Research Methods Flashcards
1
Q
Ethics definition
A
Moral principles that govern a persons behaviour or how they conduct an activity.
2
Q
Name ethical issues
A
Lack of informed consent, Deception, Protection of participants from harm, Confidentiality, Debriefing, Privacy, Right to withdraw
3
Q
How does the ‘British Psychological Society’s Code of Ethics’ help deal with ethical issues?
A
BPS regularly updates its ethical guidelines which tells psychologists what behaviours are not acceptable and give guidance.
4
Q
How do universities and other institutions where research is carried out help with ethical issues?
A
They have ethics committees to ensure that the rights of all participants are respected.
5
Q
How is informed consent dealt with?
A
Participants are asked to formally indicate their agreement.
Prior general consent - participants are told that they may be deceived about the true purpose of the study. Only the ones who agree will take part.
6
Q
How is deception dealt with?
A
The need for deception should be approved by an ethics committee.
Participants should be fully debriefed after the study and given the opportunity to withhold their data.
7
Q
How is the Right to Withdraw dealt with?
A
Participants told at the beginning of the study that they have the right to withdraw at any time.
They should also be told that they have the right to withdraw their data.
8
Q
How is protection from harm dealt with?
A
Any risk greater than every day life should be avoided.
Stop the study if it has more of an effect on participants than originally expected (e.g. Stanford Prison Experiment by Zimbardo).
9
Q
What are laboratory experiments?
A
Experiments conducted in a lab in a controlled environment whereby the independent variable is manipulated, whilst all other extraneous variables are strictly controlled.
10
Q
What are the strengths of laboratory experiments?
A
Easy to control extraneous and independent variables.
Easy to replicate if carried out well and reported clearly. Meaning it can be done again and if results are similar confidence is increased in the study.
11
Q
What are the limitations of laboratory experiments?
A
Loss of ecological validity - High level of control means the experiment becomes artificial producing unnatural behaviour.
Demand characteristics - participants try and make sense of the situation and act accordingly.
12
Q
What are field experiments?
A
Experiments in a natural setting, rather than the comparatively artificial setting of the lab. Consequently, extraneous variables are difficult to control.
13
Q
What are the strengths of field experiments?
A
Improved ecological validity - natural setting so reflects real life.
Reduction of demand characteristics - usually unaware they are being studied.
14
Q
What are the limitations of field experiments?
A
Extraneous variables - in the real world you cannot control them making it hard to replicate exactly the same.
Ethical issues - as they are unaware the are being studied they cannot give informed consent.
15
Q
What are natural experiments?
A
Experiments where the IV occurs naturally but what is being tested only happens to certain people e.g. gender, the effect a bad childhood has on a person or schizophrenia.
16
Q
What are the strengths of natural experiments?
A
Study of sensitive issues - it allows research where an IV can’t be directly manipulated.
High external validity - these studies usually involve the study of real life issues and problems as they happen, meaning they are more realistic.
Less demand characteristics.
17
Q
What are the limitations of natural experiments?
A
Loss of control - no control over extraneous variables meaning that is it difficult to replicate.
Expensive and time consuming.
Desired behaviour being displayed.
18
Q
What are quasi experiments?
A
Experiments where the IV occurs naturally and the variables simply exist e.g. being old or young - age.
19
Q
What are the strengths of quasi experiments?
A
Carried out under controlled conditions so same strengths of a laboratory experiment.
Easy to control extraneous and independent variables.
Easy to replicate if carried out well and reported clearly.
20
Q
What are the limitations of quasi experiments?
A
Cannot randomly allocate participants to conditions and therefore may be confounding variables.
21
Q
Aims definition
A
The general investigative purpose of the study.
22
Q
What are the IV and the DV?
A
The independent variable is manipulated by the experimenter. The dependent variable is the one which is measured by the experimenter.
23
Q
Hypotheses definition
A
Every experiment must have two clear statements: the null hypothesis and the alternative hypothesis.
Null - IV no effect on DV.
Alternative - IV will have an affect on DV.
- non-directional - no prediction.
