Добавил:
Опубликованный материал нарушает ваши авторские права? Сообщите нам.
Вуз: Предмет: Файл:
Скачиваний:
9
Добавлен:
19.04.2013
Размер:
389.63 Кб
Скачать

Multiple Regression Analysis Y.1

-----------------------------------------------------------------------------

Dependent variable: Y

-----------------------------------------------------------------------------

Standard T

Parameter Estimate Error Statistic P-Value

-----------------------------------------------------------------------------

K 1,13197 0,120403 9,40153 0,0000

L -19,5968 5,08977 -3,85022 0,0007

time -108,127 17,0596 -6,33818 0,0000

-----------------------------------------------------------------------------

Analysis of Variance

-----------------------------------------------------------------------------

Source Sum of Squares Df Mean Square F-Ratio P-Value

-----------------------------------------------------------------------------

Model 3,80506E8 3 1,26835E8 8592,71 0,0000

Residual 398541,0 27 14760,8

-----------------------------------------------------------------------------

Total 3,80904E8 30

R-squared = 99,8954 percent

R-squared (adjusted for d.f.) = 99,8876 percent

Standard Error of Est. = 121,494

Mean absolute error = 100,802

Durbin-Watson statistic = 0,377205

The StatAdvisor

---------------

The output shows the results of fitting a multiple linear

regression model to describe the relationship between Y and 3

independent variables. The equation of the fitted model is

Y = 1,13197*K - 19,5968*L - 108,127*time

Since the P-value in the ANOVA table is less than 0.01, there is a

statistically significant relationship between the variables at the

99% confidence level.

The R-Squared statistic indicates that the model as fitted

explains 99,8954% of the variability in Y. The adjusted R-squared

statistic, which is more suitable for comparing models with different

numbers of independent variables, is 99,8876%. (Note: since the model

does not contain a constant, you should be careful in interpreting the

R-Squared values. Do not compare these R-Squared values with those of

models which do contain a constant.) The standard error of the

estimate shows the standard deviation of the residuals to be 121,494.

This value can be used to construct prediction limits for new

observations by selecting the Reports option from the text menu. The

mean absolute error (MAE) of 100,802 is the average value of the

residuals. The Durbin-Watson (DW) statistic tests the residuals to

determine if there is any significant correlation based on the order

in which they occur in your data file. Since the DW value is less

than 1.4, there may be some indication of serial correlation. Plot

the residuals versus row order to see if there is any pattern which

can be seen.

In determining whether the model can be simplified, notice that the

highest P-value on the independent variables is 0,0007, belonging to

L. Since the P-value is less than 0.01, the highest order term is

statistically significant at the 99% confidence level. Consequently,

you probably don't want to remove any variables from the model.

Multiple Regression Analysis Y.2

-----------------------------------------------------------------------------

Dependent variable: Y

-----------------------------------------------------------------------------

Standard T

Parameter Estimate Error Statistic P-Value

-----------------------------------------------------------------------------

CONSTANT 1771,93 588,957 3,00859 0,0056

K 0,716101 0,115047 6,2244 0,0000

L -28,5746 13,2824 -2,15131 0,0406

-----------------------------------------------------------------------------

Analysis of Variance

-----------------------------------------------------------------------------

Source Sum of Squares Df Mean Square F-Ratio P-Value

-----------------------------------------------------------------------------

Model 2,36484E7 2 1,18242E7 429,93 0,0000

Residual 742576,0 27 27502,8

-----------------------------------------------------------------------------

Total (Corr.) 2,4391E7 29

R-squared = 96,9555 percent

R-squared (adjusted for d.f.) = 96,73 percent

Standard Error of Est. = 165,84

Mean absolute error = 129,964

Durbin-Watson statistic = 0,40917

The StatAdvisor

---------------

The output shows the results of fitting a multiple linear

regression model to describe the relationship between Y and 2

Independent variables. The equation of the fitted model is

Y = 1771,93 + 0,716101*K - 28,5746*L

Since the P-value in the ANOVA table is less than 0.01, there is a

statistically significant relationship between the variables at the

99% Confidence level.

The R-Squared statistic indicates that the model as fitted

explains 96,9555% of the variability in Y. The adjusted R-squared

statistic, which is more suitable for comparing models with different

numbers of independent variables, is 96,73%. The standard error of

the estimate shows the standard deviation of the residuals to be

165,84. This value can be used to construct prediction limits for new

observations by selecting the Reports option from the text menu. The

mean absolute error (MAE) of 129,964 is the average value of the

residuals. The Durbin-Watson (DW) statistic tests the residuals to

determine if there is any significant correlation based on the order

in which they occur in your data file. Since the DW value is less

than 1.4, there may be some indication of serial correlation. Plot

the residuals versus row order to see if there is any pattern which

can be seen.

In determining whether the model can be simplified, notice that the

highest P-value on the independent variables is 0,0406, belonging to

L. Since the P-value is less than 0.05, that term is statistically

significant at the 95% confidence level. Consequently, you probably

don't want to remove any variables from the model.

Multiple Regression Analysis Y.3

-----------------------------------------------------------------------------

Dependent variable: Y

-----------------------------------------------------------------------------

Standard T

Parameter Estimate Error Statistic P-Value

-----------------------------------------------------------------------------

K 0,387031 0,0404787 9,56135 0,0000

L 10,7536 2,672 4,02457 0,0004

-----------------------------------------------------------------------------

Analysis of Variance

-----------------------------------------------------------------------------

Source Sum of Squares Df Mean Square F-Ratio P-Value

-----------------------------------------------------------------------------

Model 3,79913E8 2 1,89956E8 5364,27 0,0000

Residual 991520,0 28 35411,4

-----------------------------------------------------------------------------

Total 3,80904E8 30

R-squared = 99,7397 percent

R-squared (adjusted for d.f.) = 99,7304 percent

Standard Error of Est. = 188,179

Mean absolute error = 142,529

Durbin-Watson statistic = 0,628631

The StatAdvisor

---------------

The output shows the results of fitting a multiple linear

regression model to describe the relationship between Y and 2

Independent variables. The equation of the fitted model is

Y = 0,387031*K + 10,7536*L

Since the P-value in the ANOVA table is less than 0.01, there is a

statistically significant relationship between the variables at the

Соседние файлы в папке CourseWork