Prediction Using Simple Linear Regression

Prediction Using Simple Linear Regression

We calculate the predicted value of the dependent variable (Y) by inserting the estimated value of the independent variable (X) in the regression equation. The predicted value of the dependent variable (Y) is determined using the formula:

$$\widehat{Y}=\widehat{b_{0}}+\widehat{b_{1}}X$$

Where:

  • \(\widehat{Y}\) = Predicted value of the dependent
  • \(X\) = Estimated value of the independent variable

Example: Calculating the Predicted Value of a Dependent Variable

The estimated linear regression equation for inflation and unemployment rates for a certain country is:

$$\widehat{Y}=0.070953-0.90405X_{i}$$

Calculate the predicted value of the inflation rate if the forecasted value of the unemployment rate is 7.5%.

Solution

The predicted value for the inflation rate is determined as follows:

$$\widehat{Y}=\widehat{b_{0}}+\widehat{b_{1}}X$$

$$\begin{align*}\widehat{Y}&= 0.070953-0.90405\times 7.5\%\\&= 0.3\%\end{align*}$$

Because the estimated regression doesn’t perfectly describe the relationship between the independent and the dependent variables, we need an interval estimate of the forecast to reflect the uncertainty. The estimated variance of the prediction error of Y given X is:

$$s_f^2=s_e^2 1+ \frac1n+\frac{(X_f-X ̅ )^2}{((n-1) s_X^2 )}=s_e^2 1+\frac1n+\frac{(X_f-X ̅ )^2}{∑_{i=1}^n(X_i-X ̅ )^2 )}$$

And the standard error of the forecast is:

$$s_f^2=\sqrt[s_e^2]1+\frac1n+\frac{(X_f-X ̅ )^2}{∑_{i=1}^n(X_i-X ̅ )^2 )}$$

Where:
\(S_e\) = The standard error of the estimate.
\(n\) = The number of observations.
\(X_f\) = The forecasted value of the independent variable.
\(\bar{X}\) = The estimated mean.

From the standard error of the forecast, we can see that:

  • A better fit of the regression model will result in a smaller standard error of estimates, translating to a smaller standard error of the forecast.
  • Large sample size in the regression estimation will result in a smaller standard error of the forecast.
  • The closer the mean of the independent variable (\(\bar{X}\)) is to the forecasted independent variable (\(X_f\)) the smaller the standard error of the forecast.

After we have calculated our standard error of the forecast determining the prediction interval follows. The formula for prediction interval is:

$$(\hat{Y_f} ) ± t_\text{critical for α/\(2S_f\)}$$

Where:
\(t_c\)=Two-tailed critical t-value at the given significance level with n-2 df.
\(s_f\)= The estimated variance of the prediction error.

To develop the prediction interval, we use the following steps:

  1. Predict the value of Y given the forecasted value of X.
  2. Choose a significance level for the prediction interval.
  3. Determine the critical value for the prediction interval based on the level of significance and degrees of freedom.
  4. Compute the standard error of the forecast.
  5. Compute the percent prediction interval for the prediction.

Question

Given \(Y=-159+0.26X\)

Where:

  • Y = Quantity supplied
  • X = Price

The predicted value of the quantity supplied when the price equals 1,200 is closest to:

  1. 153
  2. 155
  3. 471

Solution (A)

The correct answer is A.

$$Y=-159+0.26\times 1,200=153$$

Notice that \(|t|>t_{c}\) (i.e \(21.67>3.18\)).

Thus, the null hypothesis can be rejected. The conclusion is that the estimated slope coefficient is statistically different from zero.

The estimated value of the intercept \(\widehat{b_{}}=0.0710\).

The estimated value of the standard error for  \(\widehat{b_{0}}, (\widehat{S_{b_{0}}})= 0.0094\).

The 95% confidence interval is then calculated as:

\(\text{CI}=\widehat{b_{0}}-t_{c}\widehat{S_{b_{0}}}\) to \(\widehat{b_{0}}-t_{c}\widehat{S_{b_{0}}}\)

\(\text{CI}=0.0710±2.306\times0.0094=0.0493\) to \(0.0927\)

Since 0 lies outside this confidence interval, we can reject the null hypothesis and conclude that the intercept is significantly different from zero.

Solution (B)

We are testing

$$H_0: b_1=1$$

v.s

$$H_a:b_1≠1$$

The critical value for testing this hypothesis is the same as the critical value for testing the first hypothesis. Thus, \(t_{c}=2.306\).

The estimated value of the parameter \(\widehat{b_{1}}=-0.9041\).

The estimated value of the standard error for \(\widehat{b_{1}},(\widehat{S_{b_{1}}})\) is 0.1755.

The 95% CI for any particular hypothesized value of \(b_{1}\) is determined as follows:

$$\text{CI}=\widehat{b_{1}}±t_{c}\widehat{S_{b_{1}}}$$

$$\begin{align*}\text{CI}&= -0.9041±2.306\times0.1755\\&=-1.3088   \text{to} -0.4994\end{align*}$$

Notice that the hypothesized value of \(b_1=1\) falls outside the above range. Thus, we eject the null hypothesis at the 5% significance level.

Reading 0: Introduction to Linear Regression

LOS 0 (g) Calculate and interpret the predicted value for the dependent variable, and a prediction interval for it, given an estimated linear regression model and a value for the independent variable

Shop CFA® Exam Prep

Offered by AnalystPrep

Featured Shop FRM® Exam Prep Learn with Us

    Subscribe to our newsletter and keep up with the latest and greatest tips for success
    Shop Actuarial Exams Prep Shop Graduate Admission Exam Prep


    Daniel Glyn
    Daniel Glyn
    2021-03-24
    I have finished my FRM1 thanks to AnalystPrep. And now using AnalystPrep for my FRM2 preparation. Professor Forjan is brilliant. He gives such good explanations and analogies. And more than anything makes learning fun. A big thank you to Analystprep and Professor Forjan. 5 stars all the way!
    michael walshe
    michael walshe
    2021-03-18
    Professor James' videos are excellent for understanding the underlying theories behind financial engineering / financial analysis. The AnalystPrep videos were better than any of the others that I searched through on YouTube for providing a clear explanation of some concepts, such as Portfolio theory, CAPM, and Arbitrage Pricing theory. Watching these cleared up many of the unclarities I had in my head. Highly recommended.
    Nyka Smith
    Nyka Smith
    2021-02-18
    Every concept is very well explained by Nilay Arun. kudos to you man!
    Badr Moubile
    Badr Moubile
    2021-02-13
    Very helpfull!
    Agustin Olcese
    Agustin Olcese
    2021-01-27
    Excellent explantions, very clear!
    Jaak Jay
    Jaak Jay
    2021-01-14
    Awesome content, kudos to Prof.James Frojan
    sindhushree reddy
    sindhushree reddy
    2021-01-07
    Crisp and short ppt of Frm chapters and great explanation with examples.