- Created by: Phoebemai901
- Created on: 12-11-19 16:51
What is an Aim?
A specific area of study and what you want to find out
An aim of study should include both the thing being manipulated (independent variable) and the thing being measured (dependent variable)
What is a Hypothesis?
This is a precise testable statement of what you predict will happen in your research
Alternative Hypothesis (Experimental) - Predicts that the IV has an effect on the DV
Directional (1 tailed) PRECISE
Non Directional (2 tailed) EITHER WAY
Null Hypothesis- Predicts that the IV has no effect on the DV
One and Two Tailed Hypothesis
Sometimes a hypothesis predicts the direction in which the reults are expected to go. An example is "studying IMPROVES marks" When a hypothesis predicts the direction of the results it is referred to as a one tailed hypothesis. Results only go in 1 direction
If the hypothesis is simply stating that one factor affects another it is called a two tailed hyothesis. Examples: Anxiety influences performance
What is a variable?
A variable is a measurable characteristic or value that can differ between conditions
Independent Variable (IV)- The variable that the researcher manipulates and which we assume has a direct effect on the DV. (I change the IV)
Dependent Variable (DV)- The variable that is affected by changing the IV. (the result)
Co-Variables- The 2 variables in a correlation.
Operationalising Variables- It is very important to operationalize the variables to be studied otherwise the researcher will not know what they are looking for. This can reduce the validity and reliability of their data.
If a avariable other than the IV produces a chnage in the DV. Results said to be confounded.
unwanted variables are called extraneous variables.
Situational Variables- connected with the research situation E.G. Temperature, Noise Controlled by- standardised procedure (fair testing)/ standardised instructions (what they say)
Participant Variables- connected with the research participant E.G. Age, Gender, IQ Controlled by- Design-repeated measures/independent measures/matched pairs
Experimenter Variables- related to the researcher E.G. Gender, Personality. Controlled by- Keeping the same researcher in all conditions.
Confounding Variable- extraneous variable that hasn't been controlled and will have an affect on the DV.
Repeated measures- One group who carry out both conditions.
Strengths- Less PP's, Less individual differences.
Weakness- More order effects BLT, More demand characteristics
Independent Groups- 2+ groups. Each group carries out one condition. (or control group)
Strengths- Less order effects, Less demand characteristics
Weakness- More PP's, More individual differences.
Matched Pairs- 2 or more groups who are matched to individual differences. Almost identical
Strengths- Less order effects, less demand characteristics, less individual difference
Weakness- Many more PPs needed for matching up.
overcome the disadvantages of repeated measures
Order Effects- These are Boredom, Learning and Tiredness. They are problematic in repeated measure designs. How to overcome them...
- Change to independent measures if suitable.
Demand Characteristics- Features that let the participant guess what the study is about or what is expected of them.
- guessing the purpose of the research and trying to please the researcher by giving the 'right' results.
- guessing the purpose of the research and trying to annoy the researcher by giving thrm the wrong results. screw you effect
- acting unnaturally out of nervousness for fear of being thought 'abnormal'
- acting unnaturally in order to 'look good'
Ways to overcome:
- Single blind procedure- the subject does not know which condition of the experiment they are in
- Deception- to hide the aim of the research but this will create ethical issues
Target Populations- The total group of individuals which the sample might be drawn.
Sampling Frames- A complete list of all the members of the population that we wish to study.
Opportunity sampling- Uses people from target population available at the time and willing to take part based on convenience. E.G. A sample of students coming out of the library.
Strengths: - quick way and easy to choose PP's
Weakness: -May not provide a representative sample, - observer/sample bias
Self-selecting sampling- Volunteer sample. Your PP's come to you through request. E.G. Posters
Strengths:- Ethical. People know what they are signing up for, -quick and easy.
Weakness:- Sample bias on behalf of PP's, -Not usually representative
Random sampling- everyone in the target population has an equal chance of being selected Works best in a smaller target population.
