Question

Section 1 (3 marks: You can start this section after Week 4 lecture) Read the following article: Harford, T. (2014), ‘Big data: A big mistake?’, Significance 11(5), 14–19. Question: Critically evaluate the main points of the article using three bullet points, in less than 150 words in total. Critical evaluation means • To give your opinion on something • To support your opinion (with evidence where possible). • Note: Critiquing is NOT simply stating that something is “bad”. • Weigh up strengths and weaknesses. • Appraise the worth of something - test assumptions - judge the worth of an argument or position. Your points of evaluation may include the following (but not limited to): • Correlation vs. causation • Importance of theories or insights in statistical analysis • Multiple testing problem • Sampling error • Sampling bias • Big data hubris In providing your answers, you can also refer to the contents of Lecture in Week 4 (Statistical Significance in Empirical Research)

Answer 1

If i try to be a critic for Harford article "Big data: A big mistake i'll straight get into the point that its an act of balancing threats & malwares if big data arent safely handled. There is always big risks to the social media giants for data leaks by many other hackers the way at present CHINA is blamed for secretly keeping a watch over other countries data by the use of certain apps .These are some of data theft ususally happening due to mishandling of data security by the IT cyber cell professionals of the country it self it can be well understood by following certain points on which there are problem being faced heavily :-

Despite key advances such as growing pool of data scientists some critical data mistake still persists for critics like

1)Poor Data Quality:- if we go for using data of low kbps or older versions that can be easily traced or tracked & hackable by the intruders which is basically good  critic point to discuss

2)Too Much Data - data in bulk is also a problem as it requires more amount of servers to manage it like if we say FACEBOOK has to handle lots of data of the whole world at a single minute or second for that there cant be a single mistake to be left on managerial staffs of the firm .Its the head who will be responsible for data bulk management

3)Assuming event prediction is a slam dunk- predictive analytics is an existing made possible by lot because of its persived value to business good for stake holders but predictive analysis is not possible in all instances. Cos first ther has to be a projected claer basis.

4)Overpromising what data scientists can deliver:- there cant be just vague target & no achievement of those in a particular time it affects the firms burocrasy. Only the actual promised work for data should be delivered .