Research Methods Flashcards
Experimental
Method
Invovles the manipulation of an independent variable (IV) go measure the effect ok the dependent variable (DV).
Experiments may be laboratory , field , natural or quasi .
Aim
A general statement of what the researcher intends to investigate , the purpose of the study .
Directional hypothesis
States the direction of the difference or relationship
Mom directional hypothesis
Does not stare the direction of the difference or relationship
Variables
Any ‘thing’ that can vary or change within an investigation .
- Variables are generally used in experiments to determine if changes in one thing result in changes to another .
Independent variable (IV)
Some aspect of the experiments situation that is manipulated by the researches or changes naturally - so the effect on the DV can be measured
Dependent variable (DV)
The variable that is measured by the researcher . any effect on the DV should be caused by the change in the IV.
Operationalisation
Clearly defining variables in terms of how they can be measured .
Aims , we have a theory that energy drinks affect how much people talk . This is based on our understanding (having read a few research studies on the internet ) that energy drinks contain sugar and caffeine , and that these substances increase alertness making people ‘chattier’ .
-As luck would have it , a new energy drink speedily has come onto the market and we are keen to know whether it might affect the talkativeness of those who drink it .
-Now fhag we have an initia idea , the next step is to narrow the focus of our research to produce an aim .
-in psychological research , aims are developed from theories , like our energy drink theory above , except in psychology tje theories tend to be much more sophisticated and tend to be based on hours of research .
-aims are generally statement that describe the purpose of an investigation. In this case of our investigation, the aim would be something along the lines of:
Hypothesis
Having written an aim, we need to formulate our hypothesis. Hypothesis is a statement that is made at the start of a study and clearly describes the relationship between variables. As stated by the theory. In this case of investigation, this might be :
-Energy energy drink people to become more talkative.
Hypothesis can be directional or non-directional. In a directional hypothesis, the research and made clear sort of difference anticipated between two conditions or clips of people. This recent, directional hypothesis includes more or less, higher lower, or slower, etc.
People who drink energy drink become more talkative than people who don’t.
-Drink, water or less talkative than people who drink energy drink.
And non-directional hypothesis simply states that there is a difference between conditions, all groups of people but, a directional iPod, the nature of the difference is not specified.
People who drink speed up to find out of alterness, compared with don’t drink speed up.
Doing an experiment
We have decided to test and doing theory by using experimental method. Firstly, we are going to take glimpse of people, let’s say 10 in each group. Then, start with the first group, each person (each part – studies) kind of energy drink. A glass each. How many words, each body says in a five minute period immediately after what they had to drink.
Deciding which type of hypothesis to use
Leaving aside the debate about whether or not this is a good experiment (it’s not really – but we are taking the whole process slowly exactly details of how we would work (it probably wouldn’t) which type of hypothesis should we choose ?
Research is tend to use a directional hypothesis through the findings of previous research study suggest particular outcome. When there is no theory or previous research, or findings from early studies are contradictory, research as instead of studies, a nondirectional hypothesis.
Even though New and Ancy drink, the effects of caffeine and sugar and tortillas are well documented. Therefore upload direct to hypothesis on this occasion.
Research sent to use directional hypothesis theory or the findings of proof research studies suggest a particular outcome. When there is no theory or previous recent or finding some studies or contradictory, searches instead I decide to use a nondirectional hypothesis.
Even though speed up is a new energy drink, the effects of caffeine and sugar stiffness are well documented. Therefore we will opt for a directional hypothesis on this occasion.
Independent and dependent variables
In an experiment of research of changes or manipulates, the independent variable (IV) and record all affect this changes in dependent group (TV) or other variables potentially affect the TV should remain constant in properly run an experiment . This is so the research of gummy confident that any change in the TV was due to the IV, and the IV alone.
Level of the IV
More effective, IV renew different experimental conditions. He simply gave some participants, how would we know how they are? You need to comparison. We could  either :
-Compare What is talkativeness before and after drinking energy drink.
-Two groups of participants – 32 drink energy drink with water (which is the way we have described study on the facing page).
The cases the two conditions are no energy, drink, or drinking These are the two levels of the ID: to control (low speed up/drink of water) and experimental condition (energy drink).
