Science and Statistics

Question 1

What is a logical fallacy?

Answer 1

Logical fallacies are errors in reasoning which may sound convincing but are actually flawed, largely due to lack of evidence supported for them.

Use of invalid or faulty reasoning to construct an argument which might appear to be well reasoned if unnoticed.

Question 2

What are the 3 types of logical fallacies studied in the Psych course?

Answer 2

Argument from authority

Ad hominem

Appeal to antiquity

Question 3

What is ‘argument from authority’ in Psychology? What is an example of this?

Answer 3

It is when you believe something is true just because someone very important said it or endorses it.

An example of this is Linus Pauling who won two Nobel Prizes and is hailed one of the founding fathers of molecular biology. However, because he was so respected and very important in society, basically anything that he said was deemed to be true. As a result, he assisted in spreading the medical misconception that vitamin C prevents colds.

Question 4

What is ‘Ad Hominem’ argument in Psychology? What is an example of this?

Answer 4

This is where you disagree with what someone said but instead of attacking their claim or evidence, you attack them for being of low status or being disreputable.

For example something might go along the lines of ‘Barrack Obama can’t talk about women’s rights because he is a male’ –> apply to scientific world

Question 5

What is ‘Appeal to antiquity’ argument in Psychology? What is an example of this?

Answer 5

This is where you believe that something is true just because it has lasted a long time or has existed for a long time.

For example, ‘Homeopathy has been around for 300 years, so it must obviously work’ –> just because it has existed for a long time, it definitely doesn’t mean it works.

Question 6

What is the MAIN difference between science and pseudoscience

Answer 6

A science is a body of hypothesis based upon observation and experiment. A pseudoscience is a body of hypotheses treated at true, but without a consistent body of supporting experimental evidence.

In simple terms, science is more legit and reliable compared to pseudoscience

Question 7

What are 8 basic characteristics of science?

Answer 7

1. An attitude of humility, wonder, and commitment to understanding the truth. You accept you do not know everything, you appreciate how complex the world is, and you will not rest until the truth is discovered.
2. Understanding the methods used and the methods necessary to generate evidence in science.
3. Being able to distinguish between theories and evidence in science and being committed to fully test the truth of theories using evidence.
4. A realisation that understandings are distinct from the individuals who propose or support them.
5. Accepting that evidence-based conclusions will always be probabilistic in nature, such that science represents a continuous process of improving upon what is known.
6. All theories and evidence must be open to criticism. For this to be possible there must be complete transparency in how evidence was gathered.
7. Systems of standard communication allowing transmission of findings and criticisms to be world-wide. Every science has peer reviewed journals and conferences.
8. Merit based qualifications and grant application procedures which reward skill in research. Skill in research is demonstrated by successfully attacking existing theories and replacing them with better ones.

Question 8

What are 8 basic characteristics of pseudoscience?

Answer 8

1. An attitude of arrogance that the main answer is already known so there is no need for more study and reflection.
2. An acceptance of anecdotal and poorly controlled historical evidence in place of
   systematically collected evidence.
3. An inability to distinguish between theories and evidence, such that only supporting evidence is gathered (confirmation bias), or that attacking the evidence associated with alternative accounts is all there is supporting the theory (appeal to ignorance).
4. An “important” individual (like a cult leader in the past or present) who created the theory and is forever associated with it. Evidence for the theory may be lacking but the individual’s
   endorsement is considered sufficient support.
5. Probabilities (and often mathematics itself) are poorly understood and instead are replaced with certainties.
6. The evidence supporting the theory was collected behind closed doors or by “experts” who never explain what they did to collect it.
7. One way transmission of information such that it may be delivered in conferences and journals but cannot be questioned or criticised.
8. Qualifications are not formalised, or have little value, and can be bought with minimal training or supervision. Status and/or promotions are guaranteed by always supporting and never criticising currently held beliefs.

Question 9

What is the main feature of a pseudoscience compared to science?

Answer 9

Pseudoscience can’t be critiqued because people won’t allow for it to be critiqued –> no progress. This is compared to science where there is constant critique of theories and evidence

Question 10

What are the few questions which can be used to distinguish science from pseudoscience?

Answer 10

Transparency?

System of constant review?

Evidence assessed on merit?

Humility of approaching understanding?

Question 11

What is the replication crisis?

Answer 11

The replication crisis occurs out of a need to be able to replicate the methods utilised in a study to ensure similar results.

However, the issue of ‘replication crisis’ occurs when the results can’t be reproduced or replicated to an acceptable standard despite following the methods.

Question 12

What are some causes of the replication crisis?

