data handling Flashcards

You may prefer our related Brainscape-certified flashcards:
1
Q

strength of quantitative data

A
  • Tends to be collected through objective measures.
  • Tends to be highly reliable.
  • Can be analysed through inferential statistics.
  • scientific.
  • Easy to analyse.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
1
Q

weaknesses of quantitative data

A
  • Method of measurement may limit participant’s response which means that it may lack validity.
  • Can lack data.
  • Can lack construct validity – may not capture the complexity of what is happening e.g. human emotion.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

strengths of qualitative data

A
  • Data can be very valid – often allows for participants to freely express themselves.
  • Less likely for key information and observations to be ‘lost’ when simplifying down data.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

weaknesses of qualitative data

A
  • Data can be very subjective, as data may be processed through interpretation of the participant’s responses.
  • Data is individual so can be hard to generalise.
  • Different to analyse.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

primary and secondary data

A
  • Primary data - any data which is collected directly from the participants by the researcher
  • Secondary data - data which has already been gathered by someone else other than the researcher
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

raw data tables

A
  • used as it is a clear but quick way to record the scores for each person within each condition or when when recording how many word are remembered on both white and red paper
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

3 measures of central tendency needed

A
  • mean
  • median
  • mode
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

mean

A

def = The average of a piece of data.
calculated = Adding up all of the scores and dividing this total by how many scores there were.
advantage = More sensitive than the median, as it makes use of all of the values within the data.
disadvantage = Can be misrepresentative if there is an extreme variable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

median

A

def = The middle of a piece of data.
calculated = Placing all of the scores within the data into a set (often smallest to largest) and finding which score is in the middle of the list.
advantage = it is not affected by extreme values, so can give a representative value.
disadvantage = Less sensitive than the mean, as it doesn’t take into account all of the values.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

mode

A

def = the most frequent score within data.
calculated = Categorise results that have similar properties (e.g. same score on a test) and find the category with the most scores.
advantage = Data in categories can be useful.
disadvantage = It is not a useful way of describing data when there are several modes.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

measures of dispersion

A
  • range
  • variance
  • standard deviation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

range

A
  • Find the largest and smallest value. Subtract the smallest value from the largest then add 1.
  • advantage = Quick and easy way of getting an idea of how dispersed the results gathered are e.g. small range = similar results.
  • disadvantage = Is sensitive due to it being easily affected by an extreme value within the results.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

variance

A
  • Calculate the mean score per condition in the experiment, For each participant you then subtract the mean score from their score. This is ‘d’ (the difference), Then, you square each ‘d’ score. (d2), Finally, you calculate the mean of these d2 scores
  • advantage = Representative as every value within the data is used. Not sensitive to extreme values.
  • disadvantage = Final answer is a squared number and therefore not in the same units are the original data used.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

standard deviation

A
  • Workout the variance using the technique above, Calculate what the square root of the variance is.
  • advantage = Representative as every value within the data is used. Not sensitive to extreme values.
  • disadvantage = Time consuming and more difficult to calculate than the range score
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

levels of data

A
  • nominal
  • ordinal
  • interval
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

nominal data

A

Data which is a tally/total of the number of times something occurred

16
Q

strengths of nominal data

A
  • Easy to generate from closed questions, so large amounts of data can be collected quickly, increasing reliability.
  • Quick to find the mode to assess central tendency.
17
Q

weaknesses of nominal data

A
  • Can only use the mode as a measure of spread.
  • Without a linear scale, participants may be unable to express degrees of response.
  • Points are not on a linear scale so medians and means cannot be used to assess central tendency.
18
Q

ordinal data

A

Data which can be put in rank order, from smallest to largest (but the spaces between the ranks may not be the same size)

19
Q

strengths of nominal data

A
  • More informative than nominal data, as it indicates relative values on a linear scale rather than just totals.
  • Easy to generate from Likert and rating scales.
  • Points are on a linear scale so a median can be used as well as a mode to assess central tendency.
20
Q

weaknesses of ordinal data

A
  • As the gaps between the points are only relative, comparisons between participants may be invalid as they may interpret the scale differently.
  • Gaps between the points are not equal so a mean cannot be used to assess central tendency.
21
Q

interval data

A

Data which can be put in rank order, but has equal intervals between the scorings possible

22
Q

strengths of interval data

A
  • More informative than nominal and ordinal data as the points are directly comparable because all the points are of equal value.
  • Easy to generate from closed questions.
  • Scientific measurements are highly reliable and have an absolute zero baseline.
  • Points are on a linear scale, with equal gaps between the points so a mean can be used as well as the mode and median to assess central tendency and variance or standard deviation can be used as measures of spread.
23
Q

weaknesses of interval data

A

In interval scales that are not scientific measures, there are no absolute baseline to the scale so scoring zero may not mean that the participant does not demonstrate that variable at all, merely that the scale does not measure it.

24
Q

2 things that determine which stats test to use

A
  • The design of the investigation
  • The level of measurement of the data that has been collected
25
Q

stats test table

A

RMD IMD correlation

nominal - sign test - chi-squared - chi-squared

ordinal - wilcoxon - mann-whitney U - spearmans rank

interval - related t-test - unrelated t-test - peasons r

26
Q

stats tests where the observed value has to be lower than the critical value to be significant

A
  • sign test
  • wilcoxon
  • mann-whitney U
27
Q

stats tests where the observed value has to be higher than the critical value to be significant

A
  • chi-squared
  • spearmans rank
  • related t-test
  • unrelated t-test
  • pearons r
28
Q

significance levels

A

the accepted level of significance is when we believe that the results gathered would only have occurred by chance less than 1 in 20 times. can be expressed as 0.05. Therefore, when looking at critical value tables, we need to check whether our results are significant at the p<0.05 level.
An even stronger level of significance is when we can say p<0.01. This means that the probability results are due to chance is less than 1 in 100

29
Q

positive and negative distributions

A
  • negatively skewed - lower at join of x and y axis
  • positively skewed - higher at join of x and y axis
30
Q

reliability

A

is about how consistent a measuring device is – i.e. whether it is standardised and the same for all participants, and whether it would gain the same results if repeated.

31
Q

internal reliability

A

refers to how consistently a method measures within its self. if methods of measurement not standardised then they would give distorted final scores.
- split-half method = able to establish whether internal reliability exists by comparing the results of one half of the test with the other half. if highly positive correlation found it can be assumed that both halves of the test were consistent with each other in what they were measuring

32
Q

external reliability

A
  • refers to how how consistently a method measures over time when repeated. methods of measurement should give similar scores when repeated on the same people under similar conditions
  • test-retest method = able to establish whether external reliability exits by comparing the results taken on one occasion with the results taken on another
33
Q

validity

A

about how accurate a measurement is. Does it measure what it set out to measure

34
Q

internal validity

A

refers to whether a study’s results were really due to variables the researchers suggest were tested by their methodology
> face validity = does the test or measurement look like it will measure what its supposed to
> construct validity = is the test or measurement appropriate to measure the theory or concept
> concurrent validity = comparing new test with existing one, if results from the two are highly similar then seen to be concurrently similar
> criterion validity = how well test predicts the future performance on a different measurement

35
Q

external validity

A

refers to whether to whether the results can be generalised if conducted in different environments or using different ppts
> population validity = how well the results from the sample within the study can be generalised to the wider population
> ecological validity = whether the test or measure represents every-day activities or natural occurring behaviours