Oh well, written hypothesis should make it easy to tell what the IV and DVR. Very proudly unveiled the directional hypothesis we have written for an investigation, comparing true groups of
-The group that drinks energy drink will be chatted in the group drink, drink water..
This is different from the facing page – I thought this is common or sizes, but still variables the relationship between .
Personalisation of verbs
We have not yet managed to operationalise Abin the hypothesis in order to make it testable .
-Any of the things that are interesting, such as social behaviour, intelligence are thinking, often little fuzzy are not easy to define. Thus, in any study, one of the main task of the research ensured that the variables being investigated are fuzzy and possible. So much better hypothesis in the one above would be
-Drinking 300 mL, more words in the next five minutes and particles took 300 mil of water.
See the difference? Now that are variables are personalised and complete, we are free to concentrate on more important things, this is how we’re going to.
Hehehr
Extraneous variables
(V) any variable, other than the Independent variable (IV), that may affect a dependent variable (DV) if it is not controlled. These are essentially Newton variables that do not vary systematically with
The Iv .
Confounding variables
A kind of Evie, but the key features that are confounding variable varies systematically with the IV. Therefore, we can’t tell if any change in the DV is due to the IV or the confounding variable.
Demand the characteristics
Any any CE from the researcher or from the research situation that may be enacted by participants as revealing the purpose of an investigation. This may lead to participating their behaviour within the research situation.
Investigator effect
Any effect of the investigation behaviour (conscious or unconscious) on the research outcome (DV). This may include everything from the design of the study to the selection of, an interaction with, participants during the research process.
Randomisation
Do use of child matters to control for the effects of bias, when designing materials and deciding the order of experimental conditions.
Standardisation
Using exactly the same formalise procedures and structures of all participants in a recess study.
Extraneous variables
The Keaton experiment is that an independent variable (ivory) manipulated (changed), see how this affects the dependent variable (DV). The only thing that influence the TV is IV. Any other variables that might interfere with the IV (or the DV) should be controlled or removed.these additional, unwanted variables are called extraneous variables, and, where possible, identified at the start of the study by the researcher, who can then take steps and organise the influence.
Many extreme variables are straightforward to control the third of the participants, the lighting the lab, etc. These are described as “ nuisance“that do not very systematically with the IV. These may be “muddy “experimental water so to speak, but do not confound the findings of the study. They may just make it harder to detect result.
…
Confounding variables
Confounding variables changes systematically with the IV. This energy study. We have 20 participants to decide to use the first 10 participants who arrived for the energy drink condition. It happens at these first impossible are overexcited because they saw Prince William arrived at their school. This means that there are there was some delay for further part has arrived and by then people are less excited. This unexpected event means we have ended up with the second oriented IV – being excited or not.
So when we come to our results and find out the speed up group chat, we can’t be sure if this is because of the drink or the excitement. The problem is that the motion various systematically with the IV and the explain changes in the DV.
…
Demand characteristics
Cottisford adult passive with an experiment and are likely to be spending much of their time, trying to make sense with the new situation. They find themselves in. As such, participant reactivity is a significant extraneous variable in experiment of reset, and one that is voted for control. In the resource situation, part will try to work out what is going on. Certainly please may help them interpret what is going on. These clues (or queues) characteristics of the experimental situation may help to second-guess the experimenters intentions as well as the aims of the study
Demand characteristics, two
What they look for tell them how they should behave in experimental situation. They may act in a way that they think it’s expecting overperformed to please experimenter (the police effect), although deliberately under – performed to sabotage results of the study (the screwed effect). Either way, participant behaviour is no longer an extraneous variable that may affect the DV .
Investigator effect
What is the reactive lead to investigate effects. Considered this it is possible that during our energy drink study. As we are recording the words spoken by part, we may be inclined to Smol during our interaction with some participants and others. Given that we are expecting the energy drink group to speak more than the group water, we may unknowingly – in our unconscious behaviour – encourage a great level tattiness from the participants.
Investigator affect two.
This is an example of an investigative effect, which first any unwanted influence of the investigator on the research outcome. As HUGH, space COOL I, C,AN (2006) points out, this can include expectancy effects and unconscious queues (such as those subscribed above).
