Statistics Flashcards
What is the model/mode?
The data that appears the most frequently
How do you calculate an estimate for the mean when given a table of ranges + frequency rather than exact numbers?
Use the midpoint of the ranges given and do rest as usual
What does model class mean?
Which group/range of data is highest in frequency?
What is positive correlation?
A slope/line of best fit that goes upwards
What is negative correlation?
A slope/line of best fit that goes downwards
How to draw a frequency polygon for a table of ranges + frequency?
- Use the midpoints of the ranges and plot them on x axis
- The frequency will be your y axis
- The midpoint and frequency will be your coordinates (x being midpoint and frequency being the y coordinate)
- Draw straight lines between the Xs
How to draw a box plot?
- The start and end of your box plot will be the lowest and highest values
- The median of the data will be the middle of your box plot
- The median of the midpoint and lowest value will make your lower quartile (not including the midpoint in the range)
- The median of the midpoint and highest value will make your upper quartile (not including the midpoint in the range)
5, Join up a box between lower midpoint and upper midpoint
How to easily find your median if you have an odd amount of data?
Amount of data+1 / 2
There are two things you want to compare when comparing a box plot, what are they?
The median, interquartile range which means the data is more spread out
What is the distance between the lower and upper quartile called?
The interquartile range
What is the difference between frequency and cumulative frequency?
Frequency is how many times a value occurred whilst cumulative frequency represents the total of all frequencies in a dataset
How to draw a cumulative frequency graph?
- Calculate cumulative frequencies (add the frequencies one by one as you go down the table)
- The data on the right side of the range is your x axis whilst your cumulative frequencies are going to be seen on y axis
- Plot points using coordinates, y coordinates being cumulative frequency and x coordinates being corresponding “right side of range” values
- Draw a smooth curve starting from zero and joining all the points
How to find answers for questions on cumulative frequency graphs like “find an estimate for the number of lorries with a speed of more than 90km/h” ?
- Find the speed 90km/h on your x axis and go up until you hit the curved line
- Find corresponding y value to that point in the line you hit
- That is the estimated amount of lorries which was going 90km/h, so if it was 84 and there were 100 lorries in total in the data set, the amount of lorries going faster than 90km/h would be 100 - 84 which is 16 lorries
How to find median on cumulative frequency graphs? E.g “find the speed of the median lorry”
- Find median of final accumulated frequency on y axis, e.g if 100, median would be 50
- Find the corresponding speed of that median on the curved line, it will be on x axis.
How to find lower, upper and interquartile range on cumulative frequency graph?
Once you find the median of the final accumulated frequency, you are able to find all of these