Research Methodologies Research Methods Experiment Lab Case Study Field Natural Open-ended Self Report Interview Questionnaire Close-ended Structured Observation Correlation Semi-structured Naturalistic unstructured Experiment An investigation looking for a causal relationship in which an independent variable is manipulated and is expected to be responsible for changes in the dependent variable. Experiment searches for cause and effect relationship. For example the effect of light levels on concentration. The cause or the independent variable is the level of light. The effect or the dependent variable is the level of concentration. (IV)independent variable: the factor under investigation in an experiment which is manipulated (changed) and is expected to be responsible for changes in the dependent variable. (DV)dependent variable: the factor in an experiment which is measured and is expected to change under the influence of the independent variable. So the IV is manipulated/changed/controlled and the DV is measured. Controlled Experimental Condition and Control Condition Experimental condition: one or more situations in an experiment which represent different levels of IV. For example different levels of light (high light, low light etc) Control Condition: A condition of the experiment where the IV is absent. For example natural daylight. Different experimental conditions are compared to see the effects or an experimental condition maybe compared to a control condition. Experimental Design The way participants are arranged in different levels of IV in an experiment Types of Experimental Design Independent Measure Design Repeated Measure Design A different group of participants is used for each level of IV The same group of participants performs in each level of IV Strengths : no order effects, lower demand characteristics Strengths : lower participant variables, uses fewer participants Weakness : participant variables, more participants needed Weakness : order effects, demand characteristics Match-paired Design Participants are matched into pairs in ways that are important to the study. Twins make perfect match pairs. Strengths : lower participant variables, lower demand characteristics, no order effects Weakness : matching criteria has to be chosen, hard to find a matched sample Demand characteristics: features of the experimental situation which give away the aims. They can cause participants to try to change their behaviour which reduces the validity of the study. Participant variables: individual differences between participants (such as age, personality and intelligence) that could affect their behaviour in a study. Random allocation: a way to reduce the effect of individual differences by randomly allocating participants to each level of the IV. Order effects: practice effect (familiarity) and fatigue effect (boredom) are consequences of participating in a study more than once, e.g. in a repeated measures design. Counterbalancing: it is a technique used to reduce order effects in a repeated measure design. Sub-groups of participants perform conditions of IV in a different order. For e.g. half of the participants perform in order ABC and the other half perform in order CBA. Types of Experiments Types of Experiments Lab Experiment Field Experiment Natural Experiment Lab Experiment is conducted in an artificial surrounding such as a laboratory. It is conducted by manipulating the IV in the normal environment of the participants Study of an existing difference or change. IV is not directly manipulated Strengths: Standardization, control of variables, valid & reliable Strengths: representative behavior, less demand characteristics, ecological validity Strengths: representative behavior, less demand characteristics, real world issues Weakness: harder to control variables, less validity than lab experiment, ethical issues Weakness: changes may not exist naturally, hard to control variables, causal relationship cannot be established Weakness: unrepresentative behavior, higher demand characteristics Self-Report A research method which obtains data by asking participants to provide information about themselves. Questionnaire Questions are presented to participants in written form (paper/online). Questionnaires include closed questions or open questions. Closed questions: questions that have a fixed set of possible answers. These collect quantitative data. Yes/no answers Rating scales List of possible answers (multiple choice) Closed questions are easier to analyze and it is simple to summarize the findings. However, there is no opportunity to expand on answers or give reasons for a particular response. Open questions: questions that ask for descriptive answers in participant’s own words. These collect qualitative data. Open questions are more likely to explore the reasons behind behaviors, emotions. It produces more in-depth, detailed answers. Answers to open questions have to be interpreted and this can be subjective. The problem with questionnaires is that it is easy for participants to ignore them which means the return rate may be very low. Participants may also lie due to social desirability bias (wanting to look more acceptable). Researchers include filler questions among the real questions to hide the real purpose of the study. Filler questions: irrelevant questions put in a self-report test to hide the real aim of the study. Interview A research method using verbal questions asked directly, e.g. face-to-face or on the telephone. Structured interview: the questions asked are the same for every participant and the order is fixed (standardized). Unstructured interview: the questions asked depend on what the participant says, so the questions may be different for each participant. Semi-structured interview: there are some fixed questions to allow for comparison. In addition, it is possible to ask some questions that are specific to individual participants. As with questionnaires, interviewees may lie due to social desirability bias, or because