Flashcards in Data Deck (31)
What are the Measures of Central Tendency?
What is meant by Central Tendency, and Dispersion?
Central Tendency - A descriptive statistic that calculate the average almost typical value in the dataset; that is the average score recorded
Dispersion - A descriptive statistic that calculates the spread of scores in the dataset. Measures of central tendency can be misleading without knowing the variation between the scores.
What is the Mode?
Calculates The most frequent score in a data set. The mode is the value that occurs most frequently
What is the Median?
The middle number within an ordered set of values
What is the Mean?
The average number within a set of values
What type of data is the mode, median and mean typically used for?
Mode - Nominal
Median - Ordinal
Mean - Interval/Ratio Level
What are the Strengths + Weaknesses of the Mode?
The mode is very easy to determine. It is not affected by extreme scores.
However it is not a useful measure of central tendency on small data sets, with frequently occurring same values
What are the Strengths + Weaknesses of the Median?
The median is not affected by extreme scores or a skewed distribution
However, it is less sensitive than the mean and is not useful on data sets that have a small number of values, as it may not represent the typically score
What are the Strengths + Weaknesses of the Mean?
It is the most powerful measure of central tendency because all of the scores in the data set are used in the calculation
It can be affected by extreme values, or when there is a skewed distribution
What are the Measures of Dispersion?
What are the Problems with the Range?
The range is affected by extreme scores, so it may not be a useful descriptive statistic if there are outliers in the dataset.
It also doesn't tell us if the scores or bunched around the mean all more equally distributed around the mean
If the dataset has extreme scores, it is often better to calculate the interquartile range
What are the Strengths + Weaknesses of the Standard Deviation?
What does the Inferential Statistics Table look like?
Chi2, Sign, Chi2
MWU, Wilcoxon, Spearmans Rho
What does it mean by 'Ordinal +' ?
The levels of measurement are ranked in terms of sophistication- Nominal, then Ordinal, then Interval.
Ordinal + just means ordinal and interval data. The ones used for interval are no longer really used anymore, we just use the ordinal one for them.
What are the types of Graphical Representations of data?
What are Bar Graphs?
Bar graphs are used to present data from a categorical variable, such as the main/medium/mode.
The categorical variable is placed on the x axis, and the height represents the value of that variable
What are Histograms?
The histogram is used to present the distribution of scores by illustrating the frequency of values in the dataset.
Unlike a bar chart, the bars on a histogram are joined to represent continuous data rather than discrete data.
The possible values are presented on the X axes and the height of each bar represents the frequency of the value
How would a Graph always be Labelled?
Relevant graph title
Relevant X axis title
Relevant Y axis title
Plot anything you want (say for practical), or is relevant to the question.
What does it mean to have Normal Distribution?
Normal distribution is characterised by symmetry around the midpoint. The mode median and mean should be aligned around the midpoint.
The tail ends should not meet the horizontal axis and we can estimate the percentage of people that fall under the curve at each standard deviation.
What is the Normal Distribution curve?
What does it mean to have a Negative Skew?
If the aptitude of the sample is unusually high, it told me that most people score highly. This leads to a negative skew, where many people score above the average/mean score
What does it mean to have a Positive Skew?
If the aptitude of the sample was low it will mean that most people will achieve a lower score below the mean. This will lead to a positive skew
What does a Positive and Negative Skew look like on a diagram?
What are the different levels of measurement?
What is Nominal Data?
Where data forms discrete categories. We know nothing about each value within the categories, we just know the category names.
E.g. 1 - hair can only be nominal data because it can only be described in its categories of blonde, brown, red or black.
E.g. 2 - if you divide the class into students under 1.85m tall and over 1.85m tall, and calculate the frequency in each category, you would have nominal data. You would not know the actual heights of each individual student, or their height in relation to one another
What is Ordinal Data?
A level of measurement where numbers are rankings rather than scores in themselves. It tells us about the position, but does not tell us what was actually achieved or the difference between each rank
E.g. a rank order for attractiveness on a scale of 1 to 5
What is Interval/Ratio Data?
Data where an individual score for each participant is gathered, and the score can be identified using a recognised scale with equal distances between each score
E.g. cm, seconds, minutes, kilograms, etc
How can you judge significance? What does p<0.x mean?
For example, p < 0.10
This means the probability of whether the results are due to chance is 10%
What are Type I errors?
A type one error occurs because the level of significance is too lenient
When the null hypothesis is rejected and alternative hypothesis is supported when the effect was not real