You could do a double blind procedure to make the result more accurate, so that the research does not have less influence on the evidence they take.
Experiments are used to establish a causal relationship. A form of identifying the relationship is by using correlation. The correlation is one of the most common and useful ways of measuring the relationship between two variables. These variables already occur in the group or population and are not controlled by the experimenter. There are three different types of correlation, each having a statistical measure of two or more random variables, this being the correlation coefficient. There are also two ways in which correlations can be measured, either by use of a scatter graph or by using a statistical technique.
The first type is ‘positive correlation’. This is when one variable increases, so does another. A perfect positive correlation has a value of 1. Another is ‘negative correlation’. This is when one variable increases, the levels of another decreases. A negative correlation has the value of -1. Just because a negative correlation is -1 it is still as important as positive correlation. The final is zero order correlation. This is when the two variables have correlation coefficient value of 0, indicating that there is no relationship between the variables.
An advantage of using correlation research is that you have the ability to prove a positive or negative correlation between the two variables. If you know information about the two variables then you can make predictions about them. Also it can be time and cost effective because it can be used as preliminary research tool. However, a disadvantage to this method is that it does not allow you to come to have any conclusions about cause and effect. There also can be ethical issues when using people’s data as you have not asked their permission.
You can make the ethical issues with using correlation research better by getting consent form the people whose data you wish to use.
The observational method is a standardized approach and consists of planned watching, recording and analysing observed behaviour as it happens within some setting. There are two types of observational methods. These are the naturalistic and controlled observation.
The naturalistic observation observes the participants in a natural environment. The observer takes detailed and accurate notes and recordings. An advantage of using this method is that the observer does not interfere with the environment in any way which gives a more realistic and accurate result. It is also high in ecological validity as it can be easily repeated and can generate clear results about how often behaviour occurs. Disadvantages with the naturalistic observation it can have high demand characteristics and can be difficult to determine the exact cause of behaviour and the observer cannot control other variables that may take place.
You could use the single blind procedure or the double blind procedure to make this method better and you could also use this in the controlled observation.
Within the controlled observation the researcher can control the variables, which also may take place within a laboratory. This is because the variables have been manipulated and is high in control. Essentially there is more control so observations are more accurate and they are easily replicated. In most cases if the observations are being taken in a laboratory then it is easier to avoid problems of consent as the participants know they are being observed. This is known as an overt observation. However, demand characteristics may have a major affect on the observations results. This type of observation will be low in ecological validity compared to the naturalistic observation and cannot have control over the cause and effect.
Case studies are in depth, detailed investigations of an individual, small group, event or community. The information gathered is from a range of sources and by using several different methods, these may be observations or interviews for example. The methods used took place over a long period of time. The information gathered can be analysed using different theories. The case study method often involves simply observing what happens to an individual or small group, which allows the researcher to investigate a topic in far more detail than if it was to be tested on a large group of participants. The information gathered is organized to represent the individual’s thoughts, emotions, experiences and abilities.
Advantages of using the case study method are it provides you with very detailed information and insight for further research. Although it has low reliability as it cannot be repeated and the results cannot be generalised to a wider population. The researcher may also be bias as they may have their own personal feelings that may influence the case study. It is also very time consuming which can become very expensive.
The researcher would have to not know exactly what he was doing the case study on so that their own personal feelings never got in the way of the evidence.
Questionnaires consist of a set of questions usually in a written form used to collect information about a topic or subject. Questionnaires can contain both open questions and closed questions. Closed questions have a range of answers which the participants must select one from the list. Open questions invite the participant to provide their own answer, which can be as detailed as the participants like. Questionnaires need certain rules to ensure it is valid and reliable. It needs to be easy to analyse, as objective and unbiased as possible and the questions be clear so the participant understands what’s being asked. Questions are usually set out in a certain sequence; generally with the easier questions first and more sensitive questions till later once the participants are feeling more relaxed. Questionnaires are often able to study large groups of people easily and quickly, which examines a large number of variables. Questionnaires can be distributed in many ways, by email, over the phone, face to face or through the post.