- directional - prediction.
24
Q
What are extraneous variables?
A
The variables that have an effect on the DV that isn’t the IV. They are essentially nuisance variables - the ones that aren’t a major problem.
25
What are confounding variables?
The variables that the researcher failed to control, they are the bigger problems that effect the DV.
26
What are the demand characteristics?
Participants try and make sense of the new situation and act in the way they think is expected.
27
What are investigator effects?
Unwanted influences on the experiment which effects the research outcome.
28
What is randomisation?
Used to minimise the effect of extraneous/confounding variables on the outcome. The chance to reduce the researchers influence.
29
What is standardisation?
All participants should be subject to the same environment, information and experience.
30
What is meant by the term Random allocation?
An attempt to control for participant variables in an independent groups design which ensures that each participant has the same chance of being in one condition as any other.
31
What is meant by the term Counterbalancing?
An attempt to control for the effects of order in a repeated measures design: half the participants experience the conditions in one order, and the other half in the opposite order.
32
What is a repeated measure?
A repeated measure design involves using the same subjects in each condition of an experiment.
33
What are the strengths of repeated measures?
+Subject variables - individual differences shown by every subject e.g. intelligence is kept constant between condition.
+Better statistical tested can be used because of less variation between conditions.
+Fewer subjects are required therefore it is more economical.
34
What are the weaknesses of repeated measures?
- Order effects - learning or boredom may become constant errors when conditions done one after another - better due to practice.
- Demand characteristics - participants may guess the aim if done twice so act differently.
35
What is a independent measure?
An independent measures design involves using different subject in each condition of the experiment.
36
What are the strengths of independent measures?
+Order effects - learning or boredom do not influence as only one condition.
+Demand characteristics - less of a problem as subject only participants in one condition - less likely to guess the aim.
+Same test can be used e.g. memory test.
37
What are the weaknesses of independent measures?
- Subject variables differ - which could become confounding variables unless controlled for.
- Worse statistical tests can be used because of more variation between conditions.
- More subjects are required (because each is used only once) and it, therefore, less economical.
38
What are matched pairs?
A matched pair design involves using different but similar subject in each condition.
39
What are the strengths of matched pairs?
+Subject variables are kept more constant between conditions.
+Better statistical tests can be used because of less variation.
+Demand characteristics are less of a problem as only exposed to one condition.
+Same test can be used e.g. memory test.
+No order effects as only one condition each.
40
What are the weaknesses of matched pairs?
- Subject variables can never be perfectly matched in every respect.
- Matching subjects is very time consuming and difficult.
- More subject required therefore less economical.
41
What is a random sample?
A technique for obtaining participants, whereby every member of the population has an equal chance of being selected.
42
What are the strengths of a random sample?
It is unbiased as all members of the population have an equal chance of selection.
43
What are the limitations of a random sample?
It is difficult and time consuming to conduct; it does not guarantee a representative sample, and selected participants may refuse to take part.
44
What is a systematic sample?
A sample collected in a sequence so when every nth member of the target population is selected.
45
What are the strengths of a systematic sample?
This avoids researcher bias and is usually fairly representative.
46
What are the limitations of a systematic sample?
This is less effective than random sampling because it can’t be claimed that every member of the population is equally likely to be selected.
47
What is a stratified sample?
A sample reflecting the composition of the population, for instance 20 per cent left hands individuals, 80 per cent right handed individuals in the population would determine a selection of participants using the same percentage.
48
What are the strengths of a stratified sample?
Produces a representative sample as it is designed to accurately reflect the composition of the population. This means that generalisation of findings becomes possible. It also avoids researcher bias.
49
What are the limitations of a stratified sample?
It is very consuming.
50
What is a opportunity sample?
A sampling technique not based on random selection or probability; the researcher selects those who are convenient to him or her as respondents.
51
What are the strengths of a opportunity sample?
It is convenient and less costly in terms of time and money that other sampling techniques.
52
What are the limitations of a opportunity sample?
Researcher bias as it is completely controlled. Unrepresentative as specific area therefore difficult to generalise beyond the sample.
