Labor Market Dynamics – Jobs. Trends. Insight.

Preliminary report from BLS shows gain of 162,000 jobs in March

By Juli Morris on April 2, 2010 in BLS Nonfarm Employment, Labor Market Dynamics.

Employment rose by 162,000 jobs in March, according to today's preliminary report from the Bureau of Labor Statistics. Consensus estimates had predicted a gain of 200,000 jobs. The largest job gains were in temporary help and the health care sector, with losses in finance and information. The March numbers also reflect temporary government hiring for the 2010 Census, representing almost a third of jobs added. The economy has shed nearly 8.5 million jobs since the start of the recession in December 2007.

Click chart to view full size

Along with the preliminary report for March, the BLS issued its Final Estimate of job losses for January at a gain of 14,000 jobs, up 40,000 from its revised estimate of -26,000. It raised its February preliminary estimate up 22,000 jobs for a revised loss of 14,000 jobs. One more revision for February may still occur.

As expected, the unemployment rate held steady at 9.7 percent.

March 2010 BLS Nonfarm Forecast: -52,000

By Charles Thibault on March 23, 2010 in BLS Nonfarm Employment, Unemployment Insurance Claims.

WANTED Technologies expects that the Bureau of Labor Statistics will announce a drop in US Nonfarm Employment of 52,000 workers for March 2010.

Last month, the BLS said that US Nonfarm Employment dropped by 36,000 workers.

Click chart to view full size

This month's forecast is based on the following labor market dynamics:

Particularly meaningful for this month's forecast are offsetting changes in new Unemployment Insurance Claims:
- There were consecutive increases of 32,000 and 24,000 new UI Claims for the weeks ending February 13th and February 20th 2010. The week ending February 20th had a total 498,000 new UI claims. The BLS measures employment on the 12th day of each month, so technically the report ending February 13th can be excluded since it overlaps with February's employment count. However, it still provides a signal on what happened in the labor market and is a close straddle on the March employment reporting date.
- More recent UI claim reports have been positive. New Claims fell by 30,000 for the week ending February 27th, settling at 468,000. In the past two weeks UI Claims have improved marginally as well, falling to 462,000 and 457,000 for the weeks of March 6th and March 13th. This is a good signal as it indicates continued positive momentum in the labor market. The 4-week moving average has returned to levels around 470,000 and will fall precipitously when the value of 498,000 drops out the 4-week window used this week's release.
- The 4-week moving average now stands at 471,250. This is an increase of 3,500 claims relative to the 4-week moving average of 467,750 seen a month ago. Over a 4-week period, that means a cumulative total 14,000 more new Unemployment Insurance Claims.
New online job ads on major national job boards grew by 9,500 ads in March. This is a slight softening after 4 consecutive months of improvements in the range of 12,000 to 14,000 online job ads. Changes in Employment depend two variables – separations and hires – and we've discussed in a previous post how it's possible to have both growing hiring and falling employment.

Both of these factors combined – a slight increase in new UI claims, and a slight softening of labor demand – lead us to forecast a drop in US Nonfarm Employment of 52,000 workers. This is a relative worsening of 16,000 workers compared to last month's drop of 36,000 workers. There was no surge in Hiring Demand that would lead us to forecast employment gains.

Employment changes will fluctuate around zero as the economy and labor market have reached a steady-state equilibrium.

Over the past three years, the average difference between the BLS's first preliminary data release and its third and final data release has been 78,000 workers a month. The BLS's first preliminary report is treated as a forecast of its third and final report. The WANTED historical standard of error of forecast is 84,000 workers per month, which is consistent with the BLS's average error to its own data.

The BLS will release its Employment Situation Summary for March on Friday, April 2, 2010, at 8:30 a.m

Canadian Online Job Ads Grow 2.5% in February, Pushing Employment up 21,000

By Charles Thibault on March 15, 2010 in Canadian Employment.

Hiring Demand and Employment grew in Canada in February, according to data from WANTED Analytics and Statistics Canada. Employment grew by 21,000 workers in February on a seasonally adjusted basis. This growth was supported by 4,000 more online job ads compared to January. A total of 157,500 paid-for online job ads were posted between January 15th and February 15th on a seasonally adjusted basis, the date at which employment is reported in Canada.

The following graphs shows year-over-year percent changes (growth trends) in Hiring Demand and year-over-year percent changes (growth trends) in Canadian Employment levels. The data is weekly. WANTED reports online job ad counts on a weekly basis, so monthly Employment counts have been interpolated between data points to match the more frequent reporting of job ads.

The graph above shows a "stabilization" period in 2009. Hiring Demand and Employment have bounced back and have been trending upward since October 2009. Since then, Hiring Demand has not fallen off its trend and analysts can expect employment gains for March.

