Psychological research and scientific ... - SOCIAL SCIENCES



4678326715793Research MethodsA2 Psychology – PSYA4Name: ____________________Name: Target Grade:Class Teacher:Study Buddy’s Name:-217170-553085AssignmentTitleWhat you/your teacher/peer said you did wellWhat your you/your teacher/peer said you needed to improveYour mark/out ofGradeOver/on/ under target grade1/2/3/4/5331918-293577-250175-293577Self-Report TechniquesKey TerminologyPsychological research and scientific method key term glossaryFill in the following table at the end of each lessonEmpirical methodsReplicabilityTheory constructionObjectivityHypothesis testingInduction DeductionPeer reviewExperimentsSelf-report techniquesObservations Correlational analysesCase studiesMeasures of central tendencyMeasures of dispersionPilot studiesInter-rater reliabilityTest-retest reliablilityValidity Sampling methodsBPS code of ethics and conduct for humansEthical issues with non-human animalsInferential statistics testsProbabilitySignificanceChanceDegrees of freedomType 1 errorType 2 errorSpearman’s RhoChi-squareMann-Whitney U TestWilcoxon T TestRules with graphsContent analysisTriangulationReflexivityWhat to include in psychological report writingWhat is Science?Psychologists carry out research to test their hypotheses and construct theories. Science is a system of acquiring knowledge. In order to be a Science, Psychology needs to have 5 major features. These are:The use of empirical methodsObjectivityReplicabilityHypothesis testingTheory constructionThe scientific process indicates how scientists investigate aspects of the physical and social world in order to generate new knowledge. Induction is… Deduction is…Label the diagram above – showing the difference between the two scientific processes.Choose one of the psychological theories that you have studied and design a research study to investigate a specific aspect of your chosen theory. Chosen theory: ____________________________________________________________Think about and make notes on the following:What hypothesis/hypotheses would be tested? Is the hypothesis directional or non-directional?What research design would be used? Who would be the participants? How many would there be? How would you select them?What kinds of data would be collected?Problems with using the scientific method in PsychologySome psychologists are subjective (this means using their own opinion when conducting research). These methods aim to be valid, but data collected using interviews, questionnaires, content analysis or observations which are then triangulated could be less objective than experiments.The scientific method is reductionist and deterministic. This is because we are attempting to explain complex human behaviour in simplistic terms.Psychological treatments of mental health problems have had modest success; therefore the goals of science are not always appropriate in psychology.Experimenter bias and demand characteristics make studying human behaviour less objective and this compromises validity. Practice QuestionsJune 2012Explain what is meant by replicability. Why is replicability an important feature of science? (5 marks)January 2011A teacher has worked in the same primary school for two years. While chatting to the children, she is concerned to find that the majority of them come to school without having eaten a healthy breakfast. In her opinion, children who eat ‘a decent breakfast’ learn to read more quickly and are better behaved than children who do not. She now wants to set up a pre-school breakfast club for the children so that they can all have this beneficial start to the day. The local authority is not willing to spend money on this project purely on the basis of the teacher’s opinion and insists on having scientific evidence for the claimed benefits of eating a healthy breakfast. Explain why the teacher’s personal opinion cannot be accepted as scientific evidence. Refer to some of the major features of science in your answer. (6 marks)The role of peer review5170525-574158Peer review is assessment of work by experts in the field. It is a vital part of the verification process by which research is deemed acceptable (or not). Peer review consists of a system used by scientists to determine whether a piece of research can be published in a scientific journal. The article is scrutinised by independent experts, it is important as it reduces the chance of flawed research being accepted as fact. What are the advantages of peer review?Recently peer review takes place on the internet, with people reading an article, deciding whether it is valid or not. Some online journal sites even ask readers to rate the articles. To an extent we can say that the internet is policed by its readers.Peer reviewers are generally unpaid and there are normally a number of them in order to make sure the quality of the work in high.What three main purposes does peer review serve?Allocation of research funding:Publication of research in scientific journals and books:Assessing the research rating of university departments:Criticisms of peer review:Richard Smith, a previous editor of the British Medical Journal made an interesting comment about peer review. Use page 22 to make a note of some of his criticisms: Unachievable ideal – it isn’t always possible to find a suitable expert to review the report.Anonymity – research is conducted in an environment surrounded by competition for research grants. Relationships between experts sometimes