Strengths:- Your sample should represent the target population and eliminate sample bias
Weaknesses:- Very difficult to achieve, -unbalanced sample
Stratified sampling- Researcher identifies the different types of people that make up the target population and works out the proportions needed for the sample to be representative. The pps are then selected randomly from each layer.
Strengths:- should be highly representative (generalise)
Weaknesses:- Time consuming and difficult to get people, -Rarely Used
Systematic sampling- Chooses subjects in a systematic way from the target population like every nth PP on list of names.
Strengths:-should be representative
Weaknesses:- Very difficult to achieve
Quota Sampling: Similar to stratified, proportions of different people in the target popuation are identified and the sample is (not randomly) selected E.G. Opportunity sampling.
Strengths:- Sample should be representative of the target population
Weaknesses:- May be biased, not everyone gets a chance of selection
Snowball sampling: Selecting a sample starting with a small group of respondents and asking them for further contacts. Collection of in depth qualitative data perhaps sensitive topics. Obvious sample frame doesn't exist. Best method is peronal contacts.
Strengths:- Can be used if your population is not easy to contact.
Weaknesses:- Sample bias, -The sample may end up with is a small subgroup of the entire population
Reliability and Validity
Reliability- Replicable in the future and get the same results. Consistent. Standardised Procedures, instructions control EV.
Validity- Applied to real life. Ecological Validity. Variables can effect validity. Best way to measure the variables.
Test-Retest Reliability- The measure is administered to the same group of people twice. If the results on the two tests are similar, we can assume the test is reliable.
Split-Half Reliability- Splitting a test into two halves, and comparing the scores in both halves. If the results in the two halves are similar, we can assume the test is reliable.
Inter-Rater Reliability- If the measure depends upon interpretation of behaviour, we can compare the results from two or more raters. If there is high agreement between the raters, the measure is reliable
Conducting Pilot Studies: The aim of a pilot study is to check the method and to find solutions to any issues. This ensures high reliability and validity.
A pilot study is a small scale trial run of a specific research investigation to test out the planned procedures and identify any flaws and areas for improvements, before time and money are invested in carrying out the main study. It is carried out on a small number of participants to find out whether there are any problems.
In experiments it is important to check:
- The participants can follow the standardised instructions.
- The apparatus and materials are appropriate
- That the dependent variable covers the full range of scores to avoid floor or ceiling effects.
- For any possible missed extraneous variables that need to be controlled
- To see of any part of the procedure leads to demand charcateristics.
- Whether there are any order effects in a repeated measures design
Pilot Studies Part B
In self reports it is important to check:
- That the participants understand the questions and are prepared to answer them
- That closed questions offer suitable options (more options)
- Whether open questions are needed to allow for unexpected responses
- Whether the reporting method is appropriate e.g. if a face to face interview is too intimidating should it be changed to a questionnaire or vise versa.
- A questionnaire or interview should be piloted on people from the appropriate target population.
In observations it is important to check:
- That observers agree on operational definitions of behavioural categories i.e. the behaviour that will measure/operationalize their IV. effects internal.
- Do they need to practice inter-observer reliability
- That the behavioural categories include all the important behaviours or will others need to be added.
- That the behavioural categories do not overlap so reducing the validity
- Whether the participants are affected by the observer or should they be non-disclosed (hidden)
Experiment: Involves the experimenter manipulating one variable (independent) and measuring what effect this has on another variable (dependent). This involves strict control over extraneous variables through a standardised procedure in a controlled environment. An experiment is a primary research method and collects quantitive data.
Advantage: -Possible to test cause and effect, -Increased control and accuracy of measurement means more objectivity, -Replicable, standardised procedure.
Disadvantages:-Total control not always possible, -Artificial and lacks ecological validity, sample bias, demand characteristics, ethical problems
Quasi- Experimenter: Involves a participant being born with a variable the investigator wants to investigate, take advantage of someone's natural manipulation (independent) and the researcher just records the effect on the dependent variable.
