Scribd Logo
Upload

Welcome to Scribd!

  • 86 views

    Testing of Hypothesis For in Case of Simple Linear Regression Line

    Uploaded by

    Asif gill
    1. The document describes steps to test hypotheses for the alpha value in a simple linear regression model. 2. It provides three hypotheses to test: H0: alpha = 32 vs H1: alpha ≠ 32, H0: alpha ≤ 32 vs H1: alpha > 32, and H0: alpha ≥ 32 vs H1: alpha < 32. 3. Calculations are shown to find the test statistic, and decision rules are provided to determine whether to reject the null hypothesis or not for each case based on a significance level of 5%.

    Copyright:

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

    Testing of Hypothesis For in Case of Simple Linear Regression Line

    Uploaded by

    Asif gill
    86 views7 pages
    1. The document describes steps to test hypotheses for the alpha value in a simple linear regression model. 2. It provides three hypotheses to test: H0: alpha = 32 vs H1: alpha ≠ 32, H0: alpha ≤ 32 vs H1: alpha > 32, and H0: alpha ≥ 32 vs H1: alpha < 32. 3. Calculations are shown to find the test statistic, and decision rules are provided to determine whether to reject the null hypothesis or not for each case based on a significance level of 5%.

    Original Title

    alpha-Testing (1)

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    1. The document describes steps to test hypotheses for the alpha value in a simple linear regression model. 2. It provides three hypotheses to test: H0: alpha = 32 vs H1: alpha ≠ 32, H0: alpha ≤ 32 vs H1: alpha > 32, and H0: alpha ≥ 32 vs H1: alpha < 32. 3. Calculations are shown to find the test statistic, and decision rules are provided to determine whether to reject the null hypothesis or not for each case based on a significance level of 5%.

    Copyright:

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

    Testing of Hypothesis For in Case of Simple Linear Regression Line

    Uploaded by

    Asif gill
    1. The document describes steps to test hypotheses for the alpha value in a simple linear regression model. 2. It provides three hypotheses to test: H0: alpha = 32 vs H1: alpha ≠ 32, H0: alpha ≤ 32 vs H1: alpha > 32, and H0: alpha ≥ 32 vs H1: alpha < 32. 3. Calculations are shown to find the test statistic, and decision rules are provided to determine whether to reject the null hypothesis or not for each case based on a significance level of 5%.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 7

    Testing of Hypothesis for 𝛂 in case of simple

    linear regression line.

    Step 1:- Test of Hypothesis for 𝛂


    1. H0 : α = 32 vs H1 : α ≠ 32
    2. H0 : α ≤ 32 vs H1 : α > 32
    3. H0 : α ≥ 32 vs H1 : α < 32

    Step 2:- Level of significance


    𝛼=0.05

    Step 3:- Test Statistic


    𝒂−𝛂
    𝒕 = 𝑺.𝑬(𝒂)

    1 𝑥̅ 2
    where 𝑆. 𝐸(𝑎) = √𝑠𝑎2 = 𝑠𝑦.𝑥 √ + ∑(𝑥−𝑥̅ )2
    𝑛

    2
    ∑(𝑦 − 𝑦̂)2
    𝑠𝑦.𝑥 =
    𝑛−2

    Step 4:- calculations


    Using step four test statistic formulas.
    Step 5:- Decision rule
    Here we decide about rejection of Null hypothesis, on the basis of assumption .

    3. H0 : α ≥ 32 vs H1 : α < 32 2. H0 : α ≤ 32 vs H1 : α > 32 1. H0 : α = 32 vs H1 : α ≠ 32

    When
    When

    When
    |𝑡𝑐𝑎𝑙 |≥ 𝑡𝛼 ,(n-2)
    𝑡𝑐𝑎𝑙 ≤ −𝑡𝛼 ,(n-2) 𝑡𝑐𝑎𝑙 ≥ 𝑡𝛼 ,(n-2) 2
    Find the linear regression equation from the following data:

    X 65 50 55 65 55 70 65 70 55 70 50 55
    Y 85 74 76 90 85 87 94 98 81 91 76 74

    Assuming the normality test the Hypothesis

    1. H0 : α = 32 vs H1 : α ≠ 32

    X Y XY 𝑥2 𝑦2
    65 85 5525 4225 7225
    50 74 3700 2500 5476
    55 76 4180 3025 5776
    65 90 5850 4225 8100
    55 85 4675 3025 7225
    70 87 6090 4900 7569
    65 94 6110 4225 8836
    70 98 6860 4900 9604
    55 81 4455 3025 6561
    70 91 6370 4900 8281
    50 76 3800 2500 5776
    55 74 4070 3025 5476
    725 1011 61685 44475 85905