Answer 12

Pressure to publish –> leads many scientists to publish papers which often can’t be replicated because of too complicated design or lack of transparency of design due to having to work quickly to reach publication dates

Publications want new findings –> don’t want you to see if some other theory works –> lack of replication

Publications want significant findings –> may manipulate date to meet these expectations which may disprove earlier theories

Results in both experiments are interpreted in a bias way

Scientists attempting replication are unskilled/unsophisticated and are thus unable to replicate findings

Original responses were falsified

Differences in sample sizes (i.e. original might have small sample size compared to the re-do which might have a large sample size –> findings are more accurate compared to original)

(time acting as a confounding factor)Findings in an original study may be true for some people in certain circumstances (such as historically), however might not be true universally or enduring. For example, imagine that a survey in the 1950s found a strong majority of respondents to have trust in gov officials. Now imagine the same survey administered today, with vastly different results –> replication crisis. This doesn’t invalidate the original results but instead suggests that attitudes have shifted over time instead.

Quality of replication ma not be up to standard

Question 13

How do you fix the replication crisis?

Answer 13

pre publish hypothesis and methods (allows careful scrutiny of the method which might lead to its inability to be replicated –> fixing the replication crisis)

Have raw data available(reduces the possibility of misinterpreting data)

Encourage direct replications (copying the method to the point)

Question 14

What is professional integrity?

Answer 14

It involves demonstrating behaviours that are consistent with the standards for professional and ethical conduct.

Thus, for researchers they must have be able to distinguish their personal and professional selves in an ethical context. (Can’t let their personal beliefs override their professional knowledge)

If you have strong personal beliefs which are profoundly different to those supported by science, you either need to set them aside while practising, change them or leave the profession

It depends on your understanding of the relevant science

Question 15

What is an example of having bad professional integrity?

Answer 15

Imagine you become a well known psychologist practising therapy X, but after hours you tweet that therapy X is actually dangerous and therapy Y (for which there is no scientific support) is far better. This would mean allowing your personal factors override your professional side which is an example of bad professional integrity

Question 16

What is the mechanism in science which allows it to succeed?

Answer 16

It is the sense of being always encouraged to critique current theories which have either just been developed or stood the test of time. This allows for better theories to be established which thereby allows science to succeed on a greater scale through advancing knowledge and understanding.

Every scientist is motivated to disprove the old theories (even their own), because of a realisation that the current understanding is not the best

Question 17

Why is transparency important in science?

Answer 17

In research, transparency about the data documentation and storage is important to ensure sound credibility and to allow for the reproducibility of experiments.

Open transparency to scientific knowledge also allows policy makers and public to use research findings to make informed decisions.

More importantly, transparency allows for many things to be critiqued. For example, the method of a certain experiment could be critiqued due to transparency of it –> the experiment can become better

Question 18

Why is scepticism important in science?

Answer 18

Scepticism coupled with curiosity typically inspire scientists to constantly ‘attack’ and ‘doubt’ theories which have been established. This allows for the potential of the theories to be improved and thereby improve our understanding of science.

In science, scepticism involves recognising that the current theories aren’t necessarily perfect. It is thus important to constantly maintain scepticism because no theory is perfect, and science recognises that

Scepticism also allows the researcher to maintain an objective approach to developing research hypohthesis

Question 19

How does transparency and sceptisism allow for the continuous improvement of understanding in science?

Answer 19

Transparency allows for the different methods and evidence for theories to be evident to the public. This thereby allows for many to develop scepticism to certain parts of the theory/evidence. In turn this stimulates even greater analysis and criticism of the current theory.

As a result of this, various other hypotheses are proposed about other possible explanations. Despite having these vast array of possible explanations, a couple may be picked to propose a new theory, which in turn could contribute to a greater understanding of the world.

This cycle continues to exist, thereby allowing for the constant improvement of scientific theories

Question 20

What is critical thinking?

Answer 20

Critical thinking is defined as the mental process of actively and skillfully perception, analysis, synthesis and evaluation of collected information through observation, experience and communication that leads to a decision for action.

Question 21

Should critical thinking skills be used with care and respect?

Answer 21

Yes

Question 22

Why should critical thinking skills be used with care and respect

Answer 22

This is largely because science is effortful for everyone, and while there are some ‘easy to mock’ pseudo sciences out there, almost everyone is a sucker for something.

Additionally, because science is a system founded on probabilities, it doesn’t result in ultimate truths. Thus, although a lot of evidence may point to a certain conclusion, we can’t use our critical thinking skills to assume that that is the only possible right answer. Thus, it has to be used with care when critiquing other people if you have a set topic that you perceive to be true

Question 23

What should you ask people if they believe in some sort of pseudo science?

