Tag: Forecast

Forecast Accuracy for the CU Colorado Economic Outlook

horvath Leave a comment

In early December the Colorado Business Economic Outlook Forum (CBEO) will be held in Denver for the 46th consecutive year. The event, sponsored by the Leeds School of Business and BBVA Compass is a forecast of state employment based on the expert opinions of estimating groups for each of the NAICS sectors. Each year, one of the most common questions about the event is, “How accurate are the numbers?”

Reasons for Analysis

In the fall of 2008, I presented a simplistic analysis of the accuracy of the CBEO at the annual AUBER conference (this blog post updates that presentation to include the period 1972 to 2010). The original presentation was motivated by curiosity from estimating group members who wanted to know how accurate their forecasts were.

Questions were also raised from an academic perspective.
• Which is more accurate, a forecast calculated by an econometric model or one determined by committees, based on expert opinion?
• Does financial sponsorship of a forecast by a publicly traded financial institution increase the chance of bias in the forecast?
• An academic paper by Owen Lamont (2001) asked, “Does an experienced research team, with a wealth of knowledge, produce a more accurate forecast or does the added knowledge result in an “arrogance” which may reduce the accuracy of the forecast?

While this simplistic analysis provides insight into some aspects of the forecast accuracy, additional research is necessary to address these issues.

Jobs Gained or Lost

The first test of accuracy measured whether jobs were added or lost (+ or -).

Because an employment forecast is intrinsically a growth forecast, its real value occurs if it can identify the years when jobs are lost.

Colorado employment recorded increases in 34 of 39 years.
• The CBEO accurately predicted growth for all 34 years; however, it inaccurately forecasted growth for three years when jobs were lost.
• Said differently, jobs were lost in five years. The CBEO accurately forecasted 2 of the 5 years, or 40%, when job were lost.

Turns (The key is to accurately predict them)

A second test for measuring the accuracy of the CBEO is to evaluate its ability to recognize turns. A turn is defined by a change in the slope or direction of the trend line (upward or downward). For example, it may change directions from positive to zero or negative.

• There were 17 actual turns in 37 years. During those 17 years, the forecast accurately projected turns 12 of 17 times (12 correct turns, 5 incorrect turns). These errors occurred in 1979, 1987, 1990, 1995, and 1998.
The forecast projected 6 turns during the remaining 20 years when turns did not occur (0 correct turns, 6 incorrect turns). These errors occurred in 1973, 1988, 1989, 1993, 1999, and 2009.

• The CBEO accurately forecasted turns 52% of the time – 12 correct/11 incorrect.

This analysis illustrates the difficulty in preparing an employment forecast. There are clearly challenges in accurately predicting turns, as well as the magnitude of each of the turns. This has been demonstrated by most economists in their projections during the Lost Decade. In the case of the CBEO, its value derives more from the discussions associated with projections for each of the sectors, than the projected changes in total employment.

©Copyright 2011 by CBER.

CSU Forecast – Job Growth Less Than One Percent

horvath Leave a comment

On November 16, the Colorado State University ‘s Economics Department held its Colorado Employment Outlook for 2011. This event featured employment forecasts for various regions throughout Colorado as well as an overall forecast for the state.

Like many other forecasting groups, the CSU team accurately predicted the downturn; however, they did not project the full magnitude of the recession. The state forecast stated that employment growth would be less than 1% in 2011, or about 19,000 workers. The Denver metro area will record positive job growth, although the Boulder area will show weaknesses based on their high concentration of manufacturing and high tech. Mixed results are on the horizon for the state’s resort counties and rural parts of the state.

The forecast team worked with the staffs of the Denver Branch of the Kansas City Federal Reserve  as well as the Colorado Office of  Labor Market Information , the state agency that prepares labor and employment data for the Bureau of Labor Statistics .

For additional information contact Dr. Martin Shields or Dr. Harvey Cutler.

©Copyright 2011 by CBER.

Job Losses Expected in 2011 – State Demography Office

horvath Leave a comment

The 2010 Annual State Demography Meeting kicked off on a somber note, when staff economist David Keyser;  announced that the state’s recovery from the Great Recession will be painfully slow.

Some of the key points from Keyser’s review of the past year (2010) were:
• Job gains occurred in health care, government, and education.
• Ongoing losses in manufacturing continue to hinder the recovery because they have a high multiplier effect.
• Low wage jobs were hit harder.
• Access to credit provided a challenge for many companies.
• Small businesses saw significant setbacks.
• Rural counties that relied on oil and gas or tourism (such as the Western Slope) suffered greater losses, while agriculture-based economies were more stable.
• The loss of basic jobs, such as manufacturing, will have a long-term effect on the state because these jobs are likely to be relocated elsewhere.
• On the other hand, the loss of non-basic jobs, such as retail, food and beverage, or personal services will return in the same location.
• Colorado will remain a popular place to live and work and net migration will remain positive, but slightly below previous years.

Looking ahead, key points from Keyser’s presentation for 2011 were:
• Non-farm wage and salary employment will decline slightly and a best case scenario is that it will be flat. Wage and salary job losses should not exceed 22,000 (1%).
• Agriculture and small businesses are likely to post a slight increase, offsetting declines in wage and salary employment.
• Construction won’t come back in the immediate future.
• Health care will continue to add jobs.
• Colorado will continue to be closely tied to the US economy.
• Many of the effects of the 2007 recession could be permanent.

Keyser’s forecast for 2011 is slightly lower than what cber.co projected in late October, but the basic analysis of the current state of the economy is similar.

©Copyright 2011 by CBER.