Might also refer to any actions of the research that were related to the studies design, such as the section of the pot, the materials, instructions, etc. Leading questions, which are discussing relation to our assess of money are good example of the power of investigator effects. I’ve been mentioned an eyewitness testimony chapter) .
Randomisation
In any investigation or research, you can take to minimise your photo extraneous/confounding variables on the
-One of these is randomisation, which is first use of chance method to reduce the research on cautious suspend designing investigation
-In short, this is an attempt to control investigator effect.
-For example, memory remain for participants to be calling once from list. The order of this should be randomly generated certain percent of each word is not decided by the research
In primary participants are important number of difficult issues, all these conditions should be randomly determined. Example in the energy, energy drinks, experiment, we might want to know what quantity of energy drink causes chatting us. We may set up for experiment conditions: drinking water (condition), drinking hundred millilitres of energy, energy, drink(condition, B), 200 mL of energy drink (condition), and Twink, 300 mL of a huge drink (condition)
If all participants were to take part in all four conditions, the order in which these conditions were completed, would need to be randomised for each participants. (this is no alternative to
Counter balancing – discussed on the next bridge).
Standard
As far as possible, with an investigation, or partition should be subject to the same environment, information experience. To ensure this, all procedures are, in other words, there is a list of exactly what will be done the study. This is standardised instructions that are read to each participant. Standardisation means that law – standardised changes in procedure, do not act as extreme as variables.
Experimental design
The different ways in which participants can be organised in relation to the experimental conditions
Independent group
Participants are allocated to different groups where each group represents one experimental condition
Repeated measure
All participants take part in all conditions of experiment
Matched pairs design
Part of participants are first marched on some variable (S) that may affect a dependent variable. Then one member of the pair is the scientific condition and the other condition. B.
Random allocation
An attempt to control for participant variables in independent group design, which insures that each participant has the same chance of being in one condition as any other.
Counter balancing
And attempt to control for the effects of order in a repeated measure design: half the pot experience the conditions in one order and the other in the opposite order.
Independent group
So an independent group design is when two separate groups of particles experienced due to conditions of experiment. If there are two levels of the independent variable IV, this means that all participants experience one level of the Ivy only. In our energy treat investigation, this would involve
One group of protons (group one), drinking the energy drink (called this condition “the experimental condition)
-a different group of water, spoons (group 2) (condition, condition).
The performance of the two groups with them be compared. In this case, we would compare the difference in the main number of us spoken to 5 minute period for each group/condition.
Repeated measures
Another way of carrying out the investigation would be to use a repeated measure design – all partic experience, both conditions of experiment.
-is Woodford, for example, experience collection, eight (energy, drink, condition, the experiment condition).
-Each part is with them. Basically to be tested in condition Big (glass of water condition, the control condition) .
-following this, the two main calls from both conditions would be compared to see if there was a difference.
Matched pairs
In a matched person design, participants are put together on a variable of variables, relevant to the experiment. For instance, in the memory study, participants be matched on the IQ, as this might be a good indicator of their ability to record information.
-Participants with the first and second height will be put together with the third fourth and so on. Then one pot from each page would be allocated to a different condition of the experiment.
-This is an attempt to control the confounding variables of participant variables and often necessitates the use of a pre-test of the matches to be affected.
Matched pairs – example
Go back to energy drink study, we might observe participants interacting in a room before the experiment begins and select the two people that appear to be the chattiest. One of the power would be placed in condition and the other condition B. We will then do the same with the third and foremost of participants, and so on. The experiment would be then the same way as in dependent group design.
Evaluation – independent groups
The biggest issue with an independent group is at the participants who occupy different groups are not all the same in terms of participant variables.
-If a researcher finds a main difference between the groups and the dependent variable (DV) may be more stupid with the past variables and the effect of the IV. These differences may confounding variable, reduce validity of the values. To do with this problem, resources use rather allocation.
2.evaluation – independent groups
Independent groups design less economical than reputation register, each participant, contributes a single result only.
-Twice as many participants would be needed to produce equity from data to that collected in the repeated
-This is the time/money spent on recruitment
-The strength of using independent group that the order affect are not a problem was, there are prob:’ repeated message decides.
Participants are also less likely to guest the aim.