Answer 23

How much is it costing them, compared to the comfort they are receiving?

is it placing them in any danger?

Is it placing others in danger

Question 24

What are people in science (authorities)?

Answer 24

Ideally science has no authorities or experts which are beyond criticism (or at least a lack of authority).

However, formally authorities in science

Question 25

What are theories in science?

Answer 25

Theories are a formal explanation of the relationship among a set of observations. These observations provide evidence for the theory

Question 26

What is evidence in science?

Answer 26

It is a set of proof for a certain fact or information which indicates whether the belief or proposition is true or valid

Question 27

What is the difference between theories and evidence in science?

Answer 27

Theories utilise evidence to come up with a theory?

Question 28

What is the difference between the people, theories and evidence in science

Answer 28

The people in science are the people who synthesise the evidence to develoop theories Theories are the formal explanation of a certain relationship between presented evidence Evidence refers to a set of proof for certain theories or are rather observations made by the people in science. Evidence may be gathered by people in science

Question 29

Explain how the people, theories and evidence in science interact

Answer 29

The people in science look at the various evidence that they have to develop a theory. In turn, other people in science also analyse the theory and evidence to critique it and potentially come up with a better theory.

Question 30

What is a scientific construct?

Answer 30

It is an idea or theory often expressed as a single word, but containg lots of assumptions and conceptual relationships.

Question 31

Why do scientific constructs need to be as clear as possible?

Answer 31

In science, we use them to make predictions, and without them being clear/if they're convulated, it is harder to create predictions of the scientific construct On top of that, the things we want to measure are very hard to measure and may not even be real, so through ensuring that constructs are measured properly, it needs to be clear what the definition is.

Question 32

What are weasel words?

Answer 32

These consist of vague and misleading terminology, even though it may come across as seemingly certain --> that's what makes it misleading.

Question 33

What are some examples of weasel words?

Answer 33

'may' - implies something probable 'Scientists say that...' 'Clinical studies have shown that...' 'This medicine may help with....' 'Thought to support' 'helps in the maintenance of general health and wellbeing'

Question 34

Why are weasel words used in certain situations?

Answer 34

Used commonly by people selling things such as merchants and politicians because they want to avoid being accountable for claims that they make and may not necessarily end up being true

Question 35

What are the two ways to define a construct? Are they necessary to establish a scientific construct?

Answer 35

Through a conceptual and operational definition Yes they are important in establishing a scientific construct

Question 36

What is a conceptual definition?

Answer 36

This involves describing a construct in terms of what it is and what it isn't and how it might relate to existing theories. Here, examples are often given.

Question 37

What is an operational definition?

Answer 37

An operational definition of a construct is an explanation of how the construct might be measured. Given that there are a number of ways to measure a construct It involves finding a way in which the construct can be observed.

Question 38

Why is the operational definition of a variable not always ideal?

Answer 38

This is because an operational definition is not a construct, a construct can never be measured directly, so just choosing one of the many ways to measure it doesn't make it real Also, they could cause people to hide negative response

Question 39

What does operationalise mean?

Answer 39

Operationalisation means turning abstract concepts into measurable observations

Question 40

What are the factors in creating the method to operationalise a construct?

Answer 40

Which aspect of the construct is important to the research? How much money and time the researchers have What kind of research design is going to be used to study the construct

Question 41

What is falsifiability?

Answer 41

Falsifiability refers to the ability for a certain scientific construct, statement or theory to be proven wrong

Question 42

Why is the concept of falsifiability important to scientific constructs?

Answer 42

This is because falsifiability needs to be applied to theories to determine if it can be confirmed. In other words, if you create something which can't be assessed or measured, then there will never be any way to tell if its real - and it can never be disproven, and as a result you can neither know whether it is actually real or not.

Question 43

What are some examples of non-falsifiable constructs?

Answer 43

Fairies Invisible forces such as Chi and the Force Magic

Question 44

What is reification?

Answer 44

This is when a purely analytic or abstract relationship is treated like a concrete entity. I.e. when an adjective is treated like a noun

Question 45

What is an example of reification?

Answer 45

The best example is 'luck'. It is a concept which many refer to when something good happens such as 'that was lucky!' However, it becomes a problem when it is reified into a thing For example, a gambling addict may have a lucky medallion which contains 'luck' and will reward them in the future. This can lead to further psychological issues Also, the use of reification in logical reasoning is a fallacy because _____?

Question 46

What is pragmatic fallacy?

Answer 46

Pragmatic fallacy is the idea that something MUST be true because it works. This is a further example of the convoluted knots that can be achieved when concepts are tied to objects

Question 47

What is an example of pragmatic fallacy?

