Analysing data -help with a presentation for a job interview
Discussion
I'm going for a job interview on Friday and I've been asked to analyse sets of sales penetration figures and prepare a presentation for the board of directors to explain the data. The data is over a period of 6 months, similar to the following:
Now the obvious starting point is to graph the data, which I have already done. However, since the data sets don't neatly rise or fall over the period, but fluctuate up and down seemingly at random, I am wondering whether there is some kind of statistical formula that will allow me to quantify the change in penetration rates over the period?
Any help massively appreciated!
| Jan | Feb | Mar | Apr | May | Jun | |
|---|---|---|---|---|---|---|
| Product A | 69% | 71% | 66% | 67% | 70% | 68% |
| Product B | 56% | 56% | 58% | 59% | 57% | 58% |
| Product C | 69% | 71% | 66% | 67% | 70% | 68% |
Now the obvious starting point is to graph the data, which I have already done. However, since the data sets don't neatly rise or fall over the period, but fluctuate up and down seemingly at random, I am wondering whether there is some kind of statistical formula that will allow me to quantify the change in penetration rates over the period?
Any help massively appreciated!
Edited by TheGreatSoprendo on Monday 13th August 21:15
If the numbers you've given are any indication of your actual numbers (A and C the same, B different and peaking in April), they'll be wanting reasons why B appears to be on a different cycle to the other two. Without knowing the sector it's difficult to say any more.
Edited by davepoth on Tuesday 14th August 02:08
TheGreatSoprendo said:
I'm going for a job interview on Friday and I've been asked to analyse sets of sales penetration figures and prepare a presentation for the board of directors to explain the data. The data is over a period of 6 months, similar to the following:
Now the obvious starting point is to graph the data, which I have already done. However, since the data sets don't neatly rise or fall over the period, but fluctuate up and down seemingly at random, I am wondering whether there is some kind of statistical formula that will allow me to quantify the change in penetration rates over the period?
Any help massively appreciated!
You might also want to mention if the difference between say 69% in January and 71% in February is significant or if it could have occurred by chance. For this you would need to know the numbers involved (if 69% is 69000 out of 100000 and 71% is 71000 out of 100000, this is more likely to be significant than 69 out of 100 sales and 71 out of 100 sales). | Jan | Feb | Mar | Apr | May | Jun | |
|---|---|---|---|---|---|---|
| Product A | 69% | 71% | 66% | 67% | 70% | 68% |
| Product B | 56% | 56% | 58% | 59% | 57% | 58% |
| Product C | 69% | 71% | 66% | 67% | 70% | 68% |
Now the obvious starting point is to graph the data, which I have already done. However, since the data sets don't neatly rise or fall over the period, but fluctuate up and down seemingly at random, I am wondering whether there is some kind of statistical formula that will allow me to quantify the change in penetration rates over the period?
Any help massively appreciated!
Edited by TheGreatSoprendo on Monday 13th August 21:15
Thanks for the responses so far. To answer some of the questions:
- It's a marketing role.
- I don't have any data other than the penetration numbers (these refer to penetration of add ons to the main product, a bit like a car dealer selling things like extended warranty, gap insurance, paintwork treatment with a car)
- In fact, I've added a slide to the appendix listing some of the data that I'd want in "real life" to enable me to do this kind of analysis better.
- I have penetration figures for the same set of products over 4 different sites
- The figures I posted aren't the actual ones, but they're representative of the kind of data I have to work with (although I have more data than I posted)
- The only reason A and C are the same is because I copied and pasted and then forgot to change the numbers!
davepoth said:
Without seeing the actual data, it's very difficult to tell really. If you're worried about the company finding it by searching, add 1 to all of the values, which should fox them.
There isn't any extra data as such, I just have 4 sets of penetration figures just like the ones I posted above.What they will be looking for you to do is to be able to quickly identify trends and be able to explain why they are happening. For example, if the penetration is increasing on a particular product at one site but decreasing at another site, why is that the case. Should more marketing resource be allocated to that site to increase penentration?
If 3 sites have high penetarition and one doesn't, why is that?
If penetration drops at all sites for one month, is it seasonal?
I wouldn't get to hung up on the actual data and analysing it. Look for trends and anomoloies.
If 3 sites have high penetarition and one doesn't, why is that?
If penetration drops at all sites for one month, is it seasonal?
