JEFF ALLEN

College of Business

Western Carolina University

Abstract

This paper forecast the unemployment rate for North Carolina for the years 2000 through 2005. This forecast takes advantage of the Phillips Curve relationship between unemployment and inflation. The variables used include unemployment and estimated inflation from 1978 through 1999. North Carolina’s unemployment rate is predicted to rise in the next six years. The initial rise will come in January of 2000, after this rise North Carolina’s unemployment will stay relatively steady, with only slight increases and decreases in the remaining six years of the forecast. The government, the fed, and firms should continue present measures to maintain the low unemployment level. (JEL:E24)

Part 1. Introduction

This paper forecasts North Carolina’s unemployment rate for the years 2000-2005. The explanatory variable is the estimated inflation. Using the Phillips Curve approach, this paper estimates the relationship between inflation and unemployment. The estimate is based on data from the years 1978 through 1999.

When unemployment is low and the demand for labor is high, employers are expected to offer high wages to attract the most highly qualified labor from other employers. However, when unemployment is high and the demand for labor is low, workers are more likely not to offer them selves for less than a prevailing wage rate. As a result, wage rates will decline at a slow pace.

The remainder of this paper is organized as follows: Part 2. presents the data that was used to forecast North Carolina’s unemployment for the years 2000-2005; Part 3. explains the theoretical basis for the approach adopted in forecasting unemployment; Part 4. presents the forecast of unemployment for the years 2000-2005; Part 5. evaluates the importance of the forecast for the economy; and Part 6. discusses conclusions for economic policy.

Part 2. Data

The expected inflation data was found on the St. Louis Federal Reserve Economic Data (FRED) website under the Michigan Survey of Inflation Expectations. Unemployment data was found on the web site of the Bureau of Labor Statistics. North Carolina’s unemployment is Bureau of Labor Statistics variable LAUST37000003. This data is published once a month, but is not seasonally adjusted. Therefore, monthly values are used.

As a result of the non-seasonally adjusted data, the forecast predicts unemployment for each month for the years 2000-2005, for a more accurate forecast.

Part 3. Economic Theory:

Forecasting Unemployment using the Phillips Curve

Monthly unemployment rates are used to project future unemployment for North Carolina for 2000-2005. This forecasts that unemployment is a function of inflation:

u=f(inflation)

The above Phillips Curve relationship is a simple relationship appropriate for forecasting unemployment rates. By lagging the right hand side of the Phillips Curve by six years, it can be used to forecast six years into the future:

u=f(u_t-6,inf_t-6)

A.W. Phillips work suggests that if inflation rises, then as a result, unemployment should decline. This shows that unemployment is a negative function of inflation (Mueller, p.245).

Estimates from the forecasting equation are presented in Part 4.

Part 4. Empirical Results

The forecasting equation was estimated by an ordinary least square regression for the years 2000-2005. The R-squared of the regression is 0.20128. The estimate of the equation is as follows, with inflation and unemployment lagged 6 years in parenthesis:

u_t=4.647105-0.16095(5)+0.182265(2.8)

The data was evaluated with a six-year lag, for the years 1978-1999. The regression had t-statistics for intercept and slope, 5.735355 and –3.77013, respectively.

The sum of the coefficients multiplied by the lagged inflation rate equals the forecasted unemployment rate. To get the forecast for the years 2000-2005 the right hand side variable had to be lagged six years:

u_t=a+b(inf_t-6)

The graph below shows forecasted unemployment for North Carolina for the years 2000-2005.

Graph 1

The table below reports the forecasted unemployment for North Carolina for the years 2000-2005, as

annual data (an average of the twelve month data found in this forecast).

Table 1 Forecast North Carolina Unemployment 2000-2005
*Year*	*Unemployment Rate*
2000	4.49
2001	4.49
2002	4.49
2003	4.58
2004	4.54
2005	4.64

Part 5. Forecast Implications

Forecasting unemployment rates show the welfare of the nations citizens and of our economy. When unemployment is low, then the welfare of the citizens increases. As the citizens’ welfare improves, so does the welfare of our businesses and government. This is a result of more money flowing through the economy. With the government’s welfare increased they are capable of giving back to the public, through actions such as building schools and other such projects, they can boost the economy. Thus completing the circle and making life better for everyone.

Part 6. Policy conclusions

The forecast predicts that unemployment in North Carolina will increase drastically in the next six years. It predicts that the first drastic change will come in January of 2000 and will only change minutely after that for the next six years.

If the forecast is correct, the government needs to be concerned. The government may wish to raise the interest rate in order to bring the unemployment rate back down. However, raising the interest rate could possibly cause businesses problems. They would be less likely to borrow money and thus still damage the economy.

This forecast assumes that there will be no major changes in inflation over the next six years. A major inflation change would make this forecast obsolete.

References

Bureau of Labor Statistics, http://stats.bls.gov/top.html#laus, LAUST37000003

Federal Reserve Bank of St. Louis, Federal Reserve Economic Data (FRED), http://www.stls.frd.org/fred/

Phillips, A.W., “The Relationship Between Unemployment and the Rate of Change of Money Wages in the United Kingdom, 1861-1957,” Economica, 1958, reprinted in Meuller, M.G., ed., Readings in Macroeconomics, New York: Holt, Rinehart and Winston, 1971, pp. 245-256.