affect objectivity (imagine two psychologists wanting to settle an old dispute). Now journals prefer open reviewing.Publication bias – peer review tends to prefer positive results. This leads to misinterpretation of truth.Preserving the status quo – peer review tends to prefer results that support previous theory, rather than going against it. Science does not really like huge shifts in opinion or theory.517017089535Case Study The Monster Study is the name given to a stuttering experiment performed on 22 orphan children in Davenport, Iowa in 1939. It was conducted by Wendell Johnson at the University of Iowa. Johnson chose one of his graduate students, Mary Tudor, to conduct the experiment and he supervised her research. After placing the children in control and experimental groups, Tudor gave positive speech therapy to half of the children, praising the fluency of their speech, and negative speech therapy to the other half, belittling the children for every speech imperfection and telling them they were stutterers. Many of the normal speaking orphan children who received negative therapy in the experiment suffered negative psychological effects and some retained speech problems for the rest of their lives. Dubbed "The Monster Study" by some of Johnson's peers, who were horrified that he would experiment on orphan children to prove a hypothesis, the experiment was kept hidden for fear Johnson's reputation would be tarnished in the wake of human experiments conducted by the Nazis during World War II. The University of Iowa publicly apologized for the Monster Study in 2001.Why would a peer review have been useful in the above case study?Which of the criticisms of peer review does the above case study show?Practice QuestionsJune 2010Outline what is meant by the term peer review in psychological research. (2 marks)Explain why peer review is important in psychological research. (5 marks)Extension TaskFor recent famous cases of professional misconduct go to: Hwang Woo-suk’s fraudulent cloning case Andrew Wakefield and the MMR controversy Psychiatrist Raj Persaud is suspended for plagiarismYou might also like to type in ‘Cyril Burt affair’ for information on one of the biggest alleged frauds in psychology that had profound implications for our education system Designing Psychological investigationsYou have to be able to understand the layout of psychological journals. The order of journal reporting is as follows:TitleTable of contentsAbstractIntroductionAimHypothesesMethodDesignParticipantsApparatus/materialsProcedure Controls/ethicsResultsDescriptive statisticsInferential statistics DiscussionExplanation of findingsRelationship to background researchLimitations and modificationsImplications and suggestions for future researchConclusion ReferencesAppendices Practice QuestionsJune 2011It is thought that colours might affect our performance when carrying out certain tasks. Research in this area has been inconclusive. Some studies have shown that red improves performance but others have found the opposite. It could be that these contradictory results have arisen because red is beneficial only for certain kinds of mental processing. Some psychologists tested this hypothesis in a series of independent-groups design experiments using students at a Canadian university. The experiments involved computer tasks, with either a red, blue or neutral background appearing on the monitor. The researchers found that participants were better at a word-recall task and a spell-checking task when the screen background was red rather than blue or neutral. However, participants thought of more creative ideas when the screen was blue rather than red or neutral. The researchers concluded that red is beneficial for tasks that require attention to detail whereas blue aids creativity.What were the researchers’ aims in this study? (2 marks)Imagine that you are writing up the report for this series of experiments. What is the purpose of the introduction section of a report? (2 marks)In the discussion section, researchers are also expected to consider any possible applications of their research. Suggest one practical application that might arise from these findings. (2 marks)A researcher assessed the evolutionary prediction that women over 35 years old would conceal their age more than males over 35 years old when seeking heterosexual partners, by counting the number of times that age was revealed in dating advertisements. Five hundred male and female advertisements were assessed. The results were:Number not revealing agePercentage not revealing ageWomen35075Men10020Give an appropriate one-tailed (directional) experimental hypothesis for this study. (2)What type of experimental design was used? (2)After the study was published, another researcher decided to replicate it. Explain what is meant by replication and what the purpose of the procedure is. (4)An opportunity sample was used in this study. Explain one strength and one weakness of this method. (4)After performing this research, the investigator was interested in seeing whether there was a relationship between age of women and the number of women concealing their age in personal advertisements. Design a correlational study to investigate this, including appropriate details. (7)Psychological Investigations Summarise what can be found in each section of the journal you will be given. You don’t need to know this journal’s contents for the exam, but the layout is essential.Discussion:Results:Introduction:Aim: Hypothesis:Table:Method:Graph: Extraneous variables Standardised InstructionsStandardised DebriefConsent FormEthics Directional hypothesisNon-directional hypothesisNull hypothesisIVDVcenter-1122680center-1129665Reliability5709920363220Using the information on page 280 of your textbook, describe factors that affect the reliability of these studies:Three psychologists carry out a series of observations of children in play school...