Hypothesis: Female unemployment in the North West is greater than female unemployment in the South East. To test my hypothesis I am going to compare 40 values of data from each region. I will collect my data by using a random sample. I am going to use a random sample because this method of sample gives each separate value an equal chance of being used and it is also completely unbiased. I will assign a number from 1 to 80( because there is a total of 80 pieces of data) to every piece of data. I will then use my calculator to create a list of random number between 1 and 80. I will do this by selecting the random button 40 times. Finally I will match the numbers of the values in the data to the numbers on my random list to create my sample. This will ensure that my sample is fair and completely unbiased. For my sample I have used secondary data. My data is discrete. I will collect my data from http://tiny.cc/uujzkw .
After I collected my data I sorted it from smallest to largest. I did the by selecting all of my data the right clicking and selecting sort into smallest to largest. Once I had done this I split both sets of my data up into the upper quartile, lower quartile and I found the median which was my 20th bit of data. After I had done this I then worked out my interquartile range by taking my lower quartile away from my upper quartile which gave me the interquartile range. I got the upper and lower quartile and median by ordering my data and then splitting it up into quarters. I then recorded my highest and lowest values because this gives me the range of the data. Once I had recorded my highest and lowest value I used the lowest and highest value to plot a box and whisker plot. I used the highest and lowest values to create the scale. I then used my upper and lower quartile and the median to plot the box. I used the lower quartile to plot the beginning of the box, I did this by matching my lower quartile to the scale along the bottom. I used my upper...
Please join StudyMode to read the full document