Let’s take a random sample and see

Why do you want to take a random sample? An engineer makes his entire plan on a computer first, and subjects it to every sort of test, even when each element in it has known properties. He makes scale models, and makes corrections and tests every step of the way, till he’s absolutely sure. Then puts the structure into use very gradually. Ditto for pharmaceuticals. Yet direct marketing must hold up to testing on a random sample!

When any idiot will tell you that a test on a random sample is bound to fail, because most people in the list are bound to say No. For starters, many will never buy what you are selling. And even the ones who will are very unlikely to all be in the market exactly when you’re testing.

Which means even if a section gave a ‘thumbs up’ to the test, it’s bound to be swamped by the overall and overwhelming failure that permeates through the list as a whole?

Does that mean we shouldn’t take random samples? Of course, we should. But after understanding what the term means. We should take a random sample of those sections which we think are most likely to form the market; take enough from each of these to yield dependable numbers; and a random sample of the balance, to see how well your selection works out in real life.

Mutual funds and film dance

Switch on any film music channel and you see the same dance in every song. It’s invariably jerky and graceless. And many a time seems to have nothing to do with the song going on.

Anyway, one common characteristic of these dances is that their parts don’t seem have any sequence.

Now, in the nice old fashioned dances you sometimes had entire episodes of the story. Some were elaborately choreographed. Two prime examples that come to mind are Goldi Anand’s Guide (dances by Hiralal and Sohanlal) and Teesri Manzil (Herman Benjamin).

So why don’t we see dances like that any more (that is a ridiculously sweeping statement, but let’s stay with it)? I think it’s because a collage of ‘pretty’ sights can’t go very wrong. Lacking perhaps the time, talent and guts to do a really good piece, directors, chorographers and stars put together a sum of pretty parts that passes muster, though the whole is certainly not beautiful, let alone memorable.

It’s something like a mutual fund. It’ll never be as good as a blockbuster stock, but overall, it’ll do. Parts may even be excellent. (Ref: http://en.wikipedia.org/wiki/Curate's_egg)

Jumbo mistake?

Jumbo vada pao (a Bombay adaptation of the hamburger, which uses a potato patty) is one brand everyone admires.

While flipping channels I caught its younger owner describing his business. I remember one particular point: He said he wanted to expend overseas, but when he found that the population of mere suburb of Bombay was higher than the entire population of Indian expatriates in some gulf emirate, he decided against overseas expansion and concentrate on home.

At that time I admired his commonsense and his ability to put profits before ego.

Now, I’m not so sure.

Did he take into account the premium that gulf Indians would pay for food that reminds them of home?

Did he wonder about the chances of locals liking the food too?

Or of a rich sheik liking it so much that he’d buy a share in Jumbo and help them grow?

There are almost no Chinese in India. Yet there are hundreds of Chinese restaurants. Maybe Jumbo could have returned the favour to China.

Anyway, a single-factor decision looks very strange, especially from a successful chain. Perhaps there were more things on their minds when they decided against expanding abroad, and the owner ‘dumbed’ it down for TV (‘Dumb down’ is an idiotic thing to say, because it assumes people who cannot talk cannot think. I don’t mean that, of course. But I’ll let this stay to remind myself how ‘dumb’ I am.)

No web shopping in India?

Right now we have many festivals in India – Dushera, Id, Diwali, Chat, Christmas, New Year. Yet there is very little of web shopping in the news. I haven’t come across even one article. There are ticket offers, but that’s about it.

Why not an Indian food chain?

My wife and I have lived in Kolkata, Bangalore, Delhi and Bombay. And we are pretty sure that recipes don’t cross borders too well. For example, sambar becomes sweet in Bombay. And South Indians add tej patta to almost everything. While these adaptations may make the dishes more palatable to local palate, there are surely many who want the authentic taste. After all, what’s the fun in eating out if it tastes like the food one has at home every day (Eating out from compulsion is another matter.)

Now, South Indian fried snacks are accepted across the country, as are Delhi chaats, and Bengali sweetmeats. Rajasthani savouries are also relished. So why aren’t there food chains for any of these?

I guess there are a few with shops across India, but none at the scale of, say, McDonald’s or KFC in USA.

Is it a only a matter of time for big chains come up in India?

Or is Indian food far more difficult to cook, and cannot be adapted to industrial cooking the way hamburgers are?

Or is it the ‘vision’ thing?

Keep in touch in B2B

Would it make sense for B2B marketers if they insisted that people who want their newsletters have to give email ids and business addresses? This will ensure that they change contact details when they shift jobs. Of course, one must publish a fantastic newsletter for this to happen.

Bake me a plan

Pat a cake, Pat a cake, baker's man
Bake me a cake as fast as you can;
Pat it and prick it and mark it with a 'B',
And put it in the oven for Baby and me.

Prospective clients have the same attitude towards agencies wanting their business. Give us a plan, and if it’s any good (read: If you are cheapest) we’ll take it forward.

