HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE Chapter 1: Before You Begin ................................................................................................2 Chapter 2: Planning an Experiment ......................................................................................2 Chapter 3: Experimental Designs ..........................................................................................2 Different methods for doing research ......................................................................................3 Observational methods .........................................................................................................3 Quasi-experimental designs ..................................................................................................3 Experimental research / designs ...........................................................................................4 Chapter 4: Descriptive Statistics ...........................................................................................5 Frequency distribution / histogram ..........................................................................................5 Normal distribution ...............................................................................................................5 Positively skewed distribution ...............................................................................................5 Negatively skewed distribution .............................................................................................5 The mode...................................................................................................................................6 Advantages ............................................................................................................................6 Disadvantages .......................................................................................................................6 The median ................................................................................................................................6 Advantages ............................................................................................................................6 Disadvantages .......................................................................................................................6 The mean ...................................................................................................................................6 Chapter 9: A Quick Guide to Writing a Psychology Lab-Report ..............................................6 Things to include in a lab-report ...............................................................................................6 Title and abstract ..................................................................................................................6 Introduction ...........................................................................................................................7 Method ..................................................................................................................................7 Results ...................................................................................................................................7 Discussion ..............................................................................................................................7 References .............................................................................................................................8 Chapter 11: Answering the Question ‘Why?’ The Introduction Section .................................8 Chapter 12: Answering the Question ‘How?’ The Method Section ........................................8 The Design section .................................................................................................................8 The Participant section ..........................................................................................................8 The Apparatus section ...........................................................................................................9 The Procedure section ...........................................................................................................9 Chapter 13: Answering the Question ‘What Did I Find?’ The Results Section .........................9 The results section ....................................................................................................................9 Descriptive statistics ..............................................................................................................9 Inferential statistics ...............................................................................................................9 Some commonly used statistical symbols and abbrevations .................................................10 Chapter 14: Answering the Question ‘So What?’ The Discussion Section ............................. 10 Chapter 15: Title, Abstract, References and Formatting ...................................................... 10 The Title ...................................................................................................................................10 1 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE Chapter 1: Before You Begin This chapter has explored the reason why scientists conduct experiments to answer research questions. It began by looking at why scientists meaasure things – to make research conclusions comparable across researchers. In addition, we started to think about the way in which we measure things and the different levels of measurement. This led to a discussion of why experimentation is valuable for isolating cause and effect and to discuss some different philosofical ideas about causality. Ultimately it was discovered that to isolate causal variables it’s necessary to look at situations in which the supposed cause is present (an experimental group) and compare it against a situation in which the cause is absent (a control condition). Finally, these ideas were used to look at how theories develop using Popper’s idea about falsification and an example of when a control group might not actually act as a control was considered. It was also discovered that one could use probability to determine the ability of someone to detect when milk is added to tea – which was a bonus! Chapter 2: Planning an Experiment The chapter has described some of the initial stages in experimental design. This isn’t the whole story though, it’s just food for thought. It looked at how to refine a research question by exploring databases of research material and how it’s possible to narrow these sources down to a specific question. It’s not possible to answer everything with one experiment so it’s generally needed to constraining oneself to a very specific question (and this question must be a scientific statement: something that is testable). Once a question is