I think you guys are using the T-stat from the regression output for your confidence interval.  I believe you should use the T-value.  You can find the T-value by using the "TINV" distribution in Excel, with the probability required for the confidence interval (ex 1-.95 and proper degrees of freedom.  Using this gives the same confidence interval as the regression output.

Is the calculation for the 95% confidence interval given in the homeowork suppose to be equal to the confidence interval that comes from running the regression in Excel?  Mine do not equal each other.  Thanks.

I need a quick refresher on the confidence intervals with the t-test. I ran the regression tool in excel and got the slope variable to be .121. I notice the tool also spits out a 95% confidence interval - but it doesn't seem to match what I am doing for the t-test interval (based on the instructions in the hw).

Is my interval correct? .121+/- 4.9228*.02457

All of these inputs came from the excel tool - am i supposed to be calculating anything on my own? Thanks in advance for the help.

Write the regression equation as Yt = A + B × Yt-1. Excel gives you indicated parameters and t-values.

The indicated φ of this regression is close to 0.5, and we would not reject a null hypothesis that φ = 50%. Use the Excel regression add-in to compute the exact φ. The homework shows that you can use the Excel add-in.

You can use any statiscal package, such as SAS or R. They give the same values for the parameter.]

A.     Estimate the parameter ö by regression analysis.

B.     What are 95% confidence intervals for the value of ö?

C.    You initially believed that ö is 50%. Should you reject this assumption?

The time series course does not teach regression analysis. You are assumed to know how to run a regression analysis, and you must run regressions for the student project.

Use the Excel regression add-in. The 95% confidence interval is the estimated â ± the t-value × the standard error of â. The t-value depends on the number of observations. Excel has a built-in function giving the t-value for a sample of N observations.