Wednesday, 22 July 2015

Key Learning Points on Data Handling

Answer the following questions as much as you can, in your own words.

1. Compare and contrast (pros and cons) the three averages.

2. How may statistics be distorted to influence the public? What would you do if you were a statistician?


  1. 1. The three averages: Mode, Mean and Median. For example, here are the monthly earnings of 7 employees:
    $100, $523, $523, $839, $920, $20387, $932492
    Mean:$136541(nearest whole number)
    Mode pros: You will know the most repeated number ($523 in the example).
    Mode cons: There could be a big difference between the most repeated number and the actual average.
    Median pros: You can roughly guess the average.
    Median cons: There could be a few numbers that are way higher/lower than the median that disrupt the accuracy of the median. If you look at the example, the median is $839 but there are numbers that are a few hundred thousand so $839 is definitely not the average.
    Mean pros: You can find the exact average of all the numbers.
    Mean cons: If you want to say, looking at the example, that the mean is $136541, it is not accurate to say that everyone has around that amount of money. There are people who have only $523.
    2. Statistics can be distorted to make people believe in companies. For example, if a slimming company says that there is a 95% chance of success if you pay for their treatment, many people will go. However, the real success rate might not be that high. If I were a statistician, I would just tell the truth to the people and whether they believe it or not, so be it.

  2. Mean=Average Number
    Median=The number in the center(odd number) add up the two numbers in the center and divide it by two(even number)
    Mode=The number that appears most often
    Bi-modal=Two numbers that appear the same amount of times and are the largest in the data

    Pros and Cons
    Mean(pros)=Usually the safer way.
    Mean(cons)=If one number is larger than other numbers by a lot, it is inaccurate.
    Median(pros)=Is somewhat about the same number as the mean
    Median(cons)=Usually for lazy people who don't like to take the safe way as Median isn't as accurate as the mean.
    Mode(pros)=Is someone the same number as the median and the mean
    Mode(cons)=If one number is big, and the rest are quite low, the answer will not be as accurate

    2. How may statistics be distorted to influence the public? What would you do if you were a statistician?
    Most people would usually look at the mean. But the median would be better depending on the situation of our generation. XD
    If I am a statistician, I would give the more accurate answer as I don't feel good giving the public the least accurate answer.

  3. 1.Pros and Cons
    Mean(pros)=The easiest way to count average
    Mean(cons)=If one of the numbers is larger than one number by a lot, the answer is not accurate.
    Median(pros)=Near the same amount as mean
    Median(cons)=Median not very accurate as it is just the middle number
    Mode(pros)=Tells you what is the biggest value
    Mode(cons)=It is not accurate as the the biggest value might not be close to the other values in the table
    2. Statistics can be distorted to make the public believe in companies. The statistics companies give might not always be the real statistics that have been tested.
    If I am a statistician, I would tell the truth to the public as it is better than giving a statistic that is fake and not reliable.

  4. This comment has been removed by the author.

  5. 1. mean:
    -You do NOT have to put the data in order.
    -Mean is a very descriptive value.
    -Represents what each value would be if they were all equal.
    -It is one large calculation, often giving you a decimal number.
    -You must count all the numbers in the set.
    -Can be skewed due to an outlier.


    -It finds the middle of the data set.
    -It is not affected by one outlier number.
    -Combined with mean it can be a very descriptive tool.
    -You MUST put the numbers in order from least to greatest.
    -The way you find median differs depending on how many numbers are in the group.

    -you do NOT have to put the data in order.
    -No calculations necessary.
    -It is possible to have no mode, one mode, or many modes.
    -Not a great descriptor of a data set, there is no guarantee that Mode will reflect the greater set.

    2.if it was mean, one very big number with skew the mean
    if statistics are not real, it would not be accurate
    if i was a statistician, i would try to not include big numbers/have a number range