Wednesday, May 20, 2009

Survey technique for awkwards questions and evasive answers

I enjoyed this piece by Sidin Vadukut in last Saturday's Mint (pasted below in italics). It relates to something we often have to deal with at work - how to estimate the prevalence of issues that people may be uncomfortable talking about. Not surprisingly the Randomized Response Technique described below involves a derived answer, one that thoroughly masks the source of individual responses. Nothing wrong with that of course. In fact ensuring the confidentiality of respondents should be part of a researchers equivalent of the Hippocratic Oath. I've pasted the article in its entirety below.

In a landmark 1965 paper called “Randomized Response: A Survey Technique for Eliminating Evasive Answer Bias” author Stanley Warner outlined an interesting way of carrying out surveys. Let me explain the idea without going too much into the mathematics. Instead, I’ll focus on how it’s done, why it’s useful and what happened when we ran a little Lok Sabha exit poll here in the office using Warner’s Randomized Response method.

The Randomized Response Technique is used when you want to research the prevalence of issues that people feel uncomfortable talking about. A college would never be able to accurately survey its students for prevalence of drug use and cheating. A student would never risk the probability of being identified saying: “Yes.

And sometimes both at the same time.” Warner’s survey works in two stages: first you ask the respondent to roll a dice, pick a card and so on. Depending on the random result, you ask them to answer one of two questions without yourself knowing which question. (Hold on.) The respondent merely says if they agree or disagree with it. Then you survey the next respondent. And so on.

Finally the math comes in. Using formulae which look at the chance of a question being picked and the regularity with which an answer was given, you could approximate what the whole selection of respondents felt. Obviously, the bigger the sample, better the accuracy.

(More clear math in the second paper linked below.) But let me tell you what we tried in the office We took 16 identical pieces of paper and on 12, we wrote the statement “I did not vote for the UPA (United Progressive Alliance): Congress or allies”. On the remaining four, we wrote “I did vote for the UPA: Congress or allies”. Testy questions indeed. Then we shuffled the cards statement-side down and asked employees to pick one each. (The card was returned and the deck shuffled after each employee. Only people who actually voted were allowed to pick.) Each employee picked a card at random, looked at the statement and then merely said if they agreed with it or not. As a surveyor, all I am noting down is the number of agrees and don’t agrees. Nothing more. I have no idea which question they got, and so what their response implied. Then I ran the math. Using a sample size of 34 voters (very small, but good enough to blog about) and the 16 cards, we were able to approximate that 32.53% of the office voted for the UPA and the rest did not vote for the UPA. (So we really can’t say who they voted for. That wasn’t the question you see.) Of course, it should be wildly inaccurate given the sample size. But it’s a fun, mildly magical way to do exit polls, no? Why not try one in the office right now, process the results and then look like a genius? And unlike some of those TV channels, you have the math to prove it.

Warner’s paper can be found at: sta300308/ref4_1.pdf (Alternatively, use the following link: An easier explanation can be found at (Use the following short address: randompoll2)

Saturday, May 16, 2009

Providing health care in India's villages - An administrative problem that needs managerial solutions

I couldn't agree more with Shoba Narayan's analysis of the problem of providing health care to the over 600,000 villages across India. It's a massive logistical and administrative problem that is crying out for common sense solutions. Meeting the people who are responsible for the provision of health care services in rural India (ANM's, ASHA's and Anganwadi workers), as we often have the opportunity to in the course of our work at Barometer, is a uniformly humbling experience. For the most part these are incredibly hard working, passionate women, who think nothing of being spread thin across large popluations with minimal infrastructure and support. Maybe the newly re-elected UPA/Congress Government, which has reaped the dividends of concentrating on the rural economy, will make this a priority. Here's an extract from the article I was referring to:

The healthcare administrator’s job, I would argue, is more important than the doctor’s. Except, in most villages, such a job doesn’t exist. The PHCs are manned by doctors and the panchayat leader squeezes in the sanitation and nutrition work amid her other duties. The ASHAs (accredited social health activists) do a decent job and are one of the most innovative schemes that the Indian government has come up with. But they are stretched. Just as the government recruited local women into becoming ASHAs, they can perhaps climb the ladder to becoming rural health supervisors. This supervisor’s job would be part PR, part brute-force execution and part infrastructure. She needs to convince the people who live on the banks of the Krishna that streaming their wastewater into the river will cause water-borne diseases downstream. She needs to cajole and coerce the village panchayat into installing toilets rather than having people defecate under the great blue yonder.