53
What is a volunteer sample?
A sample of participants that select themselves by volunteering.
54
What are the strengths of a volunteer sample?
It requires minimal input from the researcher and is less time consuming than other forms of sampling.
55
What are the limitations of a volunteer sample?
Volunteer bias is a problem as participants are more likely to be helpful, keen and motivated that non-volunteers.
56
What is a pilot study?
Pilot studies are small, trial versions of proposed studies to test their effectiveness and make improvements.
57
What are the positives of a pilot study?
They are helpful in identifying potential issues early, which can be refined before committing to the length and expense of the full study.
58
What is a single-blind procedure?
Where participants may not be told the aim at the beginning. All the attempts to control the effects of demand characteristics.
59
What is a double-blind procedure?
Where neither the participants nor the researcher is aware of the aims of the investigation. This controls both demand characteristics and investigator effects.
60
What are naturalistic observations?
An observation study conducted in the environment where the behaviour would normally occur.
61
What are controlled observations?
An observation study where the researcher control some variables - often takes place in laboratory setting.
62
What are the general advantages of observations?
-Value as a preliminary research tool - careful use of naturalistic observations can lead to identification of in the appropriate hypothesis for further research or may help to save time being wasted on unnaturalistic experiments.
Validity - well performed naturalistic observations can provide a useful check on whether experimental findings apply outside laboratory conditions. This is because they have greater ecological validity.
63
What are the general disadvantages of observations?
Lack of cause and effect - there is no IV and the level of control over potential confounding variable is poor, therefore it is not possible to establish cause and effect from this method.
Observer effects - it is possible that the presence of an observer may affect participants behaviour. Also, the potential exists for bias on the part of the observer through their expectation or interpretations of events.
Categorisation of data - this may be difficult when the behaviour being studies is complicated. For example a child hitting another could be categorised as aggressive or rough and tumble play.
64
What are structured observations?
An observation study using predetermined coding scheme to record the participants’ behaviour.
65
What are unstructured observations?
Observation where there is no checklist so every behaviour seen is written down in an much detail as possible.
66
What is a questionnaire?
A set of written questions that participants fill in themselves.
67
What are the advantages of questionnaires?
Simplicity - once constructed and piloted, questionnaires can be carried out with minimum of training. Specialist administers are not to gather the information. This is a real advantage when compared with interviews, experiments and observations.
Speed - a large amount of data can be gathered from large numbers of participants relatively cheaply and in a short period of time.
68
What are disadvantages of questionnaires?
Problems with question wording - it is difficult to produce questions that do not have some problems. For example, they may be ambiguous and therefore be interpreted differently by participants or they may be leading, directing participants to respond in a certain way.
Unreliable responses - participants may not answer questions accurately. For example, they might show social desirability effects, they may give responses that they think the research is looking for or they may deliberately lie.
Representative sample - response rates to questionnaires tend to be quite low. Those that choose to respond will be a biased sample - literate individuals who are clinics to spend time filling them in.
69
What are open questions?
Questions where there is no fixed responses and participants can give answer they like. They generate qualitative data.
70
What are closed questions?
Questions where there are fixed choices of responses e.g. yes/no. They generate quantitative data.
71
What is meant by qualitative data?
Describes information that is expressed in words.
72
What is meant by quantitative data?
Information that can be measured and written down with numbers.
73
What is a interview?
Involves asking a variety of questions in a face to face setting between the participant and the researcher.
74
What is meant by structured interviews?
Interview where the questions are fixed and the interviewer reads them out and records the responses.
75
What are the advantages on structured interviews?
Can collect rich, detailed information, which would not be possible to obtain in an experiment.
This procedure can be easily repeated as the questions are fixed.
76
What are the disadvantages of structured interviews?
Interviewer effects: the interviewer’s expectations or personal characteristics may influence the answer the interviewee gives.
Participants may show a social desirability effects.
77
What is meant by unstructured interviews?
There are not fixed questions just general aims and it is more like a conversation.