-7175546355A test is devised to see if there is a correlation between parental alcoholism and later development of alcoholism in their offspring...5655945153670A group of students are tested on half a maths test on Monday, and then the other half the following Monday...ValidityUsing the information on page 280-281 of your textbook, describe factors that affect the validity of these studies:-717554445A psychologist carried out a study in a laboratory to see how much alcohol people drink when under stress...5709920164465A psychologist thinks that drug use is correlated with low self-esteem; he carries out a series of observations to test this theory...-6496056350A video of a (staged) car crash is shown to a group of students to see if they can estimate how fast the car was going at the time of the collision...Design a simple study investigating drinking (alcohol) behaviours among teenagers Experimental design = Sampling =Aim = IV = DV = Method=Crossword on Research Methods terms and conceptscenter2540Across1.these characteristics provide clues as to the aim of the study and affect how participants behave3.this is the noun for when a variable is qualified and quantified to be made as specific as possible6.a non-experimental method asking people questions verbally7.these people are not naive participants but have been briefed to play a certain role or give specific responses10.this type of sample comprises people available as long as they meet selection criteria11.this method aims to reduce the effects of asking participants to do one thing after another13.this kind of analysis is a way of dealing with ethical issues and assesses the advantages and disadvantages of a study15.this type of data is non-numerical and includes thoughts, feelings, and memories16.this study is conducted to check design and procedures and to change them if necessary19.this technique is where people give information about themselves20.this professional body introduced ethical guidelines to protect research participants22.this type of question generates a limited range of responses which are very brief23.this detailed study is conducted on one person or two maximum28.this is the noun for when a person is not identifiable by name30.these methods do not manipulate anything, and have no explicit IV or DV32.this variable is the one which is measured36.these effects stem from asking participants to do a number of things one after the other38.this variable is the one which is manipulated40.this is how reliability is increased41.in this sample type each member of the target population has an equal chance of being selected42.this form of consent is where a group of people (not the actual participants) are consulted, and used to assume the actual ones will agree43.this relates to the general area of study for the investigation44.these effects refer to things that the researcher does that may affect the participantDown2.this design technique is where neither researcher nor participant know who is in which group4.this form of experimental design is where different participants take part in different conditions5.this refers to consistency over time8.these issues must be dealt with by psychologists prior to and during the study9.this refers to whether something is measuring what it is supposed to be12.a statistical test and type of study which assesses the relationship between co-variables14.a prediction is this if previous research findings are conflicting or non-existent17.this form of experimental design is where all participants are exposed to all conditions18.a non-experimental method using written questions21.this method refers to how participants are recruited to a study24.this form of consent must be obtained from participants wherever possible25.this variable may confuse or obscure results26.this kind of analysis is a means of analysing non-numerical data27.this refers to the way that data is stored and who sees it29.these methods watch and record the behaviour of people31.this is a statement of what researchers expect to find33.these methods use either a laboratory, field or quasi method as they have an IV and a DV34.this should be an active procedure which returns participants to the state they were in prior to the study35.this can be active or passive and should be minimised so that participants are not misled37.in this sample people respond to a request for participants39.this type of validity refers to the generalisability of findingsNameDescription and how to do itAdvantagesDisadvantagesProbabilityRandom Every individual has an equal chance of selection.Give every unit in the population a number.Use a calculator, spreadsheet or random number tables to select the individuals in the sample - or more informally, pull numbers out of a hat.Simple method.Data analysis simple and has sound mathematical basis.Most standard statistical techniques assume simple random sampling.If the population is very heterogeneous the results can vary considerably.May be difficult to do for large/dispersed populations.StratifiedThe