Answer 47

For example, just because therapy based on psychoanalytic concepts helps someone feel better, doesn't mean the concepts behind the therapy (id, ego, superego and unconscious desires) are valid, instead the person may just feel better because they talked to someone about their problems Someone might also be politely listened to and treated kindly with needles and then feels better, it doesn't mean that associated concepts such as chi, ki, prana and meridians are valid. They may actually feel better because they have been treated well and acknowledged

Question 48

What are some examples of operationalising constructs

Answer 48

Motivation - rate of button pressing Memory - Number of things recalled Learning - Decrease in time to solve puzzle Personality - Score on questionnaire Arousal - Heart rate, blood pressure Attitude - Number circled on a scale

Question 49

What sort of test can be used in psychology to assist in the operalisation of constructs?

Answer 49

Self report measures

Question 50

What are the downsides to having self report measures?

Answer 50

It is largely because people are dishonest, and often lie in their responses to either not seem too bad or please the researcher.

Question 51

What does a social desirability scale do?

Answer 51

These are questions randomly placed in the survey to determine if people are lying. If someone has high social desirability, it may mean that other answers to questions in the questionnaire may be inaccurate, leading to the scrapping of the responses. Social desirability scale measures the persons tendency to lie in a questionnaire/self report, which may lead to the scrapping of the data essentially

Question 52

What are some sample questions on the social desirability scale? Sample

Answer 52

Note: Response options of True and False should be provided for each statement 1. It is sometimes hard for me to go on with my work if I am not encouraged. 2. I sometimes feel resentful when I don’t get my way. 3. On a few occasions, I have given up doing something because I thought too little of my ability. 4. There have been times when I felt like rebelling against people in authority even though I knew they were right. 5. No matter who I’m talking to, I’m always a good listener. 6. There have been occasions when I took advantage of someone. 7. I’m always willing to admit it when I make a mistake. 8. I sometimes try to get even rather than forgive and forget. 9. I am always courteous, even to people who are disagreeable. 10. I have never been irked when people expressed ideas very different from my own. 11. There have been times when I was quite jealous of the good fortune of others. 12. I am sometimes irritated by people who ask favors of me. I have never deliberately said something that hurt someone’s feelings. 13. I have never deliberately said something that hurt someone’s feelings. Scoring: Add 1 point to the score for each “True” response to statements 5, 7, 9, 10, and 13. Add 0 points to the score for each “False” response to these statements. Add 1 point to the score for each “False” response to statements 1,2,3,4,6, 8, 11, and 12. Add 0 points to the score for each “True” response to these statements. A score of close to 13 means that the person has a strong desire to be socially liked and may indicate that the responses to the questionnaire aren't genuine and were only made to please the researcher.

Question 53

What are anecdotes?

Answer 53

Anecdotes are interpreted stories about a single occurrence in the past, and are usually of no scientific value. They have a small sample size

Question 54

What are the drawbacks/limitations/flaws of anecdotes

Answer 54

Only evidence mentioned in an anecdote is in there to support the theory (no separation of theory and evidence_ --> theory only supported by the evidence mentioned --> results in an in built bias which can be misleading Anecdotes could change with each retelling Because they are based on a single instance/observation, whatever happened cant be replicated by a non biased observer Anecdotes only remembers what the person wants to remember (selective memory) Only focusses on one potential variable and not others (i.e. I am sick, and did treatment X and then I got better, so X has to work. However this ignores other variables and is only focussing on one--> there could still be other factors at work)

Question 55

What are case studies?

Answer 55

These involve an intense study about a person / group / topic, however they aim to document everything, no matter if the researcher thinks it will be relevant or not. (I,e, gathering and acknowledging all data to the field / question, no matter if it supports or disproves the hypothesis). However, they do have a small sample size The key feature is a sense of humility (arising from a desire to discover something not confirm something)

Question 56

What is the main difference which makes a case study better than an anecdote?

Answer 56

Although the case study is still a small sample size, they have several differences / benefits over the anecdotes, which makes them more reliable: Objective nature of notes means that alternative explanations are possible later (not just narrowing down to one explanation) All details whether relevant or not are recorded in a scientific matter --> more systematic Scientific humility is also a key difference (arising from a desire to DISCOVER something, not CONFIRM something) allowing for successful recording of unbiased data

Question 57

What is a correlation coefficient?

