You are on page 1of 3

Assignment-Stat-701 (28-09-2022)-Mphil-Computer Science

Name : _______________________. Regression #_____________________ Major.__________________

The data below represent investments, in $1000s, in the development of new software by some computer company
over an 10-year period

Year 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
Investment 17 23 31 29 33 39 40 41 44 47

Q #1 Write the regression models in this case and write the appropriate formulas for the calculation of parameters
of the model.
Let: x → Year
y → Investment
Regression Model:
𝑦𝑖 = 𝛼 + 𝛽𝑥𝑖 + 𝜀𝑖 … (1)

y is the dependent variable


x is the independent variable
α is the y intercept
β is the slope and
𝜀𝑖 is the random error.
𝛼 = 𝑦̅ − 𝛽𝑥̅ … (2)

𝛽 = ∑𝑖( 𝑥𝑖 − 𝑥̅ )( 𝑦𝑖 − 𝑦̅ )/ ∑𝑖( 𝑥𝑖 − 𝑥̅ )2 … (3)

Q #2 Write the interpretation of suggested regression model.


Using R software, we will find the values of our regression line parameters.
𝛼 = −6152.600 and 𝛽 = 3.067
Then the estimated regression line is:
𝑦̂𝑖 = −6152.600 + 3.067 𝑥𝑖

𝛼 = −6152.600 , represents the mean value of the response variable when all of the independent
variables in the model are equal to zero.

𝛽 = 3.067 , represents the estimated increase in y per unit increase in x.

Q #3 Construct 95 % confidence interval for both intercept and slope of the line in each suggested model and
interpret the results.
We are 95% confident that our estimated value of 𝛼 = −6152.600 will lie between
(-7387.933387, -4917.266613).

We are 95% confident that our estimated value of 𝛽 = 3.067 will lie between (2.454358,3.678975).
Q #4 Test the significance of overall regression model and check the accuracy of your model.
The F-Test of overall significance in regression is a test of whether or not your linear regression model
provides a better fit to a dataset than a model with no predictor variables. Linear regression needs the
relationship between the independent and dependent variables to be linear.

F-statistic: 133.4 on 1 and 8 DF, p-value: 2.869e-06

Since the p-value < α (0.05), we reject the H0 and conclude that our model provides a better fit than the
intercept-only model.

Q#5 Report the predictive values and residual values of your model

Predicted-values Residual-values
1 20.60000 -3.6000000
2 23.66667 -0.6666667
3 26.73333 4.2666667
4 29.80000 -0.8000000
5 32.86667 0.1333333
6 35.93333 3.0666667
7 39.00000 1.0000000
8 42.06667 -1.0666667
9 45.13333 -1.1333333
10 48.20000 -1.2000000

Q#6 Draw the scatter plot of all suggested model by displaying regression equations and 𝑅 2 on plot.
Q#7 Predict the investment of the company for the year 2025 and construct its prediction intervals. (may use
Minitab for the solution of this question)
By putting the value of x = 2025 in the estimated regression line
𝑦̂𝑖 = −6152.600 + 3.067 𝑥𝑖

Then 𝑦̂ = 57.4

And this will be lie between (53.99,60.81)

You might also like