Nothing Special   »   [go: up one dir, main page]
Scribd Logo
Upload

Welcome to Scribd!

  • 69 views

    RMD-Assignment-2 - Group-4 PDF

    Uploaded by

    Sanyam Agarwal
    - A regression model was developed using monthly income (X1) and family size (X2) to predict amount of money spent (Y) by customers. - Two models were built: Model 1 used only income as a predictor, while Model 2 used both income and family size as predictors. - Model 2 had a higher adjusted R-squared value, indicating it could predict 58.4% of variation in spending, compared to 56% for Model 1. Both income and family size were significant predictors.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    RMD-Assignment-2 - Group-4 PDF

    Uploaded by

    Sanyam Agarwal
    69 views7 pages
    - A regression model was developed using monthly income (X1) and family size (X2) to predict amount of money spent (Y) by customers. - Two models were built: Model 1 used only income as a predictor, while Model 2 used both income and family size as predictors. - Model 2 had a higher adjusted R-squared value, indicating it could predict 58.4% of variation in spending, compared to 56% for Model 1. Both income and family size were significant predictors.

    Original Description:

    Original Title

    RMD-Assignment-2 - Group-4.pdf

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    - A regression model was developed using monthly income (X1) and family size (X2) to predict amount of money spent (Y) by customers. - Two models were built: Model 1 used only income as a predictor, while Model 2 used both income and family size as predictors. - Model 2 had a higher adjusted R-squared value, indicating it could predict 58.4% of variation in spending, compared to 56% for Model 1. Both income and family size were significant predictors.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    69 views7 pages

    RMD-Assignment-2 - Group-4 PDF

    Uploaded by

    Sanyam Agarwal
    - A regression model was developed using monthly income (X1) and family size (X2) to predict amount of money spent (Y) by customers. - Two models were built: Model 1 used only income as a predictor, while Model 2 used both income and family size as predictors. - Model 2 had a higher adjusted R-squared value, indicating it could predict 58.4% of variation in spending, compared to 56% for Model 1. Both income and family size were significant predictors.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 7

    6/29/2020 Assignment 2

    RMD

    Submitted By – Group 4
    1 190301001 Abhinava Sarkar
    2 190301003 Aniket Jain
    3 190301018 Sanyam Agarwal
    4 190301015 Praveen Kumar Goldar
    5 190301019 Syamantak Sen
    6 190301004 Ankita
    1. Data on amount of money spent (Y) by customers at an e-commerce portal, monthly
    income (X1) and family size (X2) is collected for 200 customers (File attached).

    • Comment on the suitability of developing a regression model based on scatter


    plot and correlation matrix.

    • We can identify here that there is high correlation between amount spent and
    income
    • There is little correlation between amount spent and family size, and Income and
    family size.
    • Therefore, we can create a regression model based on the below plots.

    • Build two regression model at one go with SPSS a) only with monthly income b)
    both monthly income and family size together as independent variables. The
    dependent variable in both cases is amount of money spent
    • Model 1 - only with monthly income
    • Model 2- both monthly income and family size together as independent
    variables
    • Based on the multiple linear regression model
    a) describe whether the overall regression model is significant
    NULL HYPOTHESIS (H0) – There is no impact of income and family size on
    Amount spent.
    1) Significance level between amount spent and income is 0.000 hence its
    significant.
    2) Significance level between amount spent and family size is 0.025 hence its
    significant.
    3) Significance level between income and family size is 0.375 hence there is very
    low correlation between the independent variables.
    Also, Dependent variable (Amount spent) has a correlation with income (As the
    value is 0.748 “more than 0.5) but not with family size as the value -0.138 which is
    less than 0.5.
    Overall correlation is between medium to strong, for Amount spent and income.
    Therefore, we can reject the Null Hypothesis (H0).
    b) whether the independent variables are significant and which one has more
    impact
    The significant value between Amount spent and income is 0.000 and between
    amount spent and family size is 0.025. Both the independent variable has significant
    value less than 0.05. Hence both are significant
    As the value between Amount spent and income is 0.000 it has more impact than
    between amount spent and family size is 0.025
    c) the overall predictive capability of the model
    Model 1
    The adjusted R Square value of model 1 is 0.560 which means that it can predict 56 %
    of the variation of the dependent variable
    Model 2
    The adjusted R Square value of model 2 is 0.584 which means that it can predict 58.4
    % of the variation of the dependent variable.

    Model 2 is slightly better than model1 in predicting the variation of the dependent
    variable.

    d) write the regression equation.


    Y (Amount Spent) = b0(Intercept “Constant”) + b1X1(Income) + b2X2 (Family Size) +
    e (Prediction error)
    (b1 = change in income,
    b2 = Change in family Size)

    Coefficientsa
    Model Unstandardized Coefficients Standardized t Sig. Collinearity Statistics
    Coefficients
    B Std. Error Beta Tolerance VIF
    1 (Constant) 25.717 84.749 .303 .762
    Income .017 .001 .748 15.872 .000 1.000 1.000
    2 (Constant) 395.571 137.062 2.886 .004
    Income .017 .001 .752 16.358 .000 .999 1.001
    FamilySize -129.415 38.272 -.155 -3.381 .001 .999 1.001
    a. Dependent Variable: AmountSpent
    Model 1
    Amount Spent = 25.717 + 0.017 Income
    Model 2
    Amount Spent = 395.571 + 0.017 Income - 129.415 Family Size
    2. The weight-loss dataset explains the impact of three types of diets in weight loss. Please
    use Anova to find if three types of diet work differently for weight loss and to investigate
    which diet was best for losing weight.

    SOLUTION

    1. Null Hypothesis (H0) (without diets) – The is no significant impact of diet on weightloss.
    2. Hypothesis (H1) – Diet 1 and diet 2 impact on weightloss are similar.
    3. Hypothesis (H2) – Diet 1 and diet 3 impact on weightloss are similar
    4. Hypothesis (H3) – Diet 2 and diet 3 impact on weightloss are similar

    • Form the below Descriptive analysis, it is observed, that the mean of Diet 3 is more than that
    of both diet 1 and diet 2.

    • From the below anova table, it is observed that the overall significance level is 0.003
    which is less than 0.05.
    • Therefore, we will not be rejecting the NULL HYPOTHESIS – H0. Therefore, there is a
    significant impact of diets on weight loss.
    • From the above Post Hoc Tests, it is observed that Diets 1 & 3 and Diets 2 & 3 are significant
    (< 0.05), whereas the comparison between Diets 1 & 2 is insignificant.
    • Therefore, rejects HYPOTHESIS – H2 and H3.
    • Although we will not be able to reject the NULL HYPOTHESIS H1. which means Diets 1 and 2
    impact weight loss similarly.
    • Analyzing, Diet 1 and Diet 3 it is observed that Diet 3 has a higher mean, in Diet 2 and Diet 3,
    again Diet 3 has a higher mean.
    • Therefore, Diet 3 is the best diet for weight loss.

    You might also like