Business Forecasting

MSE formula

(Sum Of (Actual-Forecast))^2/number of periods

MAD formula

(Sum Of[Actual-Forecast])/number of periods

MPE formula

(Sum of (Actual-Forecast)/Actual)/number of periods

MAPE formula

(Sum of ([Actual-Forecast]/Actual))/number of periods

The analyst feels that the size of magnitude of the forecast variable is important evaluation the accuracy of the forecast

MAPE

The analyst needs to determine weather a forecasting method is biased.

MPE

MAD(Mean Absolute Deviation)

Mean Absolute Deviation - Measures forecast accuracy by averaging the magnitudes of the Forecast errors - average size of "miss" regardless of direction

10 mean (hs$UNRATE)

gives mean

n= nrows(hs)

gives number of rows on the right

9: summaary (hs [,2]

gives y value min 1st qrt median mean 3rd Q Max

m=sum (hs$UNRATE)/n

mean is put to the right

MSE (mean squared error)

- error/residual is squared, then summed and divided - penalizes large forecasting errors meaning moderate errors preferred over usually small areas and few large errors - weights errors according to their squared values - the average of squared forecast errors

MAPE (mean absolute percent error)

- in terms of percentages - can't be calculated if any zero in Yt - useful when the error relative to the respective size of the time series value is important in evaluating the accuracy of the forecast. - useful when Yt values are large - no units of measurement/used to compare accuracy

RMSE (root mean squared error)

-penalizes large errors but same units as the series so its easily interpreted

attach (dataframe)

Econ[,5]

If a 95% confidence interval on µ was from 50.5 to 60.6, we would reject the null hypothesis that µ = 60 at the 0.05 level of significance.

False

If the test statistic falls in the rejection region, the null hypothesis has been proven to be true.

False

The degrees of freedom for the t test do not necessarily depend on the sample size used in computing the mean.

False

The standard normal distribution has a population mean µ of zero and a population variance ơ2 = 1.96.

False

A normal distribution is characterized by its mean and its degrees of freedom.

False A normal distribution is characterized by its mean and variance.

If the null hypothesis is rejected by a one-tailed hypothesis test, then it will also be rejected by a two-tailed test.

False For example, in a two-tailed test the null is rejected at the 5% level if the t-statistic is less than -1.96 or greater than 1.96. For a one tailed test that the mean is less than some value, the null is rejected if the t-statistic is less than -1.64

The t distribution is used as the sampling distribution of the mean if the sample is small and the population variance is known.

False It is used as the sampling distribution of the mean when the population variance is unknown.

The mean of the t distribution is affected by the degrees of freedom.

False The mean of the t distribution is zero. It's shape, but not its mean is affected by the degrees of freedom.

MAPE takes into consideration the magnitude of the values be forecasted

False, MAD does

The Analyst needs to penalize large forecasting errors

RMSE

5: hs<- read_excel("UNRATE.xlsx)

Reads Excel file

4: Setwd("C:/Forecasting")

Reads directory for C:/ file and Forecasting folder

6: Library(ggplot2)

Reads plots

RMSE formula

Square root (Sum Of (Actual-Forecast))^2/number of periods

If Y is normally distributed with a mean of 40 and a population variance of 25, thenPr(30 ≤ Y ≤ 55) is about 97.6%.

True

If a null hypothesis is rejected at the 0.01 level of significance, it will also be rejected at the 0.05 level of significance.

True

If we decrease the confidence level for a fixed estimated standard error, we decrease the width of the confidence interval.

True

In a hypothesis test, the p value is 0.043. This means that the null hypothesis would be rejected at the 5% level.

True

MPE is used to determine if a model is systematically predicting too low or high

True

MSE and RMSE penalize large errors

True

The advantage of the MAD method is that it relates the size of the error to the actual observation

True

The t distribution is more dispersed than the normal distribution.

True

When the test statistic is t and the number of degrees of freedom is > 30, the t distribution is close to that of Z (the standard normal distribution).

True

1: ##

always you to comment

MPE (Mean Percent Error)

determines whether a forecasting is biased (consistently low or high) - unbiased and produces number close to 0 -large neg.= consistently over -large pos.=consistently under - can have negative numbers

7: plot (hs[,1:2],ylab="unemployment"

plots graph ylab labels y coor.

3: Library(readxl)

reads excel