Advantages of using questionnaires are that they are accurate and the answers you receive are straight to the point. They are time and cost effective and can reach a large sample of people. However there are many disadvantages to using this method. Participants may not want to give information if it too personal and also may have a low validity as participants may feel they are being forced to make a decision, which can cause participants to not answer the questions properly. The questionnaire method can also have demand characteristics.
To make the questionnaire better you should keep the questions short and simple and do not have leading questions.
Design a study to investigate whether people generate more ideas when they work alone or when they work in a group. (AC 3.3, 2.3, 3.4, 3.5, 2.4 3.6, 2.5, 3.7, 3.8)
Psychologists want to know if Access to HE students generates more ideas working on their own or in groups of 6.
“Participants who work in groups will generate more ideas that participant working on their own”.
A null hypothesis predict that the above statement is not true and that the will be no difference between whether groups or individuals create more ideas.
“There will be no difference in the ideas created by groups of 6 and individuals”
I think the right experiment to use for the above test would be the laboratory experiment; the reason for this is that with the laboratory experiment the researcher would have full control over the independent variable (IV) and the dependant variable (DV). This gives the cause and effect, which is what the researcher wants. The IV in this study is people working alone and people working in groups and the DV is whether people can generate more ideas if working alone or in groups. When carrying out the laboratory experiment the researcher needs to attempt to control the extraneous variables (EV). In this study the EV’s could be the time of day or the noise levels in the room. If the researcher does not have control over these it could affect the DV. However, the possibility is that one of the EV’s is not controlled. This is called a confounding variable, which has an unintended effect on the DV. A confounding variable is thought to be the biggest problem in research as it leads to lack of certainty in being able to determine cause and effect. This could be a source of bias in this study. Within this study (lab experiment) you need to make sure you have control over the noise, the temperature and what the individuals and group participants have drank/eaten to ensure that the experiment is not bias.
There are other types of bias and they are called demand characteristic, this is when a participant alters their behaviour in one of two ways. The first is the Social Desirability effect, this is where people try and do what they think the researcher wants them to do and the second is the Screw You effect. This is where the participants alter their behaviour and go against the hypothesis. One more form of bias is the Hawthorne effect, this is where participants are trying harder and being more positive simply because they are aware they are being studied and this is often an unconscious process. All of these sources of bias lead to lower validity. There are two more sources of bias. The first is Researcher or Experimenter bias. This is where the researcher expectations can influence how they design their study and how they respond to their participants and their expectations could also influence how they interpret the results. The other source of bias is Interviewer effects. Here the interviewer may only ask questions they are interested in or they could ask leading questions. The way the interviewer presents themselves, i.e. how they are dressed, appearance, gender or tone of voice may influence how the participants answer the questions asked.
To control demand characteristics we can use a single blind procedure. This is where participants remain unaware what the study is about. I would use this procedure in the study as I believe it will provide the researcher with the best results. This would remove demand characteristics as they would not know what the researcher was looking for. The double blind procedure is where both participants and the researcher are unaware of the nature of the study. This controls the experimenter bias and interviewer effects.
Sampling techniques refer to the way in which groups of participants are chosen and samples are the group of participants that are involved in a psychologists study. It is very important in how the participants are selected for the studies, as psychologists are always trying to gain a representative sample. Researchers look for a group of people who share a set of characteristics, for e.g. Retired females in Worcestershire. This is called a Target Population. A representative sample (group of people) is then taken from the target population, as the target population is usually too big to use as a sample.