Answer 57

The correlation coefficient is a statistical measure of the strength of a linear relationship between two variables. Its values can range from -1 to 1. For a population, it is given by the greek letter Rho (p) Whereas, the sample correlation coefficient is given by 'r'

Question 58

How does the sign of the correlation coefficient indicate the relationship between two variables

Answer 58

If it is positive, as values on one variable get higher, values on the other also get bigger If it is negative, as values on one variable get bigger, values on the other get smaller

Question 59

What are the different ranges of numbers for the correlation coefficient which indicates the various strengths of the relationship

Answer 59

0.1-0.3 = weak 0.3-0.7 = moderate (?) 0.7-0.9 = strong

Question 60

Does correlation allow for causation?

Answer 60

No

Question 61

What is a control condition and why is it good?

Answer 61

It is a standard to which other conditions can be compared to in a scientific experiment. It allows for filtering of variance . normally this group doesn't have the treatment. Allows us to infer causation It can exist to rule out causes such as time, fatigue, the bodys own immune system etc, which can elsewise be considered as possible explanation for the phenomena If changes can be measured in the experimental condition, which has only one, unique and carefully controlled features, and those changes aren't found in the control conditions, you can attribute changes to the unique manipulation of the independent variable

Question 62

What are the 3 different types of experiments that we look at?

Answer 62

True experiment Quasi experiment Correlational studies

Question 63

What is a true experiment?

Answer 63

This is where all independent variables of interest are controlled and are able to be RANDOMLY ALLOCATED INTO DIFFERENT GROUPS. Here, a strong casual inference can be made that the difference in the independent variables is what causes a certain effect, because random allocation makes all variations between groups cancel out (except for systematic difference)

Question 64

What does controlling all variables mean?

Answer 64

Controlling all variables typically refers to the concept of holding constant or manipulating all factors that could potentially influence or affect a particular situation, experiment, or system. While ensuring the other variables dont change(?)

Question 65

What are the pros of a true experiment

Answer 65

Establishes comparison Easy to understand and replicate Concrete method of research Ability to establish causation

Question 66

What are the cons of a true experiment

Answer 66

Expensive Too idealistic (Scenarios aren't representative of real world) --> results aren't authentic Time consuming

Question 67

What is a quasi experiment. Example

Answer 67

In a quasi-experiment, at least one independent variable is controlled by the researcher and participants can be randomly allocated to different levels of it, but other variables of interest cannot be randomly allocated. Participants in a quasi-experiment arrive “already allocated” to the levels of at least one independent variable. A quasi-experiment involves pre-existing groups. An example would be looking at how eye colour influences intelligence. Or heavy drinker, moderate drinker, light drinker

Question 68

What are the pros of a quasi experiment

Answer 68

Provides researchers control over some variables by allowing them to manipulate it Can be used when there are ethical/practical reasons why participants can't be randomised

Question 69

What are the cons of a quasi experiment

Answer 69

Lower level of internal validity than true experiments Susceptible to human error Allows for researchers bias

Question 70

What is a corrleational study

Answer 70

At least two variables are simply measured in a correlational study. The measures are taken at the same time, and the experimenter does not intervene in any way, and is approached with a view to calculate a RELATIONSHIP between the variables

Question 71

What are the pros of a correlational study

Answer 71

May predict human behaviours Can be more cost effective Used when it would be unethical to use an experiment Good starting position for research

Question 72

What are the cons of a correlational study

Answer 72

No inferences can be made Possibility of confounding variables

Question 73

What is an independent variable (IV)

Answer 73

This is usually the presumed cause in research and is the one being manipulated by the experimenter. This is the variable being changed by them

Question 74

What is a dependent variable (DV)

Answer 74

It is what is measured by the experimenter to see if the IV has had any effect

Question 75

What is random allocation?

Answer 75

It occurs when participants in a study arrive at the study not belonging to any level of the IV and can be given/administered or placed into a level/condition of the IV by a RANDOM PROCESS

Question 76

What is random selection?

Answer 76

It is the method of sampling where a representable group of research participants is selected from a larger group by chance

Question 77

What is the difference between random sampling/selection and random allocation?

Answer 77

Allocation is about separating the subjects into various groups in the IV, whereas selection/sampling is about picking the subjects in the first place

Question 78

What is external validity? What is it dependent on?

Answer 78

It is the extent to which findings from the study can be generalised to the population at large. Depends on: Sample size How the sample was chosen (random selection) Where and how the experiment was conducted (How artificial was the testing location? How real did participants think it was?) How variable the effects being studied are. (If the effect varies very little from person to person, a large sample might not be needed etc.) External validity depends critically on random selection, representative samples, and how authentic the study context is.

Question 79

What is internal validity?