78
What are the advantages of unstructured interviews?
Can collect rich, detailed information, which would not be possible to obtain in an experiment.
This procedure allows for greater flexibility. The interview tailors questions to the responses of the interviewee so that issues can be explored in depth.
79
What are the disadvantages of unstructured interviews?
Interviewer effects: the interviewer’s expectations or personal characteristics may influence the answer the interviewee gives.
Participants may show a social desirability effects.
80
What is meant by semi-structured interviews?
Interview that has started some pre-determined questions, but the interviewer can develop others in responses to answers given by the participant.
81
What are the advantages of semi-structured interviews?
Can collect rich, detailed information, which would not be possible to obtain in an experiment.
This procedure allows a little flexibility. The interviewer tailors questions to the responses of the interviewee so that issues can be explored in depth.
82
What are the disadvantages of semi-structured interview?
Interviewer effects: the interviewer’s expectations or personal characteristics may influence the answer the interviewee gives.
Participants may show a social desirability effects.
83
What are correlations?
Correlation illustrates the strength and direction of an association between two co-variables. Co-variables are the things that are being measured. It refers to a statistical analysis of scores that are paired (i.e. the co-variables) for example, hours spent watching violent TV and the number of anti-social behaviours performed in a week. It is a non-experimental technique and therefore, does not identify cause and effect, but rather, the relationship strength and direction between two naturally occurring variables.
84
What are the key points of correlations?
* A correlation tells us whether 2 variables are related.
* A positive correlation is when high values on 1 variable are associated with high values on another variable.
* A negative correlation is when high values on 1 variable are associated with low variables on another.
* Correlations vary from +1 to -1 and can be more accurately detected using a statistical test such as Spearman’s rho.
* The closer the value is to 1, the stronger the correlation.
* A zero correlation is when there is no relationship between 2 variables.
* A correlatgvtion can be displayed on a scatter graph.
85
What are the advantages of correlations?
+ A correlation is a useful way to examine variables that cannot be manipulated experimentally for practical or ethical reasons.
+ E.g. Stressful life events and heart disease.
+ Aggression score and time spent in day care.
86
What are the disadvantages of correlations?
- A correlation does not mean there is a cause and effect relationship between the 2 variables.
- Even if 2 variables are strongly correlated this does not mean that a change in one variable causes a change in the other.
- E.g. hours of violent TV watched and scores on an aggressive scale.
87
What is an experiment?
An experiment manipulates (changes) an independent variable, measures a dependent variable while keeping all other variables constant.
This enables cause and effect to be established.
A change in one variable causes a change in the other.
88
What is the difference between correlation and experiments?
Correlations, unlike experiments, are not looking for a difference in the results as a consequence of what has been manipulated by the researcher. Rather, they are looking for the relationship between 2 co-variables i.e. as one increases, what happens to the other one?
As there is no manipulation of an IV, it is not possible to establish a cause and effect relationship between one co-variable and another. For example there is a relationship between the colour of grass and ice-cream sales. The more yellow the grass gets the more ice cream is sold. However, in this case the causal variable is obviously temperature.
Psychologists have suggested a correlation between watching TV violence and aggressive behaviour. This does not suggest that TV violence causes aggressive behaviour simply that there is a relationship between them.
89
What are the advantages of experiments?
+ Detecting Patterns - it is a useful method for detecting patterns in data and seeing how 2 variables relate to each other. From this, predictions can be made about the likely value of one variable when we only have information about the other.
+ Eliminating cause and effect - although correlations cannot establish cause and effect they can eliminate it. If no association is found, it can be said that there is no cause and effect between the two variables being studied.
+ Large amounts of data - it is often possible to obtain amounts of data on a number of variables more rapidly and efficiently than with experimental designs.
90
What are the disadvantages of experiments?
- Cannot establish cause and effect - we cannot say which of the variables led to a change in the other or whether a third variable was involved.
- Curvilinear relationships - simple correlation analysis is unable to pick this up. Care must be taken to examine the scatter graph to ensure that it shows an appropriate linear pattern.