Repeated measures -evaluation
The biggest issue for repeated message that protest has to do at least two toes and the order of the task will be significant (i.e. there are order). The energy example, having the antidote may have a continuing effect on a p participant drinks, water, afterwards. To deal with this, research council, balancing.
Evaluation – repeated measures 2.
Order effect also arise, because repeating two tasks could create boredom or fatigue then might deterioration in performers on the second task, so it might as well order the task are. Alternatively, participants performance may improve through the effects of practice, especially on a skill based task– In this case participants would perform better on the second task . Order acts as a confounding variable.
If evaluation repeated measures 3.
More likely, that part of the experience or conditions of the experiment. For this reason, demand characteristics tend to be more of a feature of repeated measure design than independent groups.
-The strength of using repeated measures, all that participant variables are controlled (therefore higher validity) and for participants I need (therefore less times but recruiting them).
Evaluation – matched pairs
Participants already take part in a single single conditions, order effects and demand characteristics are less of a problem.
/although there is some attempt to reduce participant variables in this design, participants could never be much exactly. Even when they’re identical twins that uses much pairs, they will still be important differences between them that may take the DV.
-Matching, maybe top and see me inexpensive, particularly for pre-test is required, so this is the second economical and other design.
Lab experiment
An experiment that takes place in a controlled environment, within which of the research amendment placed the ivy and course effect of the TV, whilst maintaining straight to control extremely variable.
Field experiment
An experiment that takes place in the natural setting within which the research manipulates the ivy, and record the effect on the DV.
Natural experiment
And it’s from my brother changing the Ivy is not bought by the resources but would’ve happened even if the reset had not been there. The research record effect on a DV they have decided on.
QUAS I. Experiment.
I study that is almost program, but lack key ingredients.
– The Ivy has not been determined by anyone, the research or any other other person that the variables is in Big, such as being old or young.
Strictly speak. This is not an experiment.
Strength of lab experiments
Lab experiments of high, control over confounded again, extraneous variables. This means a research can ensure that any effect on the dependent variable is likely to be the result of a manipulation of the independent variable. Thus, we can be more certain about demonstrating cause and effect (high internal validity).
Two. Strengths of lab experiments.
Replication is more possible than other types of experiment because of the higher level of control.
This insures that new extraneous verbals are not introduced from repeating an experiment.
-Replication is vital to check the results of any study to see whether the fight is valid and not just one off.
Limitations of lab experiments
Lab experiments made like generalisability. The lab environment may be rather artificial and not like everyday life.
– in an unfamiliar context, Laborhood, unusual ways, so the behaviour cannot always be generalised beyond the research setting (low external validity).
– as well as this participants are usually where they are being tested in a lab experiment (they may not know why) and this may also give rise to quotation, unnatural quotation behaviour (see demand characteristics described on page 170
Meditations of lab experiments, 2.
Furthermore, the task spoons are asked to carry out in the lab is from may not represent every day experience, for instance, recording unconnected this as part of a memory experiment (low Monday realism).
Strength of field experiments
Do field experiments have higher mundane realism than lab experiments because the environment is more natural.
– Does field is very produce behaviour, a small valid and authentic. This is especially the case as possible, but it may be on the whether they are being studied (high external validity).
Limitations of field experiments
However, there is a price to pay for increased realism due to the lost controls of CVS and EVS.
– This means cool an effect between the IV and the DV and field studies may be much more difficult to establish spice replication is often not possible.
– There are also important issues. If participants are on Weather being studied, they cannot consent to being studied and so research my constitute and invasion of privacy.
Natural experiments
Natural experiments are like a lab or field experiment in so far as the researcher measures the effect of an IV on a DV. However, what distinguishes a natural experiment is the researcher has no control over the IV and cannot change it – someone or something else causes the ivy to vary. For example, before and after a natural disaster or whether a child is in hospital at age 5 or 10.
– Note that it is IV that is natural, not necessarily the setting – participants may be tested in a lab. The DV may also be naturally occurring (exam results) or maybe devise by experiment er and then measured in the field or lab..
Strength of a natural experiment
Natural experiments provide opportunities for research that may not otherwise be undertaken for practical ethical reasons, such as the studies of instantised orphans ().
