Lawrence Klein Project Essays

Lawrence Klein Project Essays Lawrence Klein Project Essay Lawrence Klein Project Essay Model 1 was created to try and explain the cause and effects of the great depression in USA in the 1920s and 1930s. It tries to explain why the economy did so badly at the end of the 1920s then eventually recovered towards the end of the 1930s. Basic Time Plot Analysis We have plotted three important variables to graphically explain what Klein was trying to explain in his model. These three variables are consumption, investment and private wages. Figure 1 shows the consumption levels every year from 1921 to 1943. In 1921 consumption is 39. Consumption rises each year steadily until 1930 where consumption is at 57. 8. Consumption falls in 1931 and rapidly. It falls for a further two years and reaches a level of 45. 6 in 1933. In 1934 the consumption levels start to rise again and do so for the next ten years except for a small dip in 1939. Figure 2 shows the investment levels from 1921-1943. Investment starts at 2. 7 in 1921. Here it falls the next year to -0. 2%, after this in general it rises each year until 1927 where it reaches 5. 6%. In the next six years it falls to -6. 2% in 1933. After 1933 there is a sharp rise in investment every year until 1937 where it flattens at around 2% for two years. From 1939 Investment rises further and in three years it reaches 4. 9%. Figure 3 shows the private wages in the time period. In 1921 private wages are 28. 8. They fall the following year, but increase at a steady pace to reach 41. 3 in 1930. From 1931 to 1934 private wages fall rapidly to 28. 5. Wages start to rise in 1935 and continue to do so except for a small fall in 1939 for the next four years. By 1938 wages have reached 41. This links in with Grangers attempt to explain the great depression. As the figures show investment falls then consumption and private wages fall with a slightly longer lag. From these results one can say that significantly different estimations are obtained using TSLS rather than OLS for consumption. We can conclude also that the model is a good fit with R2 values of 0. 97214 and 0. 982007 for the OLS and TSLS regressions respectively. The signs of the coefficients for ? and W1 are as expected; when profits and private wages rise one would expect consumption to rise too. One would expect ? -1 to have a positive coefficient as in the TSLS regression rather than the negative one found in OLS, and therefore one can say that the TSLS estimates are consistent with expectations. The estimates using OLS and TSLS are almost identical and the signs of the coefficient are consistent with expectations. Near identical R2 values of 0. 980973 and 0. 980972 for OLS and TSLS respectively imply an excellent fit it both cases, and it is not of huge importance which method is used for estimation. Correlogram When we have time series data, where the observations follow a natural ordering through time, there is always a problem that successive errors we be correlated with each other. Serial correlation is present when residuals correlate with their own lagged variables. This violates the standard assumption of regression theory that disturbances are not correlated with other disturbances. This is a problem as OLS is no longer efficient among linear estimators. Standard errors are not correct and are often understated and if there are lagged dependent variables on the right-hand side, OLS estimates are then biased and inconsistent. 1 We can use the Correlogram to find out whether the series is stationary or non-stationary. With a stationary series the autocorrelations gradually die out, indicating that the values further in the past are less correlated with the current value. For non-stationary the autocorrelations do not die out rapidly at all. We have decided to plot correlograms for consumption (figure 4), investment (figure 5) and private wages (figure 6). All three of these graphs show the same thing, the autocorrelation drops fairly soon. It certainly does not stay. From this, one can assume that all three series are stationary. The regression is therefore not necessarily spurious. When non-stationary time series occur, the problem can be that the regression may indicate a significant relationship when actually there isnt one. The correlogram has allowed us to see that the regression is not spurious and so the relationships are reliable. We can tell that there is serial correlation in the model as we have tested that at least some of the AC and PC are greater than zero. The Q-stats are significant the P values are low.