population is divided up into non-overlapping categories called strata. So first decide how to stratify the population.This will depend on what factors are likely to be significant for the investigation - e.g. age, sex, socio-economic group, place of residence...Ascertain what percentage of the entire population is in each of the strata.The size of the sample from each of the strata is proportional to the number of units from the population in it.Calculate the sample required from each of the strata using the formula: % of population in stratum ×sample size/100.Obtain a sample from each of the strata using simple random sampling.Alternative approach: if some of the strata would only have very small samples, actually collect data from a larger sample from them but "scale down" the results.If the population is very heterogeneous, gives a more realistic picture than simple random, and ensures representation of key strata.Produces more consistent estimates of population parameters (such as means and variances) than simple random.Detailed information about the population is required to define the strata.It is crucial to choose the correct stratification according to factors that affect the investigation - this may need to be refined during the investigation.Non-probabilityQuota As for stratified sampling, decide how to stratify and calculate the sample required from each of the strata. Obtain the individuals from each of the strata by whatever means are convenient.Much quicker and easier than stratified sampling.Sampling frame not needed.Cannot use inferential statistics.Within quota the sampling may be unrepresentativeAssessment of e.g. social class may be subjective.Opportunity Uses units from the target population who are available at the time.Quick and easy to do.Sampling frame not needed.Unlikely to be representative of the population.No conclusions can be drawn.Snowballing Participants recruit their friends, family, colleagues etc. Imagine how difficult it might be to study people with eating disorders. Once one or two people have been identified you ask them to direct you to other people.Allows the researcher to test participants which might be difficult to assess.Lower search costs.This research is prone to bias because researchers are only in contact with a small number of the population.Volunteer Uses units from the target population who select themselves – e.g. by responding to an advertisement. Experimenter merely has to check they are in the target population.All participants are willing to be involved.Sampling frame not needed.Quick and easy to do.Self-selected participants are very unlikely to be representative – in many cases they may have a particular "agenda".No conclusions can be drawn.SamplingEthical Issues in Psychological ResearchEthical Issues with Human ParticipantsHow do psychologists ensure that the following ethical principles are controlled for in research?Informed consentDeception Protection from harmConfidentiality Right to withdraw545760385474DebriefingThe BPS (2006) identifies four ethical principles, these are:1.2.3.4.Socially sensitive research is described as ____________________________ ________________________________________________________(Sieber and Stanley, 1988). One controversial piece of research looks at inter-racial differences in ______. Some research suggests that, in terms of IQ _____________________ ___________________. The research may be flawed, e.g. by ignoring social conditions. What effects could this research have?______________________________________________________________________________________________________________________________________________________________________________________________________________________________Practice questionTwo psychologists decided to investigate the influence of group size on bystander apathy. They arranged for participants to wait for a study in a waiting room. In one condition the participants waited alone. In the other the participant believed they were waiting in a group of three, but the other two people were confederates of the researcher. After being in the waiting room for two minutes the participants saw an actor walk through the room. As soon as the actor was out of sight the participants heard a crash and a cry. The researchers recorded the number of participants who went to help in each condition and the speed of the response.Identify 4 ethical issues that have not been addressed by the psychologists.Suggest how to deal with these issues.Case StudySouth Africa’s apartheid army forced white lesbian and gay soldiers to undergo ’sex-change’ operations in the 1970’s and the 1980’s, and submitted many to chemical castration, electric shock, and other unethical medical experiments. Although the exact number is not known, former apartheid army surgeons estimate that as many as 900 forced ’sexual reassignment’ operations may have been performed between 1971 and 1989 at military hospitals, as part of a top-secret program to root out homosexuality from the service.Army psychiatrists aided by chaplains aggressively ferreted out suspected homosexuals from the armed forces, sending them discretely to military psychiatric units, chiefly ward 22 of 1 Military Hospital at Voortrekkerhoogte, near Pretoria. Those who could not be ‘cured’ with drugs, aversion shock therapy, hormone treatment, and other radical ‘psychiatric’ means were chemically castrated or given sex-change operations.Although several cases of lesbian soldiers abused