91
What is validity?
Validity – refers to the extent to which something measures/investigates what it’s supposed to measure. For example, does a personality test really measure personality?
92
What is internal (experimental) validity and external (ecological) validity?
* Internal (experimental) validity - This refers to the experiment itself. A researcher needs to ask whether it really was the independent variable that produced the change in the dependent variable. In other words, is it a genuine effect? To make sure that it is a genuine effect researchers must keep all confounding variables under control. The greater control over these variables the more confident the researcher can be that the experiment is valid.
* External (ecological) validity - This refers to the extent to which research findings can be generalised. A research study that has high external validity can be generalised to other populations, settings and times. Researcher can increase the external validity of their study by using a wider sample, by partially replicating a study or by making it more realistic.
93
What is reliability?
Reliability – refers to consistency. Without reliability of a measure, the data gained from it is meaningless.
94
How is the reliability assessed in an experiment?
Replication: this refers to repeating an experiment under exactly the same conditions. If the same results are obtained, then those results are seen as reliable.
95
How is the reliability improved in an experiment?
Control of variables
Reducing Investigator effects
Standardisation of Instructions
96
How is the reliability assessed in an observation?
Inter-researcher reliability: this is assessed by measuring the extent to which researchers scoring the same Ps achieve consistency of measurement between each other. Raters record their own data individually and then the sets of data from each scorer are correlated. High inter-rater reliability is indicated by significant positive correlations.
97
How is reliability improved in an observation?
Observers should be trained thoroughly in the techniques being used.
Operational definitions of the key terms involved should be clear and fully understood by all the raters. A behavioural checklist could be used for this.
Discuss problem s and unusual cases.
98
How is the reliability assessed in a test/questionnaire?
Test-retest method: this tests reliability of a test over time. The same Ps are given the same test/questionnaire on 2 separate occasions with no feedback after the first. Correlational tests are used to indicate reliability. A significant positive correlation indicates test-retest reliability.
99
How is the reliability improved in a test/questionnaire?
Revising questions/test items that may be unclear/ambiguous.
Revising testing procedures.
Rephrasing instructions for clarity.
100
What is the aim of science?
The aim of science is to produce a body of knowledge through conducting research. This research is then communicated through the use of scientific journals. Before this research is published, it must be subject to the process of peer review.
101
What is peer review?
Peer review is the assessment of scientific work by others who are specialists in the same field to ensure that any research intended for publication is of high quality. It involves all aspects of the investigation being scrutinized by a small group of experts (peers) in the particular field. These experts should be objective, have no vested interest and unknown to the author or researcher.
102
What are the aims of peer review?
1. To validate the quality and relevance of the research
2. To suggest amendments or improvements
3. To allocate research funding
4. To prevent the publication of fraudulent research.
103
What is qualitative data?
Qualitative data – expressed in words, rather than numbers or statistics, and may take the form of a written description of the thoughts, feelings and opinions of participants (or a written account of what the researcher saw in the case of an observation). Thus, a transcript from an interview, questionnaire responses to an open question, an extract from a diary or an observer’s unstructured observation would yield qualitative data.
104
What are the evaluating points of qualitative data?
+ Rich in detail, compared to quantitative.
+ Greater external validity than quantitative.
- Difficult to analyse and make comparisons.
- Conclusions often rely on the subjective interpretations of the researcher.
105
How is qualitative data analysed?
* Context analysis - Categories of data and Counting frequency.
* Thematic analysis - Read transcripts, Identify themes and Write a report.
106
What is quantitative data?
Quantitative data – expressed numerically. Quantitative data collection techniques usually gather numerical scores from a participant e.g. number of words recalled in an experiment.
107
What are the evaluating points of quantitative data?
+ Easy to analyse and make comparisons.
+ Conclusions are objective - so results can't be ministered.
- Not very rich in detail.
- Has little external validity compared to qualitative data.
108
How is quantitative data analysed?
* Descriptive statistics - Mean, mode, median.
* Measure of dispersion - Range, standard diviation.
* Inferential statistics - Tests.
