Graphs And Shitt Flashcards
Quantitative data
Any number of possible values (eg. Weight)
Qualitative data
Have only certain possible values (eg. Race)
Discrete/continuous data
Information that only takes certain values
Usually numbers
Non discrete/discontinuous data
X
Difference between histograms and bar charts
Histograms have NO SPACES between bars
What to look for when looking at histograms?
- is there more than one peak?
- overall shape? Is it symmetrical or skewed?
- is the shape wide or right? Range of the intervals the bars are plotted at?
- concentration of points or outliers that distort the graph?
How to interpret box plot graphs?
X
Boxplots with raw data
X
What do box plots show?
Visual representation to show distribution of numerical data
5 number summary of the data (minimum, first quartile, median, third quartile and maximum)
Dot plots
- alternative to a bar chart
- height of vertical bars indicated with a dot instead
- same interpretation as a bar chart
Side by side box plots
XXX
- width of boxes can be made proportional to the number of values in each category
- do read the symmetry vertically ???? Ask Harv ???
- ## how does the symmetry of each box plot differ across categories?
X
X
Bar plots can also be presented as …
Stacked
What is standard deviation used for?
To measure the range of values around a mean
Does standard deviation have a degrees of freedom?
NO
Standard deviation - YES overlap
There IS an overlap in the SD bars indicates there is NOT a significant difference and results are likely to be due to chance
Standard deviation extra information
Check with Harv
XXXX
- smaller SD, the narrower the range = higher reproducibility
- smaller SD = experimental values clustered close together means higher precision
Standard deviation equation
Square root
Of the sum of the difference of the squares/ (n-1)
Standard deviation is the
Square root of variance
What is variance in SD?
Average of the squared differences from the mean
Explain in words how to calculate standard deviation?
1) calculate mean of all the values
2) subtract the mea from each value (to find how far each value is from the mean)
3) square the result for each number ^ (this is called the ‘squared difference’)
4) work out the average of the squares differences but adding all the values you get above and dividing by the total number of values measured
SD for population - divide by N (total number of values measured)
SD for sample of a population - divide by (N-1)
What do you divide by when working out SD for a population compares to a sample ?
Population - N
Sample - N-1
What actually are degrees of freedom?
???? Whatttt
Maximum number of logically independent values which are values that have the freedom to vary in a data sample
What do we usually use as a critical value?
0.05 or 95%
What actually is a p value ?
XXX
Probability of obtaining a result at least as extreme as the one that was actually observed in the biological experiment given that the null hypothesis is true
When do we REJECT the null hypothesis (In terms of calculated and critical values)
If the calculated value exceeds the critical value then we REJECT the null hypothesis