Answer 79

It is the extent to which changes in the dependent variables can be attributed to changes in the independent variable. I.e. if a strong casual inference can be made, internal validity is high, and vice versa. Casual inference is how certain we are that changes in one variable caused changes in the other Internal validity depends critically on random allocation. When internal validity is low, alternative explanations for the results cannot be ruled out. I.e., true experiments have high internal validity, correlational studies have low internal validity

Question 80

What is replication?

Answer 80

It is when the same findings/trends are found by an entirely independent party following the method you followed. Must ensure replication through making the method sections are detailed Other scientists should be able to copy our study and find the same things, eliminating fraud and sampling errors as explanations

Question 81

What is blindness?

Answer 81

Blindness applies to researchers and patients, and it refers to the inability for the parties to know which group the patients are allocated to (control or treatment group) Ideally both researchers and participant should be blind.

Question 82

Why is blindness important?

Answer 82

A participant who isn't blind may know or guess what is expected of them A researcher who isn't blind may not randomly allocate correctly, or their knowledge might lead them to manipulate data

Question 83

What is a unblinded experiment?

Answer 83

This is where both the participants and the experimenter knows which group the participants are in. I.e. participants takes a piill knowing that it is intended to relieve pain, and the researcher knows the group

Question 84

What is a single blind experiment?

Answer 84

This is where either the participant or the researcher doesn't know which group the participant is in I.e. participant is given a pill by researcher (who knows what it does), but the participant isn't told whether it will relieve pain

Question 85

What is a double blind experiment?

Answer 85

This is where neither the researcher applying the medicine and the participant know which group the participant is in. I.e. Researcher 1 makes the pills yellow and blue. She gives them to researcher 2 who doesn't know which one has active ingredients. Researcher 2 gives participants one of the pills and records hoe effective it is. Researcher 1 takes the data which records effectiveness and makes a conclusion (only they knew that the blue pill contained an active ingredient)

Question 86

What is confirmation bias? Example?

Answer 86

It refers to people's tendency to process info by looking for, or interpreting info that is consistent with their existing beliefs. (only look for evidence which confirms their belief) I.e., during presidential elections, individuals mostly tend to seek info which paints the candidate they support in a positive light, while dismissing info which paints them in a negative sense

Question 87

What is considered in the measures of central tendency?

Answer 87

Mode, median, mean

Question 88

What is considered the measures of variability?

Answer 88

Range and standard deviation

Question 89

What is a mode?

Answer 89

This is the most common score; the most frequent score in a dataset

Question 90

What are the advantages of a mode?

Answer 90

Unaffected by extreme values Can be used for categorical variables

Question 91

What are the disadvantages of a mode?

Answer 91

Doesn't take into account ALL values Can be really unstable

Question 92

What is a median?

Answer 92

This is the middle score in a dataset, when the scores are all organised in ascending order. If there is an even number of scores, it is the avg of the two middle scores. Otherwise, it is just the middle score

Question 93

What are the advantages of a median?

Answer 93

Unaffected by extreme values (less affected) Easy to understand and interpret

Question 94

What are the disadvantages of a median?

Answer 94

Not based on all values (doesn't capture full range of variation) can't be used for further mathematical tests

Question 95

What is a mean?

Answer 95

It is the average of a distribution of scores. Calculated by adding all the scores and dividing by the total number of scores

Question 96

What are the advantages of a mean?

Answer 96

Takes all scores into account --> representative Good representation of data Useful for comparison Can be used in further calculations

Question 97

What are the disadvantages of a mean?

Answer 97

Easily influenced by extreme values (outliers) Can't be used for qualitative data Can't measure skewed distributions well

Question 98

What is range?

Answer 98

It is the difference between the highest and lowest values in a dataset

Question 99

What are the advantages of a range?

Answer 99

Easy to calculate Can have a basic understanding of the spread of data

Question 100

What are the disadvantages of a range?

Answer 100

Outliers can ruin ranges

Question 101

What are the different forms of graphical distribution?

Answer 101

Symmetrical distribution Negative skewed distribution Positive skewed distribution

Question 102

How do you identify negative and positive skewed distribution?

Answer 102

Negative skewed: The tail is leaning to the negative side, also known as left skewed Positive skewed: the tail is leaning towards the positive side, also known as right skewed

Question 103

What is standard deviation

Answer 103

the standard deviation is a measure of the amount of variation of a random variable expected about its mean.

Question 104

Why do we need a standard deviation?

Answer 104

This arises from the problem of being unable to calculate the average deviation score around a mean, as it would always add up to zero. To get around this, we square each deviation before adding them together, so -ve numbers squared equals a +ve number. This means that the sum of deviations no longer cancel eaach other out This variance results when we take a sum of all these squared deviation scores and divide by the number of scores. However, this isn't meaningful because we had to square all scores before we added them. Thus, we take the square root of the variance to get the standard deviation (s.d) This is the closes

Question 105

What is the formula for standard deviation

Answer 105

S.d. = Root( sum of (x - mean) / n) x = a given score n = total number of scores

Question 106

What is an experimental hypothesis?