109
What is primary data?
Primary data – refers to original data that has been collected specifically for the purpose of the investigation by the researcher. It is data that arrives first hand from the participants themselves.
110
What are the evaluating points of primary data?
+ It fits the job – researchers can design their studies specifically, in order that they target the information the researcher requires.
- More time and effort is required, in comparison to secondary data.
111
What is secondary data?
Secondary data – is data that has been collected by someone other than the person who is conducting the research. Secondary data includes data that may be located in journal articles, books or websites.
112
What are the evaluating points of secondary data?
+ Less time and effort is required, in comparison to primary data.
- Doesn’t always fit its purpose – the research might not suit their study specifically.
113
What is meta-analysis?
Meta-analysis – this is a particular research method that uses secondary data. It refers to a process where the data from a large number of studies, which have used the same research questions and methods, are combined. It is ‘research about research’. The researchers may perform a qualitative and/or quantitative analysis of the studies. It may involve calculating the ‘effect size’ which gives the overall statistical measure of difference or relationship between variables across a number of studies.
114
What are the evaluating points of meta-analysis?
+ Greater confidence in the findings
+ Results can be generalised across much larger populations
- Prone to publication bias – the researcher may omit studies, especially those with negative or non-significant results.
115
What is descriptive statistics?
Descriptive statistics is the term given to the analysis of data that helps describe, show or summarise data in a meaningful way such that, for example, patterns might emerge from the data.
116
What are measures of central tendency?
Measures of central tendency give average scores in a set of data.
117
What does the measures of central tendency involve?
Mean
Median
Mode
118
What is the mean?
The middle value of a set of numbers that has been placed in numerical order.
119
What are the advantages and disadvantages of the median?
+ It takes all the scores into account therefore all data is represented.
- When extreme scores are present the mean is not an accurate measuring tool. This is because the anomalies will distort the mean and make it unrepresentative.
120
What is the median?
The middle value of a set of numbers that has been placed in numerical order.
121
What are the advantages and disadvantages of the median?
+ It is unaffected by extreme scores. This means it is most appropriate measure when there is an anomaly.
- It does not take into account all of the scores and is therefore less sensible that the mean.
122
What is the mode?
The value that occurs most frequently in any set of scores.
123
What are the advantages and disadvantages of the mode?
+ It is unaffected by anomalies as by definition, there will be few of them.
- It tends to be unstable, as if there are only a few scores representing each value, then even very small changes in the data can radically affect the mode.
124
What are measures of dispersion?
Measures of dispersion tell us how widely the data is spread.
125
What does measures of dispersion involve?
Range
| Standard Deviation
126
What is the range?
The difference between the highest and the lowest score in any condition +1.
127
What are the advantages and disadvantages of the range?
+ Easy and quick to calculate.
| - Vulnerable to rogue scores i.e. a very high or low score - an anomaly.
128
What is the standard deviation?
The mot frequently used measure of dispersion. It s the average amount all scores deviate from the mean.
129
What are the advantages and disadvantages of standard deviation?
+ Gives a more accurate picture of the range.
+ Takes into account all of the scores and provides a sensitive measure of dispersion.
- Vulnerable to rogue scores i.e. a very high or low score.
130
What are the three distinct types of data?
Nominal
Ordinal
Interval
131
What is nominal data?
Data is allocated to categories that are mutually exclusive e.g. male/female or smoker/non-smoker.
132
What is ordinal data?
Data allocated to categorises can be placed in a logical order based on their meaning, however the difference between the values are not the same. E.g. very confident, confident or not at all confident.
133
What is interval data?
Data can be ordered and the intervals on a scale are equal as they are based on a standard unit of measurement. However, the point used to indicate 0 is arbitrary. E.g. IQ scores - it is not possible to claim that someone with an IQ of 120 is twice as intelligent as someone with an IQ of 60.
134
What are the points of histograms?
* Can be used when presenting continuous data on interval or ratio scales of measurement.
* The scores are indicated on the horizontal (x) axis.
* The frequencies are shown on the vertical (y) axis.