I wouldn't get to hung up on the actual data and analysing it. Look for trends and anomoloies.
cuprabob said:
What they will be looking for you to do is to be able to quickly identify trends and be able to explain why they are happening. For example, if the penetration is increasing on a particular product at one site but decreasing at another site, why is that the case. Should more marketing resource be allocated to that site to increase penentration?
If 3 sites have high penetarition and one doesn't, why is that?
If penetration drops at all sites for one month, is it seasonal?
I wouldn't get to hung up on the actual data and analysing it. Look for trends and anomoloies.
Agreed. They're probably looking for you to firstly identify trends and exceptions, and secondly apply your marketing mind to exploiting trends, investing in the marketing mix, cross-selling etc to increase sales/profit/penetration.If 3 sites have high penetarition and one doesn't, why is that?
If penetration drops at all sites for one month, is it seasonal?
I wouldn't get to hung up on the actual data and analysing it. Look for trends and anomoloies.
Product A and C are actually the same products, so the data is clearly junk 
As someone said before, this is a pretty meaningless dataset, all over the shop with no real numbers, just percentages.
I suspect they'll just want some moving 3d charts - That's usually what directors want, in my experience.
Whilst they like to convince you they're the Captains of Industry, quite often they're just a bunch of over-promoted middle managers with little original thought.
M.
As someone said before, this is a pretty meaningless dataset, all over the shop with no real numbers, just percentages.
I suspect they'll just want some moving 3d charts - That's usually what directors want, in my experience.
Whilst they like to convince you they're the Captains of Industry, quite often they're just a bunch of over-promoted middle managers with little original thought.
M.
Most of the above makes sense.
The key is looking for trends.
Anything going up and to the right on your line charts needs some discussion.
You might want to address any monthly anomalies. Are they seasonal or was it a promotion.
If it's a promotion then how much of a price drop would you suggest to reach the uptick in penetration/sales and make MORE absolute sales.
i.e. in a normal month penetration is 60% but on promotion it jumped to 66%.
If that promotion was LESS than a 10% discount then it was a good idea.
But also I would consider some benchmarking.
- Take the best performing site per product (average penetration over the whole period).
- Create a new table showing the best vs. the average (ex-the best) - again for each product.
- Calculate the uptake in sales if every site were as good as the best.
Then suggest getting the sales guys from the best to train the others.
Or again, if it is a promotion led product - they should apply the most successful promotions across the board.
The key is looking for trends.
Anything going up and to the right on your line charts needs some discussion.
You might want to address any monthly anomalies. Are they seasonal or was it a promotion.
If it's a promotion then how much of a price drop would you suggest to reach the uptick in penetration/sales and make MORE absolute sales.
i.e. in a normal month penetration is 60% but on promotion it jumped to 66%.
If that promotion was LESS than a 10% discount then it was a good idea.
But also I would consider some benchmarking.
- Take the best performing site per product (average penetration over the whole period).
- Create a new table showing the best vs. the average (ex-the best) - again for each product.
- Calculate the uptake in sales if every site were as good as the best.
Then suggest getting the sales guys from the best to train the others.
Or again, if it is a promotion led product - they should apply the most successful promotions across the board.
walm said:
But also I would consider some benchmarking.
- Take the best performing site per product (average penetration over the whole period).
- Create a new table showing the best vs. the average (ex-the best) - again for each product.
- Calculate the uptake in sales if every site were as good as the best.
Then suggest getting the sales guys from the best to train the others.
Or again, if it is a promotion led product - they should apply the most successful promotions across the board.
Also, maybe look at whether any similar data is available by the following :-- Take the best performing site per product (average penetration over the whole period).
- Create a new table showing the best vs. the average (ex-the best) - again for each product.
- Calculate the uptake in sales if every site were as good as the best.
Then suggest getting the sales guys from the best to train the others.
Or again, if it is a promotion led product - they should apply the most successful promotions across the board.
- By the whole sector
- For a rival company
- For a similar company not in direct competition
ETA - don't actually do this, rather suggest it in your report
With my CIMA student head on, would market penetration necessarily equate to more profit? No point being 100% of the market if you're making a loss on every sale, so what's the return on each product? Could you maybe talk about bottlenecks? Are there any limiting factors (e.g. staffing)? Are the higher % products marketed on price or on quality? Fun!
Good luck
Gassing Station | Finance | Top of Page | What's New | My Stuff