Advantage:- high ecological validity, little sample bias, few demand characteristics as articipants are unaware
Disadvantages:- little control so hard to establish cause and effect, cannot replicate, - ethical
Lab controlled- involved strict control over extraneous and confounding variables through a standardized procedure in a controlled environment can be done anywhere not just lab.
Advantages: -possible to test cause and effect. - Increased control and accuracy of measurement means more objectivity, replicable standardized procedure
Disadvantages:- total control not always possible, artificial and lacks ecological validity, sample bias.
Field (Public)- This is where an experiment manipulates the independent variable in a real life setting.
Advantages: -Less sample bias, -Greater ecological validity than lab experiment., -Fewer demand characteristics if participants are unaware.
Disadvantages: - Difficult to replicate, -Lack of control brings problems of extraneous variables, -Difficult to record data accurately, -Ethical problems
Settings Part 2
Online- This is an experiment taht is conducted over the internet. These are widely used within psychology.
Advantages:- You can cheaply collect large amounts of data, -Easier to replicate, -Usually avoids ethical problems of consent.
Disadvantages:- You can have difficulty in verifying the identity of subjects participating in the experiment, -significant distractions may occur during the course of the experiment, -If paying participants to take part there could be issues of reliability and automatically processing the payment over the internet is an anonymous fashion.
Non experimental methods: observations are a non experimental method of investigation. There is no manipulation of variables. Observations are not technically classes as experiments. A researcher will simply observe behavior and look for patterns. We cannot draw cause and effect relationships. Observations are used in psychological research in one of 2 ways a method or a technique
observations as a research technique: this is when observations are used as part of another research method such as a lab study or a field study
Ainsworth's study: 3 to 6 month old babies were brought into a room by parents which they then spoke to a stranger and left the baby with a toy to see how they react a 2 way mirror was used to observe the lab setting experiment
people used an escalator more than stairs so the researcher turned each step into piano keys people then used the stars more as a result
This is where the entire study is an observation, for example going to a playground and observing the behaviour of children. In this example the researchers looking to see how many incidents of aggressive behavior are shown by the children. They might simply observe the children in the playground and record how many aggressive acts are demonstrated. There is no manipulation of variables and no conditions. The experimenter has not controlled the environment, the children do not know that they are in a study. recorded using a tally chart
Depending on the method of observation used the researcher may collect qualitative data, quantitative data or both types.
Qualitative data: no numbers, words
quantitative data: just numbers and stats
Types of observation
An observation can be:
Naturalistic or Controlled
Structured or Unstructured
Participant or non-participant
Overt or Covert
In a naturalistic observation, behaviour is studied in a natural situation where everything has been left as it normally is.
In a controlled observation, some variables are controlled by the researcher, reducing the naturalness of the behaviour being studied. Participants are likely to know that they are being observed and the study may take place in a lab.
Types of observation
Participant- The researcher becomes involved in the everyday life of the participant with (overt) or without (covert) their knowledge.
Non Participant- Research technique whereby the researcher watches the subjects of his or her study, with their knowledge (overt) but without taking an active part in the situation.
Unstructured observation- Researcher records all relevant behaviour but has no system. Behaviour being studied may be unpredictable. Unstructured Observation may be the first step in an investigation. Results may be used to create a coding system for further structured observations. Majority of data collected is qualitative.
Structured Observations- Researcher has a system taht is used to record behaviour. He will use a coding system to tally the number of times a behaviour occurs. Will also use various sampling procedures to decide what to observe and when.
Structured Observation Methods
Coding System- A coding system is when behaviour is operationalised/defined by being broken into different categories. E.G. when studinginfant behaviour a coding system may contain things such as playing with toys, sharing, aggression.
Sampling Procedures- In a continuous observation, observer should record every instance of the behaviour being studied. In practicality there would be too much data to record. There needs to be a systematic method of sampling.