* Consists of a series of vertical bars of equal width to represent each score or group of scores.
* The bars on a histogram actually touch.
135
What are the points of bar charts?
* Can be used when the data are in categories (nominal or ordinal) or to illustrate the average scores from different samples.
* The categories are indicated on the horizontal (x) axis.
* The frequencies are shown on the vertical (y) axis.
* Each bar is separated so that a continuous variable is not implied.
* Bars can be presented in any order.
136
What are the points of frequency polygon?
* This is a useful technique when it is necessary to compare two or more frequency distributions.
* Two or more conditions of an experiment can be presented at the same time.
* Can be used when presenting continuous data on interval or ratio scales of measurement.
* The scores are indicated on the horizontal (x) axis.
* The frequencies are shown on the vertical (y) axis.
137
What are the points of scattergrams/scatter graph?
* Used to present correlational data.
* Data from one of the variables is presented on the horizontal (x) axis and data from the second variable is on the vertical (y) axis.
138
What is normal distribution?
The normal distribution is a classic, bell shaped curve. Many human characteristics are normally distributed, such as intelligence and shoe size.
139
What are the features of a normal distribution?
* Mean, median and mode are all in the exact same mid-point.
* The distribution is symmetrical around its mid-point.
* The dispersion of scores either side of the mid-point is consistent and can be expressed in SD’s.
140
What are skewed distributions?
A distribution is negatively skewed, or skewed to the left, if the scores fall toward the higher side of the scale and there are very few low scores. In positively skewed distributions, the mean is usually greater than the median, which is always greater than the mode.
141
What is statistical testing?
Statistical testing provides a way of determining whether hypotheses should be accepted or rejected.
In psychology, they tell us whether differences or relationships between variables are statistically significant or have occurred by chance.
142
What is the sign test?
The sign test is a non-parametric statistical test of difference that allows a researcher to determine the significance of their investigation. It is used in studies that have used a repeated measure design, where the data collected in nominal.
Significance = research findings are sufficiently strong for us to reject the null hypothesis.
143
What are the concept of probability?
All studies employ a significant level in order to check for significant differences. The accepted level of probability in psychology is 0.05 or 5%. This is the level at which the researcher decides to accept the research hypothesis or not.
If the experimental hypothesis is accepted, this means that there is 5% or less probability that the results occurred by chance. In simple terms, this means the researcher can be pretty certain (95%) that the difference found was because of the manipulations of the IV (though there will always be 5% doubt even if significance is found).
In some circumstances, researchers need to be even more confident that results were not due to chance and so employ a stricter, more significant level such as the 0.01 (the 1% level). This is in case where the research may involve a human cost, such as when new drugs are being trailed or where a particular investigation is a one-off and there is no possibility that it can be repeated in the future.
144
What is the critical value in the sign test?
When the statistical test has been calculated the researcher is left with a number – the calculated value. This needs to be compared with a critical value to decide whether the result is significant or not. The critical values for a sign test are given in a table of critical values.
145
What information is required to use the table of critical values?
* The significance level desired (always use 0.05 expect in circumstances described above).
* The number of participants in the investigation (The N value).
* Whether the hypothesis is directional (one-tailed) or non-directional (two-tailed).
146
What are the 6 steps to calculate the significance of a study?
1. We need to take the result before away from the result after. For each calculation we then write in which sign we end up with (+ - 0).
2. Next we simply need to count up the amount of positives, negatives and zeros.
3. We then the lower number out of the sign (except the zero) and that will equal our 's'.
4. We then need an 'N' which is 'number of participants' and we need to minus the zero scores. N=11 minus the number of zero's.
5. We then need to calculate the level of significance to see if there is a statistical difference in these two conditions. Remember that the level of significance in psychology is 0.05 and so basically we want to be 95% sure of our results and we only allow a 5% error rate. Using the significance table and the 'N' state to find the critical value.
6. Now finally we need to see if this 'critical value' is significant. Remember the rule is: The Calculated value of 's' must be equal to or less than the critical value in this table for significance to be shown.