In statistics, it is customary to look at changes in economic variables. From an economic policy point of view, the variable of interest is the change in employment, not the total employment level (although that number does influence tax intakes, for example). The way to measure how quickly Canada is exiting the recession is to measure how quickly the Canadian economy can add jobs. In finance, the stock price or an index value are not relevant either. Analysts measure expected returns – or changes in stock prices.

The following scatter plot shows the year-over-year change in Canadian Employment and changes in the number of online jobs ads. The relationship is fitted using a quadratic equation. The relationship is also allowed to be different depending on the economic cycle – the structural relationship is not the same when the economy is growing than when it is shrinking. A cubic or fourth order polynomial equations can fit the data adequately without this assumption if desired.

It is exactly such a "structural relationship" that allows the forecasting of future Employment levels:

Notice the "clustering" at the top right of the graph. This makes sense qualitatively – even if employers posted more online jobs, there's a limited number of workers available to fill those vacant positions. In other words, even if the companies posted a record number of job postings, the effect on employment gets "topped off" because there's a finite supply of workers. A similar clustering appears on the bottom left. Even if employers have clearly said they aren't hiring, they can only shed so many workers. It's impossible for companies to shed all of their workers even if they've completely stopped hiring. So a similar effect creates a cluster at the negative end of the spectrum too.

In order to prove that an indicator can predict future values of published macroeconomic data, it has to be shown "which series leads which". If employment moves before hiring, then Hiring Demand isn't that valuable a piece of information. Fortunately, Hiring Demand explains about 94% of the change in employment, and leads those changes by two weeks.

When regressing two variables against each other, it is customary to look at the R-square, which is a measure of model fit. The R-square is the "amount of change in the dependent variable that can be explained by the model". An R-Square of 1 means you're able to explain 100% of the dependent variable – the model is a perfect fit. An R-square of 0.50 means the model explains 50% of what's going on with the dependent variable.

The simple cubic equation for the data above has an R-square of 0.944 – changes in the number of online job ads explain 94.4% of the change in Employment.

The following histogram shows model fit (R-Square) based on shifting Hiring Demand backwards or forwards a certain number of weeks.

Models where Hiring Demand data precede Employment data have negative time shifts (lag operator). Models where Hiring Demand data follows Employment data have positive time shifts (forward operator). The black column represents a contemporaneous regression or no time shift of the data.

: Source: WANTED Analytics data, Statistics Canada data

The two-week lag has the strongest fit. In other words, the model using this weeks' Hiring Demand data to predict what will happen to Employment two weeks hence has the strongest predictive power. That column is highlighted in green.

Had the "strongest relationship" occurred to the right of the zero lag, the number of online job ads would depend on employment levels, and we would not be able to say that Hiring Demand leads Employment.

So what proves that Hiring Demand leads Employment is that the model decays much faster to the right than it does to the left. Look, for example, at shifts of length 12. On the right, changes in employment explain about 72% of future hiring. However, online job ads 12 weeks ago are still able to predict 83% of the change in Employment. Previous values of Hiring Demand are much better at predicting future values of Employment than the other way around.

Is there any theoretical basis for this at all? The nature of the hiring cycle explains why Hiring Demand leads employment. The posting of an online job ad is a forward looking decision – companies post jobs online before they hire. In fact, the hiring cycle usually lasts 8 to 12 weeks: post a job online for 30 days (4 weeks), conduct a round of interviews (2 weeks), conduct a possible second round of interviews (another 2 weeks), and hire. If that hire is already employed somewhere else, the customary two week's notice is tagged on. (Compare this to mattress sales, which lag home sales. Home-buyers usually move into a new house, then purchase a mattress then can bring into the house. Consumers usually don't buy a new mattress for a new home and store it somewhere while they're waiting to move in. So, mattress sales would not be a good leading indicator of home sales, but stock analysts interested in forecasting the performance of mattress manufacturers could use home sales data).

From a strategic perspective, one more element is missing in order to complete the picture. Hiring Demand leads Employment, that's been shown. However, if Hiring Demand data is released with such delay that that statistical lead time evaporates, the data is not of much help. Fortunately, Hiring Demand provides an additional 4-week reporting advantage. Statistics Canada released its February 15th employment counts on March 12th, 2010. That is a 4-week difference. (Analysts there must compile and process surveys, and seasonally adjust their results). In addition to the 2-week statistical advantage, there's a 4-week reporting advantage because WANTED can tabulate weekly online job counts within a few days (as opposed to a month later).

In sum, three factors combined allow WANTED Technologies to accurately forecast movements in Canadian and US Employment levels:

- There is a structural, long-term economic relationship between the the number of online job ads and employment growth. Online job ads predict more than 94% of what happens to total employment levels. From a practical perspective, it's not much of a leap to suggest that when companies post an online job ad, they'll be hiring a worker. On the other side, companies also generally do not post jobs when they're laying off workers. The number of online job ads is indicative of both employment gains and losses.