Event Sampling- counting each time a particular behaviour is observed (tally)
Time Sampling- recording data at particular intervals. E.G. what is an individual doing every 30 secs
Validity of observations
+Tend to have high ecological validity, as they involve more natural behaviours. Ecological validity is especially high in covert, naturalistic observations where the participants are unaware that they are being observed.
+What people say they do is often different from what they actually do, Therefore, observations may be more valid than questionnaires for example.
-Ecological validity may be lowered in controlled observations, as they do not take place in a natural environment. Overt observations where the participants know that they are being observed can lead to artificial behaviour from the participants.
-Depending upon the people being observed, there may be a sample bias, meaning that the sample is not representative of all people.. Results may not be generalisable.
-Major issue is the validity of the coding system. E.G. some observations might belong in one or more observations.
-Observer bias- If the observer has an idea about what he expects to happen he may only record data that fits this theory
Reliability of observations
-Often observations can be difficult to replicate, they take place at a specific place and time.
+Reliability can be assessed using inter-observer reliability.
Dealing with validity in observations
- A researcher can assess the validity of his observations by conducting further observations in different settings with varied people so that the results can be more generalisable.
- By using more than one observer, observer bias can be reduced
- Observer bias can also be reduced by using a double blind technique, where the person doing the observing does'nt know the aims of the study
- The validity of a coding system can be assessed through content, construct, concurrent and predictive methods.
Dealing with reliability in observations
- In observational research, the issue is that any observations should be consistent. If they are consistent we would expect two observers to produce the same observations. The extent to which any two or more observers agree is called Inter-observer reliability. This is calculated by correlating the observations of two or more observers. Generally, if there is more than 80% agreement between the observers, the data has inter-observer reliability.
- Reliability can also be increased by training in the use of a coding system through practise.
A technique for systematically describing written, spoken or visual communication. Provides a quantititive data. Many CA involve media, newspapers, magazine, TV, video, movie, internet. CA is also used to analyse new material recorded by researchers
+reduces complex information to numbers to enable comparisons
-Meaning and content may be missed
-Difficult to decide what and how to code.
Self Report Techniques
A self report technique is any method which involves asking a PP about their feelings, attitudes, beliefs etc. They can be interviews and questionairres.
+infer cause and effect
+able to study large samples of people very quickly
+allow PPs to describe their own experiences rather than inferring.
- PPs may lie, can affect reliability
-Socially desirable change answers to look good
-unclear questions, guess answers
Questionnaires and Interviews
Non Experimental technique- Similarly to correlations and observations questionnaires and interviews are non-experimental, meaning that there is no IV and DV. Both questionnaires and interviews are types of self report method. This is because the participant reports their own thoughts and feelings about a particular matter. A questionnaire is where the responses are written dwon by the participant, and an interview is where the participant gives a verbal response which is then recorded by the interviewer.
Interviews and questionnaires can either be used as a technique as part of another type of research study (such as lab study) or it can be used by itself as a research method. When used as a techhnique it may be something that the researcher does at the end of an experiment in order to gain information about the participants experience.
Questionnaires: A questionnaire is a set of questions. It is designed to collect information about a topic or topics.
+You can collect the same information from a large number of people relatively easily.
+You can acess what people think.You can ask people directly instead of guessing
Types of questions
Open Question- The participant can give any answer they wish. Qualitative
Closed Question- There are a set number of response which the participant selects from. Quantitative.
Semantic Differentials- There are a number of responses to a question which often demonstrate a degree of agreement. Quantitative
Likert Scales- The participants makes a mark on a line to express the level of agreement with a particular view. Quantitative
What is a structured interview?
Interview in which the PP's are asked a series of fixed questions with a limited rage of verbal answer options yes/no
+reliable, replicable, fast to complete
-Can't guarantee honesty, cannot infer cause and effect. Less valid due to distortion of restricted answers and closed questions
What is a semi structured interview?