they think they know the aim of the study. When interpreting the answers to an interview, researchers need to be careful not to be subjective instead aim for objectivity. Subjective vs Objective : subjectivity is basing findings on personal viewpoint whereas objectivity is an unbiased external viewpoint. Case Study A case study is a detailed investigation of a single participant or a group of participants. The data collected is detailed and in-depth and may be obtained using a variety of techniques e.g questionnaire, observation etc (triangulation). It is a useful technique for researching developmental changes. A problem with case study is the development of close relationship with the researcher which may lead to subjective findings. Confidentiality and privacy of participant is at risk. Subject attrition is another problem (when participants drop out or die). Observations Observation is a study conducted by watching human or animal participants. Naturalistic Observation vs Controlled Observation: naturalistic observation is conducted by watching the participants’ behaviour in their normal environment without interference from the researchers. controlled observation is conducted by watching the participants’ behaviour in a situation in which the social or physical environment has been manipulated by the researchers. It can be conducted in either the participants’ normal environment or in an artificial situation. A naturalistic observation is more true to real life but the behavior being researched may not exist naturally so a controlled observation may be necessary. Structured vs Unstructured Observation: In an unstructured observation, the observer records the whole range of possible behaviors. In a structured observation, the observer records only a limited range of behaviors defined by behavioral categories. Behavioral categories: Clearly defined activities recorded in an observation. Participant vs Non-participant observer: Participant observer is part of the social setting, whereas a non-participant observer does not become involved in the situation being studied. Covert vs Overt Observer: an overt observer is obvious to the participants whereas, a covert observer is not obvious, e.g. because they are hidden or disguised. If participants are unaware of the observer, study may produce more valid results as this reduces the risk of demand characteristics and social desirability but this raises ethical issues. Correlations A correlational analysis is a technique used to investigate a link between two measured variables. The two defined variables are related but we cannot know whether the change in one variable is responsible for the change in the other variable. (co-variables instead of independent and dependent variables) Positive correlation: the two variables increase together or the change is in the same direction. (direct relation) Negative correlation: increase in one variable is accompanied by a decrease in the other variable. The change is in opposite directions. (inverse elation) Zero correlation: if there is no link between two variables, then we can conclude that there is no relationship or zero correlation. Correlations are useful as they can indicate whether a relationship exists that might be worth pursuing. Correlations are also useful because they enable researchers to explore problems when it is not practically or ethically possible to conduct experiments. Research Process Aim tells you the purpose of the investigation or what the study intends to find. Hypotheses Hypothesis is a testable statement that predicts the relationship of variables. A study can have multiple hypotheses. The main hypothesis in a study is called the alternative hypothesis. Directional (one-tailed) hypothesis: a statement predicting the direction of a relationship between variables, e.g. in an experiment whether the levels of the IV will produce an increase or a decrease in the DV. Non-directional (two-tailed) hypothesis: a hypothesis that predicts that there will be an effect, but not the direction of that effect. Null hypothesis: a testable statement saying that any difference or correlation in the results is due to chance and not due to the variables being studied. Variables Variables are factors that change or can be changed. Operationalisation: the definition of variables so that they can be accurately manipulated, measured or quantified and replicated. An experiment has independent variables and dependent variables as well as extraneous variables that are needed to be controlled by the experimenter. Extraneous Variables: a variable which acts randomly existing in all levels of DV. Extra variables. Any variable other then the IV which may cause an effect in the DV. Extraneous variables should be controlled by the experimenter in order to make sure the experiment is valid and that changes in the DV are caused by the IV only. These are also called confounding variables as they confound, i.e. confuse the results. Researchers may conduct a pilot study (preliminary test of experiment) to find and control extraneous variables. Situational variable: a confounding variable caused by an aspect of the environment e.g light or noise. Controls Keep potential extraneous variables constant It is important to have controls in an experiment to make sure that changes in DV are caused by the IV and not other confounding variables. One way to achieve this is through standardization. Standardization: keeping the procedure for each participant in an experiment exactly the same. Sampling Techniques ways used to obtain the participants for a study from the population. Population: the group, sharing one or more characteristics, from which a sample is drawn. Sample: The sample is the group of people who participate in a study. Opportunity sampling: participants are chosen because they are available, e.g. university students are selected because they are present at the university when the research is taking place. It is a quick and easy way however, an opportunity sample