- Hiring Demand provides a 2-week statistical advantage. In other words, Hiring Demand leads Employment by about two weeks in Canada. That relationship is strong even when looking at 2 or 3 month lags, allowing multiple step-ahead forecasts.

- Professional forecasters gain an additional 4-week advantage because Statistics Canada reports employment with a one-month lag. Combined, statistical lead time and reporting lead time generate insight 6 weeks before employment data is made publicly available.

Preliminary report from BLS shows loss of 36,000 jobs in February

By Juli Morris on March 5, 2010 in BLS Nonfarm Employment, Labor Market Dynamics.

Employment fell by 36,000 jobs in February, according to today's preliminary report from the Bureau of Labor Statistics, citing severe winter storms as a factor in reducing payroll employment. Consensus estimates had predicted a loss of 50,000 jobs. The largest job losses were in construction and information, while temporary help again added jobs. The economy has shed 8.4 million jobs since the start of the recession in December 2007.

Along with the preliminary report for February, the BLS issued its Final Estimate of job losses for December at a loss of 109,000 jobs, up 41,000 from its revised estimate of 150,000. It lowered its January preliminary estimate down 6,000 jobs for a revised loss of 26,000 jobs. One more revision for January may still occur.

Click chart to view full size

The unemployment rate held steady at 9.7 percent; consensus estimates had expected it to climb slightly to 9.8 percent.

BLS Nonfarm Employment Forecast: +5,000

By Charles Thibault on February 22, 2010 in BLS Nonfarm Employment.

WANTED Technologies expects the BLS will report a small gain of 5,000 nonfarm workers when it releases its Februrary 2010 Employment Situation on Friday, March 5, 2010, at 8:30 a.m. (EST).

Hiring Demand has stabilized and changes in employment will fluctuate around zero. The following graph tracks new online jobs, daily, over the past 4 months. Notice the periodic weekend dip when workers aren't at their office to post jobs. Jobs have been trending upward at a steady rate, about 0.5% a week.

There were 10,700 more online job ads on major US national employment websites on February 15th compared to January 14th (Monster, CareerBuilder, HotJobs), a 2.4% increase in Hiring Demand. The growth rate did flatten compared to last month, but at least it has been positive/above zero for last the 4 months – labor demand is growing.

New UI Claims are flat compared to last month. However, they were on a fairly aggressive downward trend before growing for two consecutive weeks. The S&P 500 Index also fell 4.5% during that period. Continued Claims fell by about 50,000 compared to two weeks ago, suggesting that there has been at least some absorption of unemployed workers in the past month.

Preliminary report from BLS shows decline of 20,000 jobs in January

By Juli Morris on February 5, 2010 in BLS Nonfarm Employment.

Employment fell by just 20,000 jobs in January, according to today's preliminary report from the Bureau of Labor Statistics. Consensus estimates had predicted no change. The largest job losses were in construction and transportation and warehousing, while temporary help and retail trade both added jobs. The economy has shed 8.4 million jobs since the start of the recession in December 2007.

Along with the preliminary report for January, the BLS issued its Final Estimate of job losses for November at a gain of 64,000 jobs, up 60,000 from its revised estimate of 4,000. It lowered its December preliminary estimate down 65,000 jobs for a revised loss of 150,000 jobs. One more revision for December may still occur. These revisions were also affected by Annual Benchmark Revisions, which restate the history of US employment.

The unemployment rate unexpectedly fell from 10.0 to 9.7 percent; consensus estimates had expected it to climb slightly to 10.1 percent.

January 2010 Employment Forecast – Withheld

By Charles Thibault on January 26, 2010 in BLS Nonfarm Employment.

Under exceptional circumstances, WANTED Technologies will withhold its forecast of US Total Nonfarm Employment for January 2010, as reported by the Bureau of Labor Statistics.

Every year, the BLS revises the entire history of US employment in what it calls "Annual Benchmark Revisions". These revisions create a break in the data series: forecasts of month-over-month changes aren't particularly useful when there isn't a 'next month' in the series, or when the data series is only a month old. This is what happens when the BLS revises its US employment time series – the old series ended, and a new, restated one begins.

Additionally, annual revisions are released at the same time as the monthly Employment Situation Summary report which contains the data we're forecasting. In other words, not only would we be forecasting a number for a series that's no longer being used, we'd be forecasting the future values of a dataset we don't have access to.

Additionally, we are expecting substantial revisions to 2009 employment numbers because of the volatility in the US economy over the past 16 months.