have been documented so far—including one botched sex-change operation—most of the victims appear to have been young, 16 to 24-year-old white males drafted into the apartheid army.Dr. Aubrey Levin (the head of the study) is now Clinical Professor in the Department of Psychiatry (Forensic Division) at the University of Calgary’s Medical School. He is also in private practice, as a member in good standing of the College of Physicians and Surgeons of Alberta.Should this research even be carried out? By not carrying it out there could be potential benefits missed (e.g. public funding), and by ignoring it psychologists are abdicating their social responsibility. Psychologists need to focus on the implications of their research and the worrying potential it could have.What ethical guidelines were broken in the above case study?Remind yourself about the role of ethical committees. How could an ethical committee have had an influence on the case study?You must design a completely unethical study, in groups, ready to present to the class next lesson...Ethical Issues with Non-Human AnimalsWhy might a psychologist use non-human animals in research? Moral justification of using animals in researchSentient beings – do animals experience pain and emotion? There is evidence they respond to pain, but is this the same as conscious awareness? Some humans are not sentient (e.g. brain damaged) but we still wouldn’t experiment on them without consent.Speciesism – discrimination on the basis of species is no different from gender or culture (Singer, 1990), thus you should be careful with the species chosen for research.Animal rights – some views are utilitarian (whatever is best for greater number is ethically acceptable), so if results of the research can justify the pain caused then it is acceptable. Regan (1984) said that this is unacceptable and that animals should be treated with respect and never used in research.3274060105410Is this fair to the monkey? Why/why not?While the BPS has guidelines, there is also important legislation; the Animals (Scientific Procedures) Act (1986). This act requires that animal research is only carried out in licensed laboratories, with licensed researchers, on licensed projects. Licenses are only granted under certain conditions, these are: The 3 R’s was endorsed by the House of Lords in 2002. However the law states that animal research needs to continue in order to test new drugs.The 3 R’s:Reduction (of the number of animals)Replacement (use alternative methods where possible)Refinement (use improved techniques to reduce stress)Graphical RepresentationsRead over your AS Level Research Methods and page 280-1 for a test next lesson.Sketch three graphs, one showing positive correlation, one showing negative correlation, and one showing no correlation at allWhat does a ‘correlation coefficient’ tell you about a set of data?Name two variables which are likely to be positively correlatedGive an example of a positive correlation coefficient and a negative correlation coefficientA psychologist wants to find out what the nation’s favourite colour is. Which graphical representation would he choose?-16510231775ScattergraphUsed with correlations (2 variables)-55880227965Bar ChartsBar charts are used for plotting discrete (or 'discontinuous') data. The types of data do not overlap in any way. E.g. types of birds, breeds of dog.Histograms-400055080Similar to a bar chart, but the x-axis does not show discrete data it is continuous. There are no gaps between the bars.Frequency Polygon-55880307975Very similar to a histogram. It has continuous variables on the x-axis and a continuous line connecting the points instead of barsProbability and SignificanceProbability is expressed as a number between 0 and 1 (where 0 means something definitely will not happen, and 1 means that is definitely will). To calculate probability a psychologist uses this equation:Probability = number of particular outcomesnumber of possible outcomesFor example, if you were to flip a coin, what is the probability that it will be a head? ______Sometimes you can convert probability to a percentage, what is the answer above _____%Statistical SignificancePsychologists use a sample of participants and want to be able to generalise to the population. However, we already know that samples are prone to error. When we carry out a statistical test we want to know how accurately our sample reflects the general population.In order to carry out an inferential test you need a null hypothesis (H0) and an alternative (otherwise known as experimental) hypothesis (H1).What is a null hypothesis?What in an alternative/experimental hypothesis?Inferential statistics allow psychologists to look at patterns of results to see if they have arisen by chance. However, if the results could not have arisen by chance then the pattern is said to be significant.But what is a small enough probability? This is known as a level of significance. In psychology we generally accept a 0.05 0r 5% level of significance (written as p0.05 level of significance; 1 in 20 probability that the results are due to chance factors). This means that anything less than 0.05 is significant and it is unlikely that the null hypothesis is true. Anything above 0.05 is not significant and we reject the null hypothesis.If the researcher wants to be more certain about their results then they use a more stringent probability, such as p0.01 or p0.001. Whatever level is chosen, the p is the significance