is unlikely to be representative because readily available people will tend to be alike. Volunteer (self-selected) sample: participants are invited to participate, e.g. through advertisements via email or notices. This sampling technique is unlikely to be representative as volunteers have similar characteristics such as having more free time than average. Nevertheless, it is a useful technique when looking for participants who are unusual in some way. As participants come to the researcher, they are more willing and committed. Random sample: all members of the population have an equal chance of being selected. They are selected in a unbiased way, e.g. by taking numbers from a hat. A random sample is more likely to be representative. Data The results from an investigation. This has to be analyzed and simplified for interpretation. Quantitative data: numerical results about the quantity of a psychological measure such as pulse rate or a score on an intelligence test. It is easier to analyze and compare but limits participant’s responses. Qualitative data: descriptive, in-depth results indicating the quality of a psychological characteristic, such as responses to open questions. Allows participants to express themselves but harder to generalize. Data analysis Numerical Analysis of Data Measures of central tendency (averages) Mean Median Mode Measures of spread (dispersion/variation) Standard Deviation Range Mean: average. It is worked out by adding up all the scores in the data set and dividing by the total number of scores. Median: the middle value. To find the median, all the scores in the data set are put in a list from smallest to largest (ranked). The middle one in the list is the median. If there are an even number of participants, so there are two numbers in the middle, these are added together and divided by 2 to find the median. Mode: the most frequent score(s) in a data set. Range: range is the simplest measure of spread and is calculated by subtracting the smallest value from the largest value and adding 1. Standard Deviation: a calculation of the average difference between each score in the data set and the mean. s= Σ(x − x)2 n−1 Graphs Visual illustration of data Bar chart: a graph used for data in separate categories and total or average scores. There are gaps between each bar that is plotted on the graph because the columns are not related in a linear way. The levels of the IV go on the x-axis and the DV goes on the y-axis. Histogram: a graph used to illustrate continuous data, i.e. data measured on a scale rather than in separate categories. It has a bar for each score value, or group of scores, along the x-axis. The y-axis has frequency of each category. Scatter graph: a way to display data from a correlational study. To construct a scatter graph, a dot is marked at the point where an individual’s scores on each variable cross. Sometimes a ‘line of best fit’ is drawn on a scatter graph to show the nature of the correlation. Normal distribution curve: a normal distribution is a ‘bell-shape’ curve which is symmetrical. It has the mode, median and mean together in the centre. Ethical Guidelines a code of conduct that guide psychologists to consider the welfare of participants Ethical issues: problems in research that raise concerns about the welfare of participants. Ethical Guidelines For Human Participants Informed consent: knowing enough about a study to decide whether you want to agree to participate. This, however, makes the aim of the study clear to the participants raising the concern of demand characteristics. In some situations it is not even possible to ask for consent such as in naturalistic observations and field experiments. In such situations, presumptive consent is taken. (the researcher presumes that the participants would agreed to participate) Protection (physical/psychological): participants should not be exposed to any greater physical (e.g. engaging in risky behaviors or receiving injections) or psychological (e.g. embarrassment or stress) risk than they would expect in their day-to-day life. Right to withdraw: : a participant should know that they can remove themselves, and their data, from the study at any time. Deception: Participants should not be deliberately misinformed,i.e. deception should be avoided. When it is essential to deceive participants, they should be told the real aim as soon as possible. Privacy: participants’ emotions and physical space should not be invaded, for example they should not be observed in situations or places where they would not expect to be seen. Confidentiality: participants’ results and personal information should be kept safely and not released to anyone outside the study. Debriefing: provide participants with an explanation at the end of the study that explains fully the aims of the study and ensures that they do not want to withdraw their data. Ethical Guidelines for Animals Replacement: Researchers should consider replacing animal experiments with alternatives, such as videos from previous studies or computer simulations. Species and strain: The chosen species and strain should be the one least likely to suffer pain or distress. Number of animals: Only the minimum number of animals needed to produce valid and reliable results should be used. Pain and distress: Research causing death, disease, injury, physiological or psychological distress or discomfort should be avoided. Reward, deprivation and aversive stimuli: The use of reward should be considered as an alternative to deprivation and alternatives to aversive stimuli should be used where possible. Housing: animals should be housed with enough space to move freely and with sufficient food and water for their health and well-being, both in terms of their biological and ecological needs. Isolation and crowding should be avoided. Anaesthesia, analgesia and euthanasia: Animals should be protected from pain, e.g. relating to surgery using appropriate anaesthesia and analgesia, and killed (euthanize) if suffering lasting pain.