– Natural experiments often have high external validity, because they involved the study of real world, issues and problems as they happen, such as the effects and a natural disaster on stress levels
Limitations of natural experiments
I’m actually occurring event may only happen very early, reducing the opportunities for research. This also made a limit to Skype for generalising findings to other similar situations.
– Another issue is that participants may not be randomly allocated to experimental conditions. (no, that is only applies when there is an independent group design).
This means that research might be less so the IV affected the DV. Example, in the study of Romanian orphans, the IV was whether children were adopted as late. However, there were lots of other differences between the groups, such may have made them escaping for prospective parents.
– Such research may be conducted in the lab and therefore made luck realism and demand characteristics may be an issue
Quasi experiments
Quasi experiments have an IV that is spaced on an existing difference between people (age or gender). No one has manipulated this variable, simply exist and, unlike in a natural experiment,  the“independent variable “cannot be changed. Instance, if this anxiety, level of phobic and non-phobic patients were compared, the ivy of “having a phobia “was not have come through any experimental manipulation.
– As with a natural experiment, the DV may be naturally caring (exam results) or maybe advise by the experiment and measure in the field or a lab.
Quasi, experiments, strength and limitations
– Quiz experiments are often carried out and controlled conditions in their forces and states of the lab experiment (replication).
– Quiz, experiments, like natural experiments, cannot randomly allocate to conditions and therefore there may be confounding variables.
– In addition, in both quiz, experiments are natural experiments, the IV is not to the change by the research and therefore we cannot claim that the IV has caused any observed change.
Population
A group of people who are the focus of the research as interest, from which are smaller samples is drawn.
Sample
A group of people who take part in the recent investigations. The sample is drawn from (target) population, and is presumed to be representative of that population, I stand as “fairly “for the population being studied.
Sampling techniques
The method used to select people from the population.
Bias
The context of sampling, when certain groups are over – or under – represented within sample selected . For instance , there may be too many younger people or too many people or one ethnic origin in a sample . This limits the extent to which generalisations can be made to the target population
Generalisations
The extend to which findings and conclusions from a particular investigation can be broadly applied to the pppilaorpk . This is possible of the sample of participants is reprengative of the target population .
For practical and economic reasions
It is usually not possible to include all members of a target population in an investigation so a reacher selects a smaller groip , known as the sample .
Ideally the sample that is drawn will be representative of the target population so that generalisation of findings becomes possible . In practice , however it is often very dofffilt to repreeent populations in any given sample due to the iniwikirt diverse nature of pppularipns of people .
Inevitability then , the vast majority of sallows contain some degree of bias .Samplww are selected using a sample technique that aims to produce a representative sample . We will look at the main techniques used by psychologists .
Random Sample
-A random sample is a sophisticated form of sampling in which all
Members of the target population have an equal chance of being sedated .
-The first step in selecting a radn
Sample is to obtain a complete list of all members of a target population .
- sexoenlu , Al of the names
Of the list are assigned a number . Finally , the actual sample is selected through the use of some LOTTERU MERHOD (a computer or picking numbers relm a hat ).
Systematic Sample
-A systematic sample is when every nth member of the target population is selected , for example every 3rd house on a street or every 5th pupil on a school register .
- A SAMPLING FRAME is produced which is a list of people in the target population organised into , for instance , alphabetical order .
-A sampling system is nominated (every 3rd every 6th every 8th) person etc .
-may begin from a randomly determined start to rescue bias .researcher rhen works through the sampling frame until sample is complete .
Stratified same
A stratified sample is a sophisticated form of sampling in which the COMPOSITON AOF THE SAMLLE REFLECTS THE PROPRITIONS of people in certain subgroups (starts) within the target population or the wider population .
Stratified sample. (2)
To carry out a stratified sample , the researched first identifies the different strata that makes up the population .
-Then , the proportions need for the sallle to be relrewenriave are worked out .
-Finally , the participants that make up each state im are sleedredbusing random sampling .
(Let’s say In Manchester argh check the page 176)
Opportunity sample
Given that representative samples of the target population are so difficult to obtain , many researchers simply decide to select anyone who happens to be willing and available (an opportunity sample ).
-The researcher simply takes the chance to ask whoever is around at the time of the study , for example in the street . (In the case of market research )
Volunteer sample
-A volunteer sample Involved participants selling themselves to be part of the sample , hence it is also referred to as self-selection .