Answer 106

It is a prediction of what will happen in the study. It has to be derived from either previous literature and findings or from a theory which allows for specific predictions. If humour makes relationships more satisfying, then we would expect that satisfaction after high humour day would be higher than on low humour days (we normally state this in an experiment)

Question 107

What is the null hypothesis?

Answer 107

This is a construct to help overcome natural tendencies to avoid testing what we currently believe. Because it is a lot easier to disprove something than it is to profe something. It is set up to fail The null hypothesis is the case if nothing is happened (i.e. hypothesis of no effect). If there is evidence to disprove the null hypothesis of no effect, then you can reject it and say something has been found. Meanwhile, if there isn't evidence to disprove the null hypothesis, it is retained and an there has been an effect I.e. If humour is unrelated to relationship satisfaction, then we would expect that satisfaction after high humour days to be no different than satisfaction after low humour days (We normally don't state this in an experiment)

Question 108

What is the alternate/alternative hypothesis

Answer 108

This states that there is a statistically significant relationship between two variables. It is usually known as the hypothesis (if something is happening between the two variables) I.e. Null hypothesis might state that there is no difference in salary between female and male workers, however alternative hypothesis might state that males have a higher salary than females. The alternative hypothesis H1 (sometimes denoted HA ) is the hypothesis that suggests that sample observations are influenced by a non-random cause. I.e. If humour is related to relationship satisfaction, then we would expect that satisfaction after high humour days be DIFFERENT from low humour days Note the difference between alternative and experimental hypothesis.

Question 110

What is a sampling distribution?

Answer 110

It is a hypothetical distribution based on a hypothetical set of sample means. This is achieved through simulating the same experiment being done over and over again, and then putting it into a distribution Here, each point on the x axis represents a sample mean value, and the height of the line (or columns of Ms) represents how freuquently the sample mean of a particular value is expected to occur The sample means cluster around the middle, which is the population mean THE SHAPE IS ALWAYS NORMAL REGARDLESS OF DISTRIBUTION

Question 111

What is the standard deviation of the means in a sampling distribution called?

Answer 111

Standard error

Question 112

What is the difference between a frequency distribution and a sample/sampling distribution

Answer 112

A frequency distribution looks at the distribution of raw scores, whereas the sampling distribution is the distribution of means in the curve

Question 113

What is the normal curve?

Answer 113

It describes a symmetrical plot of data around its mean value, where 68% of all results are contained within 1s.d. of the mean, 95% within 2s.d. and 99.7% within 3s.d. They always have the same shape

Question 114

What is the p value?

Answer 114

It is the probability of observing a test statistic under the assumption that the null hypothesis is true (in other words the probability that the null hypothesis is true) They vary between 0 and 1 and express a probability It is created from a sampling distribution

Question 115

Is it good for the p value to be low or high

Answer 115

It is good for the p value to be low because it shows that there is a relationship within the test statistics, because the lower it is, the more likely the null hypothesis is false

Question 116

What is the p value cut off to be able to reject the null hypothesis?

Answer 116

If the p value is less than 0.05, we reject the null hypothesis. If the p value is greater than 0.05m we retain the null hypothesis. The 0.05 p - value as a cut off is due to convention

Question 117

What phrases are used when p - value is either <0.05 or > 0.05

Answer 117

For p values < 0.05, phrases like 'statistical significance' are used, and the result can be freely discussed from that point on For p values > 0.05, phrases like ' is not significant' are used

Question 118

Discuss the probabilistic nature of science/psychology based on conservatism and liberalism.

Answer 118

We have to realise that we aren't making conclusions on 'solid' and 'certain' findings. Every decision is probabilistic in nature, especially because science doesn't deal in certainties. However, decision making can't wait until its perfect, otherwise this is too conservative and prevents us from doing anything Meanwhile decision making can't be influenced by tiny differences which could be due to luck - this is too liberal and is driven by random findings Thus, it is a probabilistic science, and the point where we change our mind is the challenge inferential statistics faces

Question 119

What is variability?

Answer 119

This refers to the extent to which data values in a dataset differ from central tendency. If trying to establish whether an effect is real, you can no longer rely just on means, you need info on variability

Question 120

What is the difference between population and sample?