defined, one has to think about what variables to manipulate (the independent variables) and what one wants to measure (the dependent variables). In considering how to measure the dependent variables it’s necessary to consider what type of measure to use (physiological, behavioural or self-report) and how best to construct these measures. If self-report measures are used then it is important to try to ensure that the measure produces the same results in identical circumstances (reliability), and that it measures what is wanted to measure (validity). Chapter 3: Experimental Designs There are many issues that have to be considered in designing an experiment, but if one of the standard experimental designs described in this chapter is used, one should be well on the way to producing a study which will provide reliable and valid results. There is no one perfect design, because the optimal design will depend on the particular circumstances. However: 2 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE 1. Define precisely what it is you want to measure. 2. Before running the study, think carefully about what statistics you are going to use. 3. Sample the appropriate population to obtain suitable participants. Sometimes you can get away with using students, sometimes you can’t. You may want to use a particualr population. 4. Decide which design is most appropriate for your particular circumstances. Keep the design as simple as you can. 5. Having obtained a result, you have to assess its reliability and its validity. One way to do this is by using multiple converging operations: investigate the same phenomenon from different angles by using different techniques, participant groups, dependent variables etc., to ensure that your results are not specific to your particular original study. 6. You must behave ethically when you conduct research. Participants must give informed consent to participating in your study. Avoid deceiving them or exposing them to physical or mental harm. Once they have finished the experiment, give them an explanation of what is was all about, and make sure they leave in as good a state of mnd as they were in when they arrived! Different methods for doing research Observational methods enables the researcher to get a good idea of how people normally/really behave (which may differ from how they behave in an experiment). more time-consuming than experiments. it’s more difficult to identify cause and effect Quasi-experimental designs the experimenter doesn’t have complete control over the independent variable (e.g. age). Types of quasi-experimental design: One group post-test design Treatment Measurement One group pre-test / post-test design Measurement Treatment Measurement Interrupted time-series design M M M T M M M time 3 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE The static group comparison design (the participants are not assigned to the two conditions randomly) Group A: Treatment Experimental group Measurement Group B: No treatment Control group Measurement Experimental research / designs randomization is essential (to avoid bias) Between-groups (or ‘independent measures’) designs: use separate groups of participants for each of the different conditions in the experiment. Each participant is tested once only. Post-test only / control group design Group A: Treatment Experimental group Measurement Group B: No treatment Control group Measurement Random allocation Pre-test/post –test / control group design Group A: M Treatment Experimental group M Group B: M No treatment Control group M Random allocation The Solomon four-groups design Group A: M Treatment M Group B: M No treatment M Treatment M No treatment M RA Group C: Group D: An experiment with multiple levels of one independent variable 4 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE Group A: M Treatment Level A M Group B: M Treatment Level B M Group C: M Treatment Level C M Group D: M No treatment Control group M RA Within-subjects (or ‘repeated measures’) designs: each participant is exposed to all of the conditions of the experiment Basic two-condition repeated measures design Treatment M No treatment M No treatment M Treatment M RA Chapter 4: Descriptive Statistics Frequency distribution / histogram a graph of how many times each score occurs Normal distribution a bell-like shaped curve Positively skewed distribution the frequent scores are clustered at the lower end Negatively skewed distribution the frequent scores are clustered at the higher end Platykurtic distribution many scores in the tails and looks flat – the scores are far from the mean Leptokurtic distribution thin in the tails and looks pointy – the scores are close to the mean 5 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE The mode = the most common score / the score with the highest frequency if a data set has two modes it is known as bimodal if it has several modes it is called multimodal A bimodal distribution: Advantages can be used with nominal data Disadvantages even a single score can dramatically alter the value of the mode The median = the middle score of a distribution of scores when they are ranked in order of magnitude 1. Arrange the scores into ascending or descending order 2. Position of middle score is found by Error! (n = the number of scores) 3. If there’s an even number of scores, the median is half way between two, and it is then found by averaging the two scores Error! x = score Advantages it’s relatively unaffected by extreme scores at either end of the scale (outliers) if the distribution is skewed, the median is less affected by this than the mean can be used with ordinal, interval and ratio data Disadvantages cannot be used with nominal data large samples are more reliable The mean = the sum of all scores divided by the number of scores = Error! Chapter 9: A Quick Guide to Writing a Psychology Lab-Report Things to include in a lab-report Title and abstract a clear and informative title (10-15 words) the abstract is a clear summary of the study’s aims, methods, findings and conclusions (max. 150 words) 6 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE Introduction summarize relevant experimental findings and theories which relate to the aims of your experiment. Use this information to provide a justification for why your experiment is worth doing. outline your proposed experiment make specific predictions about the outcome of the experiment, on the basis of the literature you have reviewed. Method include sub-sections on: design, participants, apparatus and procedure make sure there is enough relevant detail for the reader to be able to repeat the experiment purely by reading the method section Design section: identify the independent and dependent variables, and say whether you used independent measures, repeated measures or a mixed design give relevant background characteristics of the sample of participants, as well as saying how many took part write the apparatus and procedure section in proper English, and not like a recipe Results make