- To select a volunteer sample , w researcher may place an advert in a newspaper or on a common room noticeboard .
Alrernaigely , willing participants may simply raise their hand when the researcher asks .
Volunteer sample
-a volunteer sample involves participants electing themselves to be part of the sample . Hence , it is also referred to as self-selection .
- To select a volunteer sample , a reswaecher may place an advert in a newspaper or on a common room noticebaprd .
-Alternaotbely , willing participants may simply raise their hand when the researcher asks .
EVALUATION -Random Sample (1)
-A random sample is potnentislly unbiased .
-This means that confounding or extraneous variables should be equally divided between the different groups , enhancing n internal validity Z.
Evaluation (2)- Random Sample
-however random sampling is difficult and time consulting to conduct . A complete list of the target population may be extremely difficult to obtain .
- furthermore you may end up with a sample that is still unrepresentative -the laws of probability suggest that random sampling is likely to produce a more repeesnwriwbe sample than OPPORTUNITT SAMPLING. X
-Howveer C it is still possible that the random method may select (example 20 female psychologists )
- in soffit on , selected participants may refuse to take part (which means you end up with something more like a volumetric sample )
- rhis particular issue applies to Al the methods below .
Systematic sample -EVALUATION
-This sampling method is objective. 9’cs the system for selection has been established the researcher has no influence lede over who is chosen (this is even
Lprenrje gase or the start is randomly
selected ).
-As with random
Sampling , this method is this
Method
Is time
Consuming and , in the end ,
Participants
May refuse to take
Part
, resulting in a volunteer sample
.
stratified sample
EVALUATION
This method produces a representative sample because it is designed to accurately reflect RHE composition of the population .
-Yjis
Means that generalisation of findings becomes possible
.
-Howeved , statification is not perfect . The identified starts cannot reflect
All the ways people are different , so
Complete reprentstiom of the target population is not possible .
Opportunity Sample
is convenient . This method is much less costly in terms of money and then say random sampling . Because a list of members did the target population is not required and there is Ko need to divide tjenpppilafopn into different starts as there is in start field sampling .
Negatives -EVALUATION
- on rhe negative side , opportunity samples suffer from two forms of bias .First , rhe sample is unrepresentative of the target population as it drawn from a very specific area such as one steeet in one town , so finish’s cannot be generalised to the target population .
-second , the researcher has complete control over the selection of participants and for instance , may avoid people they do not like the look of (researcher bias ).
Opportunity Samples
- On the meagibe side , the oppprutnity samples suffer from
- Tel forms of bias . First , the sample is unprensentaobe of the target populations it is drawn from a very specific area ? Such as one steer in one town , so findings cannot be gernalsoed to the target population . Second , the researches had complete control over the election of participants and , for instance , may Aldi’s people they do not look like the look of (researcher hows )
Volunteer sample EVALUATION
- a cool yeee sample ks ways at kt requires minimal input from the researcher and is also less time consuming than other forms of sampling .
- -the researcher end up with apricpamfa who are lore engaged mkre so than someone who was stopped I t steer .
- VOLUNTEER BIAS Is a problem - asking for volunteers may attract a certain profile
Volunteer bias
- VOLUNTEER BIAS Is a problem - asking for volunteers may attract a certain profile of person , fhat is one who is cutie and more likely to try to plewse tje reswvejr (which might then affect how far findings can be generalised ).
Volunteer sample
Collecting a volunteer sample is easy . It requires minimal input from the researcher (they come to you )
-and so is less time consuming than other forms of sampling .
-Thw ewswwwdhee ends up with participants who are more engaged , so more than someone who stopped in the street .
Volunteer bias
Is a problem . Asking for volunteers may attract a certain to “profile” or person that is one who is curious and more likely to please the researcher (which might then affect how far findings can be generalised ).
Ethical issues
These arise when a conflict exists between the right of participants in research studies and the goals of research to produce authentic and valid and worthwhile data .
BPS code of ethics
A quasi -legal documented produced by British Pyschological society (bps) that instructs psychologists in the uk about what behaviour is and is not acceptable when dealing with participants .
-The code is built around four major principles respect , competence , responsibility and integrity I .