level.Using the example of bags of chips on page 284, explain the term significance:Using inferential testsInferential statistical tests are used to test the difference between a set of results. Each test is chosen because of the type of data. For example, if you are testing the relationship between two variables, you will need to choose a test which tests for a correlation. In order to choose the correct inferential test you need to know the type of data that you are handling:Nominal IntervalOrdinal Observed and critical valuesReason for applying a statistical test:The purpose of applying the test is to measure the observed value against the critical value to see if the null hypothesis can be accepted or rejected. The observed value is based on the observations you have made.The critical value is the value that needs to be reached in order for the null hypothesis to be rejected.Inferential statistics enable the researcher to make a decision as to whether the results are due to the variable that is being manipulated or due to chance factors.The statistical test, along with the level of significance, allows a researcher to estimate the extent to which results could have occurred by chance. The researcher will look at the table of critical values to see if the null hypothesis is to be rejected.Each inferential test has its own table of critical values.To find the appropriate critical value you need:The degrees of freedom (df) which in most cases is the number of participants (N). In cases where an independent groups design is used there are two values for N, one for each group (N1 and N2)One-tailed (directional hypothesis) or two-tailed (non-directional hypothesis)Significance level (normally p0.05)RSome tests are significant if the observed value is greater than the critical value, while some tests are the reverse. In the chi-squared and Spearman rho the obtained (observed) value has to exceed the critical value for an effect to be significant. In the Mann-Whitney and Wilcoxon tests the observed value has to be below the critical value for a significant result. You will also find this under each table. But try to remember this:If there is an R then the observed value should be gReateR than the critical value (e.g. Spearman’s and chi-square). If there is no R (e.g. Mann-Whitney and Wilcoxon) then the observed value should be less than the critical value.ErrorsType 1 errorThis is where the null hypothesis is wrongly rejected. The experimental hypothesis is claimed to be supported when results are, in fact, due to chance factors.Reasons for a Type 1 error: different significance levels can be used (e.g. p0.05 or p0.001. some levels can be regarded as ‘too lenient’ as they allow too much of a chance that the IV is not responsible for the experimental effect.Type 2 errorThis occurs if the null hypothesis is falsely accepted. The experimental hypothesis is claimed to be rejected when results are, in fact, not due to chance factors.Reasons for a Type 2 error: p0.01 (a 1 in 100 probability that chance factors were responsible) or p0.001 (a 1 in 1000 probability that chance factors were responsible) may be too strict for the type of experiment or correlation. A strong difference or correlation may be ignored because the level that has been selected is too demanding for that investigation.Choosing Statistical TestsYou use chi-square......if the data have been put into categories, they are classified as nominal data. The results are independent in each cell, and the expected frequencies (i.e. number of entries) in each cell are greater than 4. The appropriate inferential test to use is therefore a chi-square test.You use Spearman’s rho......if a test of correlation is needed as the hypothesis predicted a correlation. The data involved ratings made by participants that are ordinal data so Spearman’s rho is chosen.You use Mann–Whitney......if a test of difference is required because the hypothesis predicts there will be a difference between the two groups. The design is independent groups, and the data were scores on a test (ordinal or interval data). Therefore the Mann–Whitney test is suitable (test of difference, independent groups).You use Wilcoxon......if a test of difference is required because the hypothesis predicts there will be a difference between the two conditions. The design is repeated measures or matched pairs as all participants were tested twice. The data is interval (a true zero) or ordinal, so a Wilcoxon test was chosen.YesNominal data?(i.e. in categories?)Chi-squaredNoYesYesNoNoNoIndependent groups? Correlation? Wilcoxon T Mann-Whitney U Spearman’s Rho Step 4: Find the critical value of rhoStep 5: State the conclusion left3083437Step 2: Record the data63798451041400Step 1: Write the hypothesesNull hypothesis??Alternative hypothesisWhy would you choose a Spearman’s rho test?1. ?2. ?3. Step 3: Find the observed value of rho (correlation coefficient)right2698455Step 5: State the conclusion Step 3: Find the observed value of UStep 2: Record the data and allocate pointsTest score with no music (?/10)Points Test score with iPod (?/10)Points7?5?8?6?5?3?7?7?9?3?10?8?7?2?5?5?8?6?N1= 9?N2 = 9?Step 4: Find the critical value of U ____________-1968502857500Step 1: Write the hypothesesNull hypothesis??Alternative hypothesisWhy would you choose a Mann-Whitney test?1. ?2. ?3. Step 5: State the conclusion Step 3: Find the observed value of TStep 2: Record the data, calculate the difference between scores and rankPptWith iPodNo iPodDifferenceRank156????245????333????467????554????678????734????