sure you have clearly described the results and explained whether the evidence (in general) supports the hypothesis under considerations. Describe them, but leave interpretations (in terms of relationship to theories and previous experimental work) until the discussion section. if you have a fair amount of numerical data, put it in a table or graph number the tables and figures so that you can refer to them in the text. Figures and tables are numbered independently of each other make sure each table and figure is clearly labelled and has a self-explanatory title make sure tables and graphs are intelligible without reference to the text, and vice versa where inferential statistics are used, indicate the statistic that was used (e.g. t, F, etc.). Give the value of the statistic used, the number of degrees of freedom, the level of significance reached and whether the test was one-tailed or two-tailed. put raw data and statistical calculations in an appendix, not in the main text remember to include means and standard deviations (or medians and ranges or semiinterquartile ranges, if these are more appropriate). Discussion summarize the main results provide some interpretation of what your results mean, in theoretical terms indicate clearly whether or not your initial hypothesis has been accepted discuss your own data with reference to other experimental findings and theories in the area, particularly those summarized in the introduction identify potential problems with your study, but don’t produce a litany of trivial criticisms. Make intelligent suggestions for future studies. 7 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE References give only the surname(s) of the author(s) and the date of the publication in the text, unless it is a direct quote – in which case give the number of the page on which the quote can be found if a source you have used (e.g. Smith, 1991) cites an author to whom you wish to refer (e.g. Bloggs, 1950), it must appear in the text as follows: ‘Bloggs (1950, cited in Smith, 1991)’. Smith (1991) should be the reference which appears in the list at the end of your report, not Bloggs. Chapter 11: Answering the Question ‘Why?’ The Introduction Section the introduction’s main purpose is to explain to the reader the reasons why you did your study. What has been done in this area before? Why is your study worth doing? introductions normally have three main parts: a description of relevant previous research and theories; a brief outline of your experiment; and an informal summary of what you expect to find and what your findings might imply theoretically. reasons for doing a study include all or some of the following: to test a theory; replicate or extend previous findings; or to try to resolve anomalous or contradictory findings from previous work. in referring to previous research, make sure you stick to studies which are directly relevant to your own, and avoid going into too much detail about them. the introduction ends with a statement of what you expect to find Chapter 12: Answering the Question ‘How?’ The Method Section The ‘Method’ section sub-divides into the ‘Design’, ‘Participants’, ‘Apparatus’ and ‘Procedure’ sections. Together they give the reader enough details for them to replicate the study should they wish to do so. The Design section outlines the formal structure of the study identifies the experiment’s independent and dependent variables tells the reader whether you used independent-measures, repeated-measures or mixed design The Participant section gives relevant details of the people who took part in the experiment 8 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE The Apparatus section provides information on what equipment you used to rum your experiment. (‘Equipment’ may include questionnaires, pencil and paper tests, computers etc.) The Procedure section describes how you actually carried out the study in practice Chapter 13: Answering the Question ‘What Did I Find?’ The Results Section The results section this section tells the reader what you found, but leaves the interpretation of your results for the next section (the Discussion). you may need to ‘tidy’ your data before analyzing them, but this has to be done in an honest way – you shouldn’t discard participants data just because they didn’t fit in with what you expected to find! this section will normally consist of descriptive statistics and inferential statistics. statistical calculations (whether by hand or computer) and raw data should not appear in the results section: if they must be included, put them in an appendix. Descriptive statistics may be presented within the text of the results section, in a table, or in a graph. If you use tables or graphs, they should be labelled clearly enough for them to be understandable without reference to text of the report. Inferential statistics are usually (but not invariably) presented within the text of the results section. They should be presented in a standard way, and accompanied by a brief explanation of what they show. 9 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE Some commonly used statistical symbols and abbrevations ANCOVA df H LSD MANOVA MS N ns R r2 SD SS U < X2 Analysis of Covariance Degrees of freedom Kruskal-Wallis test statistic Fischer’s Least Significant Difference test Multivariate Analysis of Variance Mean Square Total number in a sample / Numbers of members in an entire sample Non-significant Multiple correlation Coefficient of Determination (Pearson’s correlation squared) Sample standard deviation Sum of squares Mann-Whitney test statistic Alpha: probability of a Type 1 error less than Chi-squared test statistic ANOVA F HSD M Analysis of Variance F-ratio (ANOVA test statistic) Tukey’s Honestly Significant Difference test Mean Mdn MSE n Median Mean Square Error Numbers of members in a subset taken from en entire sample p r rS Probability Pearson’s correlation coefficient Spearman’s correlation (‘rho’) SE / SEM T > Standard error (of measurement) Wilcoxon’s test statistic Sigma: Population standard deviation Beta: probability of a Type 2 error greater than Chapter 14: Answering the Question ‘So What?’ The Discussion Section The purpose of the Discussion is to interpret the results that you have found, in relation to previous research: how do your findings fit in with what’s already known on the topic in question? The Discussion has three main parts: 1. A brief recapitulation of your main findings 2. A discussion of how these results fit in with previous research in this area 3. A discussion of possible problems and limitations with your study, perhaps with intelligent suggestions for future research. As with the Introduction, make sure that the research and theories that you describe are relevant to your own study. Chapter 15: Title, Abstract, References and Formatting The Title 10 to 12 words long include a mention of the independent variables and the dependent variables in the study 10 HOW TO DESIGN AND REPORT EXPERIMENTS BY ANDY FIELD & GRAHAM HOLE 11