    12∗61685−725∗1011
    The value of slope b= = 0.897 , a = 30.056
    12∗44475−(725)2
    Required regression line.
    𝑦̂ = 30.056 + 0.897

    ∑(𝑦 − 𝑦̂)2 = 186.939

    ∑(𝑥 − 𝑥̅ )2 = 672.917
    Step 1:- Test of Hypothesis for 𝜶
    1. H0 : 𝜶 = 32 vs H1 : 𝜶 ≠ 32

    Step 2:- Level of significance


    𝛼=0.05

    Step 3:- Test Statistic


    𝒂−𝛂
    𝒕 = 𝑺.𝑬(𝒂)

    1 𝑥̅ 2
    where 𝑆. 𝐸(𝑎) = √𝑠𝑎2 = 𝑠𝑦.𝑥 √ + ∑(𝑥−𝑥̅ )2
    𝑛

    2
    ∑(𝑦 − 𝑦̂)2
    𝑠𝑦.𝑥 =
    𝑛−2

    Step 4:- calculations

    2
    ∑(𝑦 − 𝑦̂)2 186.939
    𝑠𝑦.𝑥 = = = 18.6393
    𝑛−2 10

    1 (68.42)2
    𝑆. 𝐸(𝑎) = √𝑠𝑎2 = 4.3236√ + = √0.0833 + 6.9567 = 11.47
    12 672.917

    30.056 − 32 −1.944
    𝑡= = = −0.169
    11.47 11.47
    Step 5:- Decision rule

    1. H0 : α = 32 vs α ≠ 32
    When

    𝑡𝑐𝑎𝑙 = −0.169
    |𝑡𝑐𝑎𝑙 |≥ 𝑡𝛼 ,(n-2)
    2 𝑡𝛼 ,(n-2)
    2
    |-0.169|≥ 2.228
    Alpha in present case 0.05
    0.169≥ 2.228

    When condition is not 𝑡0.05 ,(12-2)


    2
    fulfilled.
    = 𝑡0.025 ,(10) =2.228

    Finally conclusion:-

    Do not Reject H0

    The data provide an evidence to conclude


    that alpha is 32 for true population on the
    basis of 5% level of significance.
    Suppose if are interested to test:-
    H0 : α ≤ 32 vs H1 : α > 32

    Step 2:- Level of significance


    𝛼=0.05

    Step 3:- Test Statistic


    𝒂−𝛂
    𝒕𝒄𝒂𝒍 = 𝑺.𝑬(𝒂) = −𝟎. 𝟏𝟔𝟗 calculation done already

    Decision rule:

    H0 : α ≤ 32 vs H1 : α > 32

    When

    -0.169≥ 1.812 𝑡𝑐𝑎𝑙 ≥ 𝑡𝛼 ,(n-2)

    Finally condition not hold true, as 𝑡𝟎.𝟎𝟓 ,(12-2)


    calculated value is “-0.169”
    which is not greater than or equal to = 𝑡0.05 ,(10) =1.812
    tabulated value. So do not reject
    null hypothesis.
    Suppose if are interested to test:-
    H0 : α ≥ 32 vs H1 : α < 32

    Step 2:- Level of significance


    𝛼=0.05

    Step 3:- Test Statistic


    𝒂−𝛂
    𝒕𝒄𝒂𝒍 = 𝑺.𝑬(𝒂) = −𝟎. 𝟏𝟔𝟗 calculation done already

    Decision rule:

    H0 : α ≥ 32 vs H1 : α < 32

    When

    𝑡𝑐𝑎𝑙 ≤ −𝑡𝛼 ,(n-2)


    𝑡𝑐𝑎𝑙 ≤ −𝑡𝛼 ,(n-2)
    -0.169≤ −1.812

    𝑡𝟎.𝟎𝟓 ,(12-2)

    = 𝑡0.05 ,(10) =1.812


    Finally condition not hold true, as
    calculated value is “-0.169” which is
    not less than or equal to tabulated value(-
    1.812). So do not reject null hypothesis.

    You might also like