Answer 120

Population: - The entire collection in which you are interested - Properties of these scores are called parameters and use greek letters such as mew(μ) for mean, and sigma (σ) for s.d. Sample: - A selection from the entire collection we are interested in - Properties of these scores are called statistics and use latin (normal letters), E.g. mean = M, Standard deviation = S or SD

Question 121

What is statistical significance?

Answer 121

It is how likely the effect was due to chance or whether it arose from a true underlying effect. It is proclaimed when the p value is below 0.05. It is said something is statistically significant when the result produced is unlikely to be by chance It only indicates the RELIABILITY of an effect

Question 122

What is practical significance?

Answer 122

Refers to the ability for an effect to be large enough to be mmeaningful in the real world. It is also looking at the practical significance / application --> how useful is the effect in the everyday world?

Question 123

How does the probabilistic nature of science lend itself to logical errors?

Answer 123

Science is probabilistic, yet we continue to accept the probabilities, and try to minimise the probability of being wrong, because we still need to make decisions and make progress, and if we're being too conservative with probabilities, it can't ever be confirmed. Science expresses the boundaries of uncertainty. However, the probabilistic nature of doing science and humility of expressing uncertainty leaves science vulnerable to the appeal to ignorance (argument from irgnorance), false dichotomies and denialism

Question 124

What is the appeal to ignorance? Give an example

Answer 124

The premise involves stating that if something can't be conclusively proven true, then the opposite must be true (especially a problem with scientists assertions of humility that everything is uncertain) I.e. Using X is bad because it can't be proven to be helpful, thus using Y can be helpful OR Because we can't prove that God does exist, then God must not exist

Question 125

What is a false dichotomy? What is bad about it?

Answer 125

It is a fallacy of presenting only two choices or sides to an argument, when there are definitely more available. It is bad because it restricts imagination, limits opportunities (to only two) and lends support to pseudo logical arguments. I.e. 'Let's debate both sides'

Question 126

WHat is denialism?

Answer 126

This implies a broader rejection of a series of claims or an entire body of evidence and theories based on the slightest uncertainty, even though it is well backed. I.e. Heisenberg's Uncertainty Principle, Disease, Holocaust, 9-11, climate change denial etc Wikipedia: In the psychology of human behavior, denialism is a person's choice to deny reality as a way to avoid believing in a psychologically uncomfortable truth.

Question 127

What are type 1(alpha) errors?

Answer 127

It is the possibility of rejecting a true null hypothesis. In other words, saying there is an effect when there isn't

Question 128

What are type 2(beta) errors?

Answer 128

It is the possibility of retaining a false null hypothesis In other words, saying there is no effect when there is

Question 129

What is the relationship between alpha and beta errors?

Answer 129

As one error is reduced / minimised, the other error conversely increases / grows

Question 130

What is statistical power?

Answer 130

It is simply '1 - beta' , which is the probability of correctly rejecting a null hypothesis when it is false It refers to the 'sensitivity of an experiment' - likelihood of a real effect. More power is GENERALLY desirable

Question 131

What error is it when you say you see something but nothing is there

Answer 131

Alpha error aka a false alarm

Question 132

What error is it when you say you see nothing but something is there?

Answer 132

beta error aka a miss

Question 133

What is the method to find the appropriate cut off for making a decision in non-scientific/report situations?

Answer 133

We need to decide: What is the cost of a false alarm? (e.g. scare someone into thinking they have cancer when they don't?) What is the cost of a miss? (e.g. patient told they are healthy when they do have cancer?) As a result, for health conditions, type 1 error is preferrable as it reduces risk

Question 134

Can power be measured?

Answer 134

No, it can only be estimated

Question 135

How can power be estimated? What factors are involved?

Answer 135

Variability of the effect Size of the effect Sample size

Question 136

What is the effect of 'variability of the effect' on power?

Answer 136

The greater the variability, the lower the power A smaller variability increases the power because it is more consistent, and thus there is a much greater chance of a correct rejection

Question 137

What is the effect of 'size of the effect' on power?

Answer 137

A larger effect size = more power For example effect size refers to the distance between the hypothesised curve and the experimental/frequency curve from your own data. The bigger the effect size, the more likely you are able to notice a differnece in the hypothesised curve and experimental curve, and realise something of importance is happening --> increased power

Question 138

What is the effect of sample size on power?

Answer 138

A larger sample size = more power. This is because if there is a real effect, a greater number of people will allow for random variables to cancel out within people and instead allow us to see actual trends The larger the sample size, the smaller the standard error, because with larger experiments the impact of extreme scores is much lower

Question 139

Why don't we want too much power?

Answer 139

An over powered study will give a greater likelihood / probability of obtaining significance, even though in effect, it is miniscule and has a questionable importance