Key Science Skills

• Aim


  A statement outlining the purpose of the investigation. Helps focus the research. Should NOT have any result predictions included.
• Aim


  • The aim of this investigation is to compare the differences in the amount of sleep obtained by adolescents and elderly people.
  • The aim of this experiment is to assess the effects of practice on learning.
• Hypothesis


  A research hypothesis is a testable prediction of the relationship between two or more variables. It should be written as a single sentence statement.
• Hypothesis


  • It is hypothesised that adolescent males who sleep for less than six hours a night will be more likely to have lower memory abilities, as measured by scores on a comprehension test, than adolescent males who sleep for six or more hours a night.
• Independent Variable (IV)


  The variable that is manipulated in order to see the effects it has on the dependent variable.
• Dependent Variable (DV)


  The variable that is then measured, to see if it was affected by a change in the independent variable. That is, it is dependent (reliant upon) on the independent variable.
• Operationalising Variables


  Defining how the IV and DV will be manipulated or measured. Being specific!
• Operationalising Variables


  • Intelligence - a score on a standardised intelligence test
  • Memory - score on a test of free recall
  • Physical Attraction - the number of times someone touches another person
• Controlled Variables


  Variables that are considered to have an effect on the dependent variable in an experiment so they need to be held constant. By controlling them, we are removing their potential to affect the experiment.
• Population


  An entire group of research interest from which a sample is drawn and to which the researcher will seek to generalise (apply) the results of their investigation.
• Sample


  A subset or part of the population that is selected for research purposes.
• Generally, as the sample size increases, the characteristics of the sample tend to more closely reflect the population. Larger samples also tend to minimise the likelihood of an unexpected sampling error.
• There is nothing wrong with conducting a well-planned small investigation with a small sample size. Having a small sample size does not mean your sample is not representative.
• Random Sampling


  Ensures every member of the population of research interest has an equal chance of being selected to be part of the sample. Lottery type system (easiest to do electronically - random number generator). Advantage: with a large sample is highly representative of the population. Limitation: It can be difficult to obtain a complete list of the target population.
• Stratified Sampling


  The process of selecting a sample from a population comprised of various subgroups in such a way that each subgroup is represented. It involves dividing the population to be sampled into different subgroups (called strata) then selecting a sample from each subgroup (called stratum) in the same proportions that they occur in the population of interest. This is only relevant if there is a characteristic which may significantly affect the results.
• Stratified Sampling Advantage


  Can be combined with random sampling to provide a random selection from each strata to ensure the highest degree of representation.
• Stratified Sampling Limitation


  It can also be difficult to obtain a complete list of the target population and is very time consuming.
• Control Group


  The group exposed to the control condition, where the Independent variable is absent.
• Experimental Group


  The group or groups exposed to the experimental condition(s), where the IV is present.
• Random Allocation


  The best way to divide the sample into the control and experimental groups. A technique that ensures that every member of the sample has an equal chance of being assigned to either group.
• Experiments


  An experimental investigation of the relationship between an IV and a DV. Requires control and experimental groups. Control Group: is not exposed to the IV under investigation. Provides a baseline for comparison. Experimental Group(s): is exposed to the IV under investigation. Can have multiple. Random Allocation is used to randomly split the sample into the two groups.
• Between Subjects Design


  Each participant is randomly allocated to either the control or experimental group(s) and provides one score for data analysis. Advantages: Efficient and cost effective. Limitations: Participant differences (variables) can affect the results, especially if there is a small sample size.
• Within Subjects Design


  Each participant is in both the experimental and control groups. Advantages: Eliminates participant differences between the control and experimental groups, as the same participants are in both conditions. Limitations: Order effects may occur, due to the order in which participants partake in either the control or experimental conditions.
• Mixed Design


  Combines features of both a between subjects and within subjects design. This can be present in many forms, for example there may be two IV's being measured at once. Or there may be a comparison of a pre and post test. Advantages: Can make the most of the strengths of both experimental designs without sacrificing anything. Limitations: Not always relevant.
• Laboratory Experiment


  Stricter control of variables. Not always realistic.
• Field Experiment


  Occur naturally and 'real world'. Experimenter can't easily / ethically manipulate the variables.
• Advantages of Experiments


  • The IV can be manipulated under controlled conditions in order to observe the effect on the DV. Possible to test cause-effect relationships. Experiments can be replicated many time to improve reliability and validity.
• Limitations of Experiments


  • Can't test all variables in a lab e.g. grief, love, hate. Not always relevant to 'real life'. Can't always control every variable.
• Correlational Studies


  Used to investigate the relationship that exists between variables without any control over the setting in which the relationship occurs or any manipulation by the researcher. Relationships can be between any variables that can be measured e.g. behaviours, mental processes, physical characteristics, objects, events. No IV's, DV's, or groups.
• Positive Correlation


  The two variables change 'vary' in the same direction. As one variable increases, the other tends to also increase.
• Negative Correlation

  The two variables change 'vary' in the opposite directions. As one variable increases the other tends to decrease.
• Zero Correlation


  There is no relationship between the two variables.
• The Danger of Mixing up Causality & Correlation
• Advantages of Correlational Studies

  • Can be used to make insightful predictions. Can be used to identify relevant and important factors for further investigation. 'Real World' -> possibly more realistic. Identify trends & patterns.
• Limitations of Correlational Studies

  • Can't draw firm conclusions. Difficult to control unwanted variables.
• Self-Reports

  For some investigations it may be more appropriate to ask people about their thoughts, feelings or behaviour. A self-report is a participant's answers to questions presented by the researcher. Answers may be spoken or in writing. Most commonly used self-report methods are interviews (which are usually completed orally – spoken) and questionnaires (which are usually completed in writing). Sometimes a focus group is used - typically 8 to 12 individuals, who share characteristics and are selected to discuss a topic of which they have personal experience.
• Advantages of Self-Reports


  • Useful for measuring behaviours/characteristics that cannot be easily observed. Questionnaires are easy to administer, cost and time effective way to collect data from a large group in a short period of time, easy to compare participant responses and replicate the research, especially when fixed response questions are used. Use of questionnaires can provide anonymity when collecting data about sensitive topics. Unstructured and semi-structured interviews and focus groups can provide rich information.
• Limitations of Self-Reports


  • Assumption is that people are self-aware, can reliably recall or communicate information about how they think, feel and behave, and are willing to answer all questions honestly. Social desirability effect - participants may intentionally give false or misleading answers to create a favourable impression of themselves, by presenting attitudes or beliefs which encourage others to see them in a positive way. The presence of an interviewer or other focus group participants can also influence responses, especially about personal topics. Lack of confidentiality in focus groups.
• Observational Studies


  An observational study involves collection of data by carefully watching and recording behaviour as it occurs without any intervention or manipulation of the behaviour being observed. The behaviour must be clearly visible and easily recorded. Individuals are trained to record the behaviour without personal interpretation. An observational study can reveal a relationship between two variables but cannot establish cause and effect as it is not a controlled experiment with a manipulated IV etc.
• Advantages of Observational Studies

  • Researchers can watch and record spontaneous, everyday behaviour without the need for any manipulation or intervention. Researchers are likely to gain more accurate information. Can study behaviours that may be unethical or impractical to study in a laboratory setting (e.g. impact of early childhood deprivation).