What would the unemployment rate in April 2018 be?

The weekly unemployment rate had spiked to 7.41% in the week ended April 8

The unemployment rate in India was around 7.25 per cent during the first fortnight of April 2018. This unemployment rate is high compared to the levels observed in a fairly long time.

The weekly unemployment rate had spiked to 7.41 per cent in the week ended April 8. This was the highest weekly unemployment rate in 78 weeks, or since early October 2016. However, a solitary spike does not always tell a true story. It could be an outlier -- particularly because it was significantly higher than the observed average of around 6.5 per cent in the preceding weeks.

But, the high unemployment rate has persisted in the following week of April 15. Now, the preceding week's 7.41 per cent does not look like an outlier but, possibly, looks like an indication that the unemployment rate has inched up again.

The unemployment rate has been rising since July 2017 when it clocked a mere 3.4 per cent. The rate rose quickly to 5 per cent by October 2017 and then stabilised around 5 per cent for three months before spurting to 6 per cent in February and March 2018. Now, with data for two weeks in hand, it seems poised to rise higher in April. It would be safe to assume that the rate has risen and April is likely to report an unemployment rate that would be the highest since demonetisation.

Weekly estimates are a close approximation of the monthly estimates. Weekly estimates are based on a sample of about seven thousand households that provide the employment/unemployment status of nearly 25,000 individuals that inhabit these sample households.

However, there are a few details that one needs to keep in mind while extrapolating weekly estimates of unemployment to monthly estimates.

First, weekly estimates are for the week ended Sunday and months don't necessarily end on Sundays. But, this is a very minor problem. 

Secondly, weekly estimates are not adjusted for non-responses and monthly estimates are adjusted for non-responses. This makes the monthly estimates a little more reliable than the weekly estimates. You are justified if you ask, so, why don't we just adjust the weekly estimates for non-responses. 

The answer is that the weekly sample is a little fluid because of operational problems. Survey execution at a household that is supposed to be surveyed in a particular week may have to be shifted to the next week because of a local problem. For example, in the last couple of weeks, internet services were temporarily suspended in many parts of the country to contain the several protests that have erupted. This hampered survey execution temporarily. As an aside, it is not a good sign when a country has to suspend internet services repeatedly from entire regions. It brings far too many activities to a halt -- including tax filings, regulatory filings, financial transactions and settlement of bills.

Thirdly, and more substantively, weekly estimates are based on a survey design that uses appropriate weights for rural and urban India at the all-India level. The monthly estimates are based on a survey design that uses appropriate weights for rural and urban India at the state-level. Thus, there is a much greater stratification deployed in the monthly estimates than in the weekly estimates. This again, makes the monthly estimates more reliable than the weekly estimates.

The total number of strata used in the monthly estimates is 49. If the responses from any of these is less than a minimum requirement then the data from such strata is not used because they can skew the results. This greater stratification and stringent requirements on the sample make the monthly estimates fairly robust.

Data of the recent past suggest that weekly estimates overestimate the unemployment rate, on an average, by about 50 basis points compared to the monthly estimates. This implies that the 7.25 per cent unemployment rate we see in the first fortnight of April 2018 could well be 6.75 per cent. Even this is significantly higher than than the unemployment rate of 6.2 per cent in March and 6.1 per cent in February. 

It is apparent that the unemployment rate which has been rising steadily over the past eight months will continue to rise during the ninth month -- April 2018.

In spite of the several technical challenges involved, fast-frequency measures are very useful to foresee trends and reduce the uncertainties in assessing where we stand and where we are likely headed. This is an important contribution made by the BSE-CMIE partnership in understanding unemployment in India. 



Methodology

Consumer sentiment indices and unemployment rate are generated from CMIE's Consumer Pyramids survey machinery. The weekly estimates are based on a sample size of about 6,500 households and about 17,000 individuals who are more than 14 years of age. The sample changes every week but repeats after 16 weeks with a scheduled replenishment and enhancement every year. The overall sample size run over a wave of 16 weeks is 158,624 households. The sample design is of multi-stratrification to select primary sampling units and simple random selection of the ultimate sampling units, which are the households.

The Consumer Sentiment index is based on responses to five questions on the lines of the Surveys of Consumers conducted by University of Michigan in the US. The five questions seek a household's views on its well-being compared to a year earlier, its expectation of its well-being a year later, its view regarding the economic conditions in the coming one year, its view regarding the general trend of the economy over the next five years, and finally its view whether this is a good time to buy consumer durables.

The unemployment rate is computed on a current daily basis. A person is considered unemployed if she states that she is unemployed, is willing to work and is actively looking for a job. Labour force is the sum of all unemployed and employed persons above the age of 14 years. The unemployment rate is the ratio of the unemployed to the total labour force.

All estimations are made using Thomas Lumley's R package, survey. For full details on methodology, please visit CMIE India Unemployment data and CMIE India Consumer Sentiment.

The creation of these indices and their public dissemination is supported by BSE. University of Michigan is a partner in the creation of the consumer sentiment indices.