In combination, these three factors, have prompted us to withhold our monthly forecast:

The additional forecast standard error introduced by the annual Benchmarking process is 56,000 workers per month (estimated over the past 8 years). Revisions are greater during economically volatile periods: for the previous recession (2002) the benchmarking related forecast standard error was 107,000 workers per month.
The annual benchmarking revision process creates a dataset which we don't have access to but whose future value we must predict. It would be possible to forecast employment changes if we had access to the revised series before the release of the Employment Situation report; unfortunately revisions are released concurrently with the Employment Situation Summary.
Employment gains are "within two standard errors" of our forecast. When changes are around zero, there's a qualitatively different interpretation of changes in employment. For example, we wouldn't interpret two competing forecasts of -50,000 and +50,000 the same as we would two competing forecasts of +450,000 and +550,000 – even though both sets of forecasts are 100,000 workers apart. When exiting a recession, 'which side of zero' you are on is more important than your 'number', creating an asymmetric penalty response function to a forecast.

The BLS will release the January Employment Situation on February 5th, 2010, at 8:30am ET.

Several internal BLS data elements are revisited in detail during the Annual Benchmark Revisions: Read more »

UI Claims Rise by 11,000 as Employers Skip Normal January Hiring Spree; Next Week Critical

By Charles Thibault on January 15, 2010 in Unemployment Insurance Claims.

New Unemployment Insurance Claims rose by 11,000 in this week's Department of Labor Report. Employers missed their usual January rendez-vous with job seekers – Hiring Demand fell by 7% or 15,000 new online job ads** last week on a seasonally adjusted basis. Employers can make it up next week, however.

December and January employment data is highly volatile in terms of seasonal fluctuations. Job ads usually drop heavily during Christmas-time and then pop back up in January.

What's more, there's something we call "the January bounce" – not only does January Hiring Demand come back from the Holiday slump, it usually jumps above previous December levels. New budgets are usually the source of this "January Bounce" – there's a sort of pent-up demand for labor that's waiting for a new budget cycle to kick in.

During the last week of December, UI Claims benefited from a smaller than expected seasonal dip in Hiring Demand (UI claims improved by 22,000). This week, however, UI Claims suffered from a smaller than expected January rebound in Hiring Demand.

The two tables below show historical December/January seasonal fluctuations, compared to what we've seen so far this year.

BLS reports loss of 85,000 jobs in December, but Gain of 4,000 for November; Construction and Business Services Industries below Growth Trend

By Juli Morris and Charles Thibault on January 8, 2010 in BLS Nonfarm Employment.

Employment fell by 85,000 in December, according to today's preliminary report from the Bureau of Labor Statistics. This loss was worse than consensus estimates: major stock market indices lost 0.25% in the first two hours of trading today but stabilized after that.

The unemployment rate held at 10.0 percent — consensus estimates had expected it to rise to 10.1 percent.

The economy has shed 7.4 million jobs since the start of the recession in December 2007.

Along with the preliminary report for November, the BLS issued its final estimate of 127,000 job losses for October, a worsening of 16,000 from its revised estimate of -111,000. It revised its November preliminary estimate up 15,000 jobs to report gains of 4,000 jobs, which is the one piece of good news from the report. One more revision for November is in the works.

The "culprits" this month were deviations from trends in the Construction industry and in the "Professional and Business Services" industry. Employment losses in the Government sector also contributed to this month's employment declines.

The table below shows how the Construction industry slipped in December, and how employment in the Professional and Business Services industry also fell below trend: Read more »

Good News from UI Claims Report as Hiring Demand Jumps; Forecast of -18,000 for Next Week

By Charles Thibault on December 31, 2009 in Unemployment Insurance Claims.

The Department of Labor released some good news this morning: there were 22,000 fewer new Unemployment Insurance claims compared to the prior week, a 4.8% drop. Our forecast was for a drop of 6,000 so the news is better than we had expected. This improvement in the UI claims report comes as the number of online job ads jumped 8.6% in a single week on a seasonally adjusted basis.

This news also confirms our expectation that the Bureau of Labor Statistics will announce increases in levels of US employment for December.

The correlation between the number of new online job postings (Hiring Demand) and unemployment insurance claims has been -0.72 over the past 4 years. As more new online job ads appear on the internet, more people can find work, and fewer must file for unemployment insurance – hence the <negative> sign on the correlation coefficient. What's more, the correlation improves to -0.80 when looking at the one-week lagged value of Hiring Demand, supporting the hypothesis that Hiring Demand leads UI claims by a week. (Remember that the "best correlation" possible is -1.0 when two variables move in opposite directions).

Given the strength and robustness of this relationship, we can forecast changes to UI Claims data using the number of new online job ads. WANTED Technologies predicts that new UI Claims will fall by 18,000 on a seasonally adjusted basis for the week ending January 2^nd. Read more »

« Older Entries

Newer Entries »