Contains guidance for questions for verbal interview with PP's but phrasing and timing of questions may vary and answers may be open ended
+Large amounts of detail generated, Fairly flexible and sensitive, Fairly reliable and easy to analyse
-Cannot guarantee honesty, Cannot infer cause and effect, Difficult to compare answers
Non-experimental technique- as with the previous research methods we have learned about, this is a non experimental technique.
A case study is an in depth study of one person or a small group of people. It can also refer to the study of an institution (such as a school or hospital) or an event. It uses a range of sources from both the person under investigation, and from their family and friends.
What is a case study?
A case study is technically a type of research method, but more often it is actually a combination of many types of research method. A pure case study would just be a detailed written account of the person, their behaviour and the researchers interpretations. In reality however a researcher might use a lab experiment, a questionnaire, a psychometric test or an observation etc as part of the case study.
Examples of case studies
For example a case study on a person with Alzheimer's disease a researcher might:
-Carry out a structured observation to see what particular behaviour the person shows
-Assess their cognitive ability with a psychometric test
-Test their cordination with a lab experiment.
-Conduct interviews and questionnaires with the friends and relatives of the person.
-Correlate two or more variables such as the person's alertness with the number of hour they sleep.
Strengths of case studies
-Validity- real life, collects qualitative data
-Quality of data- high, one person, detailed
-Gaining an insight and deeper understanding. lots of data, long time.
-Somethings that can only be investigated with a case study
Weaknesses of case study
-Ethics- people aren't always able to give consent
-Reliability- impossible to repeat, cant be generalised
-Subjectivity- involved with their life
-Not easy to analyse. Lots of data
-Practicality- takes up time and money
-Confidentiality- ethics, not nice to call people fake numbers or names for a long time
Dealing with validity in case studies
The validity in case studies will often depend upon the methods being used as part of the study. Therefore the way to deal with validity issues will depend upon the method.
Dealing with reliability in case studies
A major issue with case studies is that the qualitative data often requires interpretation, which can be open to the researcher's own bias. Onre way to overcome this is to use inter-observer reliability. By showing the results to another researcher and comparing the results, we can assess how reliable (consistent) the data is.
The case of Clive Wearing
The conclusions drawn from the HM's case study, can be applied to the case of Clive Wearing. He contracted a viral infection which attacked his brain, damaging the hippocampus and associated areas. Like HM, Wearing lost all ability to transfer memeories from STM to LTM. He only remembers some aspects of his life before the infection. For example, he knows he has children from an earlier marriage, but cannot remember their names. He recognizes his wife Deborah, but whenever he sees her greets her as if it was the first seeing her in a long time.
Like HM, his procedural memory is intact- he had been a conductor and pianist, working for the BBC and can still conduct a choir and play the piano but has no recollection of his musical education. (episodic memory)
The case of KF
Unlike HM and Clive Wearing, KF's brain damage (from a motorcycle accident) left him with normal long-term recall but variable problems with short term memory. He has a digit span of one (i.e. when given a string of 20 numbers to recall in sequence he usually can only remember one of them). This suggests he has almost no short-term recall. These deficits support the multi-store model because they show that STM and LTM are separate.
However, other KF's deficits support the working memory model. If KF is given a paired associates task, KF's performance is only slightly poorer than normal control participants. This shows that only some areasof his STM are damaged. In addition KF does better on short term recall tasks if material is presented visually than when it is presented autiorally, which again fits the working memory model.
Definition: Method of data analysis which has already been collected (secondary data) from observation, interview, questionnaire and other methods. It measures the relationship between 2 or more variables to see if a trend or relationship exists between them.
-Data is quantative, easy to analyse
-Data has already been collected, so little time and effort is involved
-No manipulation of behaviour is needed.
-No cause and effect can be inferred but it often is.
-Other factors affecting the correlation may not be noted by the researcher, but may influence the variables
-Low in validity.