching people in the street and asking them to complete a questionnaire.
Volunteer sampling: Participants offer to take part (also called self-selected sampling).
E.g. Placing an advert online inviting people to complete a questionnaire.
What are variables?
Independent variable: Something that is changed by researchers in an experiment.
E.g. In Bickman’s study of the effects of uniforms on obedience, the independent variable was the uniform of the person giving orders.
Dependent variable: Something that is measured by researchers in an experiment.
E.g. In Bickman’s study of the effects of uniforms on obedience, the dependent variable was how many people followed the orders.
Extraneous variable: In addition to the variables actually being investigated (independent and dependent), there may be additional (unwanted) variables in the experiment
Confounding variable: Researchers must control for extraneous variables to prevent them from skewing the results and leading to false conclusions
Operationalisation of variables: It is where researchers clearly and measurably define the variables in their study
For example, an experiment on the effects of sleep (independent variable) on anxiety (dependent variable) would need to clearly operationalise each variable. Sleep could be defined by number of hours spent in bed, but anxiety is a bit more abstract and so researchers would need to operationalise (i.e. define) anxiety such that it can be quantified in a measurable and objective way
What is a pilot study?
It is basically a practice run of the proposed research project. Researchers will use a small number of participants and run through the procedure with them
The purpose of this is to identify any problems or areas for improvement in the study design before conducting the research in full. A pilot study may also give an early indication of whether the results will be statistically significant.
For example, if a task is too easy for participants, or it’s too obvious what the real purpose of an experiment is, or questions in a questionnaire are ambiguous, then the results may not be valid. Conducting a pilot study first may save time and money as it enables researchers to identify and address such issues before conducting the full study on thousands of participants