You won’t expect a lawyer, doctor or architect to work under those terms, would you? Or a dress designer? You hire on the basis of recommendations and reputation, fix a price, then start the work.

But agencies are supposed to do elaborate speculative plans, including detailed costing, creative elements, response rates, and RoI.

Anyone with commonsense will understand the whole thing is absurd. How can another company, no matter how intelligent and experienced its people are, solve your business problem on the basis of an interview and a few downloads from your website?

What we probably don’t realise is that this method is counterproductive. Because an agency doing a speculative plan will be stupid to work hard. Besides, even if it did, it just doesn’t know enough about the intricacies involved to come up with something truly worthwhile. If it does, it probably owes more to luck than skill or brains.

Wouldn’t it be better to buy the agency’s commitment by appointing first, giving a few simple jobs to familiarise their people with your company, then scaling up to plans and programmes?

PS: Admittedly, in certain engineering work detailed plans are asked for in the contract bid. However, three things need to be kept in mind: (a) These are for very large contracts, where the rewards are very large too, and make the risks worthwhile (b) The requirements are given in some detail (c) Engineering projects are notorious for budget and time overruns.

No beta, yes risk

In direct marketing texts very little is discussed about sample sizes, and even less about Type I and Type II errors. Admittedly, the latter is somewhat complicated, and business statistics books often recommend that readers go over sections covering it carefully and repeatedly.

‘Complicated’ is, unfortunately, not synonymous with ‘of theoretical value only’. In fact, the opposite is true in this case, because the Type II error is of fundamental importance, as becomes apparent if we step back and ask why we bother about test and sample size in the first place.

We do so, basically, for two reasons. First, we don’t want to throw the baby out with the bathwater. We don’t want to take a test result that is somewhat less than our expectation on its face value. We’d rather use the test to estimate the list characteristic leading to the result, and if that turns out to be acceptable, we’d like to scale up. This is why we worry about a (the probability of rejecting a true null hypothesis).

At the same time, we don’t want to lose money by scaling up when we shouldn’t have. This means we should worry about the minimum response that would be ok. For this we must worry about b (the probability of accepting a false null hypothesis).

Yet, the commonly used formula for sample size completely ignores beta (not only in direct marketing books and online calculators but also in most of the business statistics texts I’ve come across)!

The formula goes like this:

N =	za/22p(1-p)
	E2

Where

z is the value used for the specified confidence level

p is the estimated response (population proportion) and

E is the ± sampling error allowed.

Let’s say estimated response is 2%; the allowed error is ±0.25%; and confidence level is 90%.

Putting these into the template yields a sample size of 8,485.

Let’s see what this means in terms of b if the true response (which we’ll get to know only if we scale up to the entire list) is, say, 1.65%. b turns out to be 23%, that is, 1 in 4!

Humm, that’s bad. There’s a 1 in 4 chance that while accepting a figure between 1.75% and 2.25% as ‘as good as’ a 2% response rate, we’ll actually accept a list with only 1.65% response.

No wonder one of the well accepted rules of the thumb in direct marketing goes: “As a rule, the response rate from a rollout to the balance of the list after a successful test mailing will usually be lower than the response from the test.”

This may be because of a variety of differences between test and rollout conditions. But one thing needs to be kept in mind: If one ignores Type II errors, the success of the test can be very suspect indeed.

A way out could be to use an alternative formula:

N = (	|z0|(p0(1-p0))1/2 + |z1|(p1(1-p1))1/2	)2
	p0 – p1

Where
p₀ is the estimated response

p₁ is the value for which Type II error will be monitored

z₀ is z_a or z_a/2 depending on whether the test is one- or two-tailed and

z1 is z_b where b is the limit on type II error probability when p = p₁.

Let’s see what happens if estimated response is 2%, the allowed error is ±0.25%, and confidence level is 90% (as before); while p₁ is 1.65% and b is 10% (i.e., there is only a 1 in 10 chance – not 1 in 4 as earlier – that we’ll accept a list with a real response rate of 1.65% by performing the test).

We get a sample size of 12,643.

Sure, it’s a 50% increase in sample size. But it may be well worth it if the roll out numbers and costs are far higher than the test’s.

In any case, won’t decisions be better if they were taken with a clearer idea of the risks?

PS: Please excuse the ungainly appearance of the formula. It's the best I could manage using a Word file. Both formulas can be found in the useful templates at http://highered.mcgraw-hill.com/sites/0070620164/student_view0/excel_templates.html

Reader’s Digest list

Reader’s Digest is often talked of as a good magazine to learn English from. Shouldn’t they target people buying English courses?

Would you tell your plumber how to do it?

It’s your kitchen, your money, your headache. Yet you won’t tell your plumber how to fix your kitchen. You may try, but if he thought it won’t work, he won’t do it your way. If you insist, he won’t do the job. He’ll tell you, in no uncertain terms, to go to someone else. Chances are, you’ll back off. He know best.

Yet you’ll rewrite your agency’s copy, and redo their art. Chances are they don’t know a thing. Then why did you hire them in the first place?

Yet you pay them a lot more than you pay your plumber.