Part of the problem is that doctors, let alone administrators, don’t want rural postings. In late February, then Union health minister Anbumani Ramadoss announced that he was going to make rural postings compulsory even though, as many Indian medical blogs noted, they have “failed miserably” in the past. One medical education blog written by a Dr Anshu said that after being trained in medical colleges with sophisticated equipment and colleagues, doctors found the “learned helplessness” of rural postings frustrating.

This is one instance where I believe throwing money at the problem will help. Rural postings can only become attractive when they afford job satisfaction. Private charitable hospitals are doing a great job with this. Teresa is now taking her son to the Sathya Sai Baba hospital in Whitefield, Bangalore. We got her son an appointment via email and the neurologist is treating Gerald without taking a penny. The Mata Amritanandamayi Hospital has a waiting list of doctors wanting to serve, I am told. I am not a follower of “Amma”, or Sathya Sai Baba for that matter, but I would urge them to set up their institutions in remote rural spaces. The global manpower and funds they can draw will ensure a facility that will serve as a draw for not just patients but doctors and therefore, a thriving medical community that gives job satisfaction in rural postings.

Wouldn’t it stand to reason that the jobs that were the least satisfying ought to be paid the most? Of course, by that logic, a street sweeper ought to be paid more than a CEO. By that same logic, a rural medical posting ought to get more than the measly Rs10,000 that it commands. Double their wages, I say, to compensate for the intellectual isolation that doctors complain about. In this recessionary economy, that would make doctors flock to villages in droves.

You can read the entire article here.

Monday, May 4, 2009

Hindustan, Schizostan

A week spent in the field, deep inside rural India, and it's hard not to return feeling that we're a nation characterized by even more schizophrenia than our cities suggest. We're going to be a nation of a billion cell phone users with no electricty to charge the phones. A million Nano's and no roads to drive them on. Bijli, sadak, and paani (electricity, roads and water) are going to be election mantras for ever because actually delivering on them hardly seems to be necessary for getting elected. Yet when market forces are unleashed the Indian entrepreneur and private sector never fails to deliver value. You only need to find yourself in a State Tourism hotel (i.e. Government run) in small town India before discovering that there's a privately run option next door to see the difference.

Tavleen Singh hits the nail on the head when she says:

" In other countries, when school teachers do not turn up to teach they are sacked. When public services like hospitals and health centres do not do their job they are closed down, and long before major towns like Ankleshwar and Baruch end up looking like slums, something is done to stop this happening. When I drove through them last week on Narendra Modi’s new six-lane highway, I was gripped by a sense of despair. If we can build six-lane highways why is it so hard for us to come up with systems of waste disposal? Will we wait till all our highways are lined with rotting garbage before we realise that something needs to be done?
Probably. It has always been that way. In my view this is because we have tried to build the edifice of a modern, democratic nation without laying the foundations. The foundations can only be created by investment in human capital. You cannot build a modern democracy if 45 per cent of your children are malnourished, you cannot build a modern democracy if your schools do not have teachers and if your public healthcare is mostly a means for corrupt officials to make money by handing out construction contracts to their friends and family. You cannot build a modern democracy if you have not been able to provide that most fundamental of human needs: clean water. Yet, this is what our political leaders have tried to do. And, we have let them.

We in the media are almost as much to blame as the political class because we spend far too much time talking about stupid things and ignoring what is crucial. Throughout the election campaign we have spent so much time discussing the foibles and failings of the Gandhi progeny that we have found little time to talk of real issues. I got so tired of hearing important journalists discuss the badness of Varun Gandhi and the goodness of Rahul and Priyanka that I stopped watching the news channels. How many times did we hear serious discussion of why our public services are such a mess or why after 60 years of Independence our political leaders are unable to provide clean drinking water? Or why unplanned urbanisation has put Bharat Mata well on the road to becoming a continent of slums by 2050?

Having said this I must add that all the big changes that I have seen on my travels in the wilds of India that is Bharat have been wrought by the arrival of television and the cell phone. It is because of these two technological marvels that the 21st century is beginning to limp slowly into even our remotest villages. Thanks to technology, the poorest, most underprivileged Indians have realised that they do not have to live this way. And, that there are many Indians who do not live without clean water, electricity and roads. They know that there is only one real issue in this election. Governance. "

Read the whole article here -

However, I'm not sure if knowing that governance is the real issue actually affects voting behavior. Maybe so in states where people can see that its possible to escape from the quicksand of poverty. But not so in less developed, Bimaru type states where prospects for the average person are so bleak that a few cases of booze or petty cash disbursements that take care of the next couple of meals are more than enough to buy votes.