-1803402721610Step 4: Find thecritical value of TWhy would you choose a Wilcoxon test?1. ?2. ?3. Step 1: Write the hypothesesNull hypothesis??Alternative hypothesisWhy would you choose a Chi-Square test?1. ?2. ?3. Step 1: Write the hypothesesNull hypothesis??Alternative hypothesisStep 2: Draw the contingency tableMaleFemaleTotals≤10 cigarettes12921>10 cigarettes71017Totals191938?Step 4: Add all the values in the final column to find ______________ the observed value??Row x column / total = expected frequency (E)Subtract expected value from observed value, ignoring signs (O-E)Square previous value(O-E)2Divide previous value by expected value (O-E)2/ECell A21x19/38= 10.5??2.25???Cell B?21x19/38= 10.5??2.25??Cell C17x19/38= 8.5??2.25??Cell D?17x19/38= 8.5???2.25??Step 4: Add all the values in the final column to find ____________ the observed value7773035676275Step 6: State the conclusion Step 5: Find the critical value of chi-square. Degrees of freedom = (rows—1) x (columns –1) ??Step 3: Find observed value by comparing observed and expected frequencies for each cellStep 4: Add all the values in the final column to find ______________ the observed valueStep 4: Add all the values in the final column to find ______________ the observed valuePractice QuestionsH1 = There is a significant association between subject studied and personality (2-tailed)H0 = There is no significant association between subject studied and personalityWhich test will you choose?χ2 = 1.72 df = 5 (degrees of freedom)Critical value = p0.05 (significance level for a 1-tailed test)Accept… Reject… H1 = There is a significant correlation between shoe size and attractiveness rating (2-tailed)H0 = There is no significant correlation between shoe size and attractiveness ratingWhich test will you choose?N = 7r = 0.52Critical value = p0.05 (significance level)Accept…Reject…H1 = People with pink hair score significantly higher in IQ tests than people without pink hair (1-tailed)H0 = There is no significant difference in IQ test scores between those with and without pink hairWhich test will you choose?N1 = 15 (number of people in the smaller group)N2 =14 U = 128Critical value = p0.05(significance level)Accept…Reject…H1 = There is a significant difference in the number of comprehensible words spoken by participants before and after alcohol has been consumed (2-tailed)H0 = There is no significant difference in the number of comprehensible words spoken by participants before and after alcohol has been consumed Which test will you choose?N = 6 T = 3Critical value = p0.05 (significance level)Accept…Reject…Statistical TestsCreate a revision resource on this page to help you remember three reasons why you would choose each statistical test.Qualitative DataIdentify three methods which you could use to collect qualitative data. Three different ways in which you might analyse qualitative data: Interpretative phenomenological analysis Grounded theory Discourse analysisSelect two studies that you are familiar with (from AS or A2) and give details of both quantitative and qualitative data collected in the study. Now fill in the table below:QuantitativeQualitativeWhat does ‘triangulation’ mean?What does ‘reflexivity’ mean?Remember this from AS?Type of dataAdvantagesDisadvantagesQuantitativeEasier to analyseCan be summarised into graphsCan draw neat conclusions due to numerical data Oversimplifies human experience into numbers QualitativeRepresents how complex human behaviour isGains access into human thoughtsProvides rich details More difficult to detect patterns and draw conclusionsSubjective analysis can occur due to personal expectations and beliefscenter-695960centercenter-388398-446316-43092816270324774270centerPast Paper-384736386597January 2013-38473613944004614781-513774Past PaperPSYA4 June 2012Past Paper438086525090-25714586124PSYA4 January 2011PSYA4 – Psychological Research and Scientific Method ChecklistUse this checklist to ensure that you have covered all the areas needed for success in your exams. The following topics will be covered in class. However, it will be your responsibility to catch up with any topics you miss and to actively revise the different areas.Remember – you also need to revise your AS research methodsTopic AreaCovered in ClassRevisedThe application of scientific method in psychologyThe major features of science, including replicability, objectivity, theory construction, hypothesis testing, the use of empirical methodsValidating new knowledge and the role of peer reviewDesigning psychological investigationsSelection and application of appropriate research methodsImplications of sampling strategies, for example, bias and generalisingIssues of reliability, including types of reliability, assessment of reliability, improving reliabilityAssessing and improving validity, including internal and externalEthical considerations in design and conduct of psychological researchDesigning psychological investigationsAppropriate selection of graphical representationsProbability and significance, including the interpretation of significance and Type 1/Type 2 errorsFactors affecting choice of statistical test, including levels of measurementThe use of inferential analysis, including Spearman’s Rho, Mann-Whitney, Wilcoxon, Chi-SquaredAnalysis and interpretation of qualitative dataConventions of reporting on psychological investigations ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download