Colorado to add 15,000 Jobs in 2011

horvath Leave a comment

In late October, the Bureau of Labor Statistics released its first estimate of September employment data for Colorado. Based on that report, the state is on track to lose 35,000 jobs in 2010. (Preliminary 2010 data will be released in March 2011.)

Recently, many of the nation’s top economists have revised their 2011 Real GDP forecasts downward, in the range of 1.9% to 2.6%. Output growth of 2.4% points to a miniscule job increase of 0.7%, or 15,000 jobs, for Colorado next year.

This Colorado economic forecast  was shared with state business and government leaders this past week. A summary of the responses from these individuals follows:

  • The country should be concerned about the effect the Lost Decade will have on its competitiveness.
  • The recent announcement that Q3 Real GDP was 2.0% is better than expected; however, if output growth continues at this level next year, Colorado cannot expect meaningful job growth.
  • The lack of overall growth in the economy is reflected in the real estate market.
  • Colorado typically lags the nation in entering and exiting economic downturns. Colorado’s exit from the Great Recession seems to be slower than that of the nation – despite lower unemployment.
  • For some time, I’ve been concerned about unrealistic expectations for growth in consumer demand, given the deleveraging overhang and unemployment.
  • Colorado’s major wealth creation industry – mineral extraction – continues to be hobbled by policy, yet Wyoming is projecting a healthy recovery in the months ahead- thanks to their policies regarding extractive minerals.
  • Southwest Colorado is no better than the Front Range.
  • The word that best describes the Western Slope economy is “lagging.” We’re used to growing faster than the state; recently we were losing jobs faster, although those declines have slowed.
  • There is a reasonable chance that Colorado will experience back-to-back-to-back job losses.
  • We are seeing more inquiries, which hopefully will bode well for our local economy.
  • We are seeing more inquiries, but they are not translating into sales – yet.
  • Efforts are being made to manipulate the housing and equity markets to create the illusion that the economy is better than it really is. The hope is that if consumers see their net worth rise, then they will start spending again. This makeshift effort does not eliminate the fundamental problems.

While these comments are not intended to be a representative sample of all Coloradans, they support the belief that the prospects for a solid recovery are not in the immediate future.

 

©Copyright 2011 by CBER.

Real GDP and Colorado Employment

horvath Leave a comment

Over time, there has been a strong correlation between the values of Real Gross Domestic Product and Colorado employment. Logically, this makes sense because both are growth variables that follow similar paths.

Employment data for Colorado was first recorded in 1939. In 4 of the decades since, (50s, 60s, 70s, 90s) there has been a strong correlation between changes in the U.S. economy and Colorado employment. In three of the decades, the tie between the two variables was weaker. This can be explained by a variety of economic disruptions:
• 1940s – World War II and the post-war effect caused the two variables to be out of sync.
• 1980s – Colorado experienced regional issues including an oil and gas boom and bust, savings and loan crisis, overbuilt housing market, and net out-migration for 5 years.
• 2000s – The primary and secondary effects of two recessions hit Colorado harder than other regions of the country.

Since 1939, Colorado has experienced net job losses 8 times. On 5 of these 8 occasions, the U.S. recorded positive Real GDP growth.

Colorado experienced job losses 4 times during the past 8 years:
2002    42,700 jobs lost.
Real GDP = 1.8%.
2003    31,400 jobs lost.
Real GDP = 2.5%.
2009    106,300 jobs lost.
Real GDP = -2.6%
2010    35,000 jobs lost.
Real GDP = 2.6%.
There was positive expansion in output in 3 of the 4 years that job losses occurred.

Recent forecast updates suggest that the U.S. will experience below potential output growth through 2011. This raises the question, “Has the fragile state economy recovered to the point where it can add jobs in such a volatile economic environment?”

 

©Copyright 2011 by CBER.

NABE Downgrade of Real GDP Bodes Ill for Colorado

horvath Leave a comment

The National Association of Business Economists (NABE) released its fall consensus forecast in early October. NABE revised its outlook for output from 3.2% (in May) to 2.6% based on lower than anticipated economic activity during the summer months.

In addition, NABE indicated that modest growth in consumer spending is on tap through 2011. Consumers will remain cautious as a result of continued high unemployment and weak gains in employment. As well, minimal growth is expected in household net worth, i.e. small gains are expected in equity portfolios and home prices

Finally, NABE opined that the downward revision in the forecast reflects “a greater appreciation of the importance of stimulus policies in countering forces holding down the economy’s performance.”

While it is not surprising that NABE lowered its expectations for expansion of the economy, the amount of the decrease is reason for concern. In simplistic terms, the May forecast suggested that the U.S. would see above potential growth this year while the October forecast now says that growth will be well below potential.

Were the NABE panelists overly anxious to see a recovery or did the positive impact of the stimulus package on Q1 Real GDP cause them to be overly optimistic in their May outlook? Clearly panelists missed indicators of the summer slowdown in their May forecast; are there other factors, favorable or unfavorable, that panelists may have missed in their October update?

The revisions in the NABE forecast illustrate the challenges that economists and business researchers face in evaluating and forecasting the performance of the economy. Many of the econometric models that have worked well during periods of growth have proven to have limitations caused by the volatility of the economy over the past decade. This is not intended as criticism, but rather an illustration of the challenge our public and private sector leaders face when they are forced to make decisions without perfect information.

While Colorado is a great place to conduct business, the underlying message from the NABE forecast bodes ill for Coloradans. Lackluster growth at the national level translates into an extended recovery for the Colorado economy, i.e. there will be limited job growth on the horizon.

©Copyright 2011 by CBER.