There are 3 different types of sampling techniques that can be used by psychologists. The first is Random sampling. This is when every person who is in a target population has an equal chance of being selected. It is important to have the names of the participants who are members of the target population so selecting a sample is random. The second technique is Opportunity sampling. This is a non random method of sampling and is the most convenient. This involves the researcher selecting anyone who is available. The final technique is Volunteer (self selecting) sampling. This also a non random method and involves participants selecting themselves to take part in a study and usually involves responding to an advertisement. For the study I would use random sampling as it removes bias and would make the experiment more effective.
When conducting a psychological study you must always take into consideration the ethical implications of whatever is being done. All psychologists whether you are a student or a professional have to stick to a strict set of guidelines. There are 8 principles, the first being informed consent which is where investigators must get the informed consent of the participants this is sometimes very difficult if you are try to remove demand characteristics and are conducting a single blind procedure. The second is deception; psychologists must avoid deceiving participants about the nature of the research in any way. This is also very difficult to achieve if the researcher wants to remove demand characteristics, psychologists can check if the deception is justified by consulting other colleagues and similar participants. Debriefing is informing the participants of the nature of the research and the findings, the psychologists should be prepared to discuss the procedure; claims have been made that the use of psychological debriefing may prevent the onset of more long term psychological problems (Hodgkinson and Stewart, 1991).
The fourth is the right to withdraw from any study the researcher is conducting at any moment without penalty and the participant can request that the data that has been recorded to be destroyed in front of them. This is a problem when doing the field experiment as the participants does not know that they are part of a study or that data is being taken. Confidentiality is law in 1984 it was put in the data protection act. This means that participants have the right to expect that the information they give remains confidential and that they remain anonymous.
Psychologists have the obligation to offer advice if they identify and physical or psychological problems they have to provide information on how the participants can get further support, they also share the responsibility to maintain a high level of ethical defensibility in their own research and the research of their colleagues. Observational research is when covert observation is needed to collect data there are problems of informed consent, deception and debriefing. This research the natural experiment is only allowed to be use if the research is deemed useful and is only allowed to take place where people would usually expect to be watched. There are many areas of human life that cannot be studied using the experimental methods because it would be too unethical.
A psychologist conducted a study into whether people recall more words when they learn the material in silence than when they learn the word while listening to loud music.
The psychologist found that the probability of the result being due to change is less than or equal to 5%. So according to the hypotheses the change in the noise within the learning environment with have affect on the amount of words the participants remember. Although there is a significant difference in the data this may be due to other variables which have not been controlled.
The psychologists used descriptive statistics. Descriptive statistics help to describe, show or summarise data that they had collected from the test. However, it does not allow you to make conclusions beyond the data that has been tested or make any conclusions regarding any hypothesis that have been made. They found the mean number of word recorded so that they did not just have a load of number that would be hard to interpret. Descriptive data is very useful it helps to put the data down in a way which other people can understand.
The psychologist used inferential statistics to make inferences from the data in order to make conclusions that go beyond the data. The data can then be used to make assumptions about the wider population and can be used to make predictions about the future.
There are two statistical tests that can be performed to analyse data recorded from a test they are parametric and non- parametric. The function of both tests are exactly the same, they discover the probability that the results of the experiment occurred by chance. The difference between the two tests is the way in which they are calculated.
The non-parametric test was used in this study as the majority of tests involving data that can be put in order are done in this way it was used to test the null hypothesis against the alternative hypothesis. This could add more power to this study by repeating with the same people under the same conditions and comparing the results. You could also use a parametric test so that you can look at the effect of the two or more of the extraneous variables. An example of a non – parametric test is the Wilcoxon Mann – Whitney test.
To use a parametric test there are 3 criteria that needs to be met the raw scores must be measured on an interval or ratio scale, scores must be normally distributed and the variances of the two samples are not significantly different. Parametric test are seen as more powerful than non – parametric ones as they make more use of the data that has been collected, also some parametric tests can allow you to look at the effect of two or more variables.
Statistical significance is a mathematic tool that is used to determine whether the result of an experiment is due to the relationship between specific factors or due to chance.
