Scribd Logo
Upload

Welcome to Scribd!

  • 21 views

    PS Quiz1 Sol

    Uploaded by

    Sri Ram
    The document describes a study examining the effect of different coating types (A, B, C) on the conductivity of television picture tubes. It presents conductivity data and fits a linear model to test if there are significant differences in conductivity between the coating types. An ANOVA finds a significant effect of coating type on conductivity (F=12.3574, p<0.05). The document concludes there is a significant difference in conductivity due to the different coating types, but notes the conclusion comes with some uncertainty.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOC, PDF, TXT or read online from Scribd

    PS Quiz1 Sol

    Uploaded by

    Sri Ram
    21 views3 pages
    The document describes a study examining the effect of different coating types (A, B, C) on the conductivity of television picture tubes. It presents conductivity data and fits a linear model to test if there are significant differences in conductivity between the coating types. An ANOVA finds a significant effect of coating type on conductivity (F=12.3574, p<0.05). The document concludes there is a significant difference in conductivity due to the different coating types, but notes the conclusion comes with some uncertainty.

    Original Description:

    dSD

    Original Title

    PS Quiz1 Sol.doc

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    DOC, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes a study examining the effect of different coating types (A, B, C) on the conductivity of television picture tubes. It presents conductivity data and fits a linear model to test if there are significant differences in conductivity between the coating types. An ANOVA finds a significant effect of coating type on conductivity (F=12.3574, p<0.05). The document concludes there is a significant difference in conductivity due to the different coating types, but notes the conclusion comes with some uncertainty.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOC, PDF, TXT or read online from Scribd
    Download as doc, pdf, or txt
    21 views3 pages

    PS Quiz1 Sol

    Uploaded by

    Sri Ram
    The document describes a study examining the effect of different coating types (A, B, C) on the conductivity of television picture tubes. It presents conductivity data and fits a linear model to test if there are significant differences in conductivity between the coating types. An ANOVA finds a significant effect of coating type on conductivity (F=12.3574, p<0.05). The document concludes there is a significant difference in conductivity due to the different coating types, but notes the conclusion comes with some uncertainty.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOC, PDF, TXT or read online from Scribd
    Download as doc, pdf, or txt
    You are on page 1of 3

    PS Quiz-1 Solutions Q1 A manufacturer of television sets is concerned with the effect on tube conductivity of three different types of coating

    for colour picture tubes. The following are the conductivity data for the three coating types. Coating Type A B C (i) (ii) 143 152 134 Conductivity 141 149 127 150 143 132 146 137 129

    Write down a model with all its assumptions taking into account the effect of coating type. Test whether there is a significant difference in conductivity because of coating types. Write down your conclusion and attach with it a measure of uncertainty?

    ANS. (i) Model: Xij = i + eij where eij are error term and i = 1, 2, 3 k, j = 1, 2, 3ni Assumptions: a) The response variable is normally distributed b) The variance of the response variable is same for all populations c) The observations must be independent. (ii) H0: A = B = C against H1: Not all population means are equal.

    We have x A = 145 , x B = 145.25 , x C = 130.5 , nT = 12 , k = 3 x=

    x
    j= A

    =
    C

    420 .75 = 140.25 3


    j

    MSTR =

    n
    j= A C

    ( x x)
    j

    k 1
    j

    = 2( 142.625 ) = 285.25 = 207.75 = 23.0833 9

    MSE =

    ( n
    j= A

    1 )s 2 j

    nT k

    F ratio =

    MSTR 285.25 = = 12.3574 MSE 23.0833


    ANOVA table

    Source Treatment Error Total

    SS 570.5 207.75 778.25

    DF MSS 2 258.25 9 23.0833 11

    F-ratio 12.3574

    For = 0.05 and F2, 9 (0.05) = 4.26. Since F > F2, 9 (0.05), we reject our null hypothesis. Q2. A plant distils liquid air to produce oxygen, nitrogen and argon. The percentage of impurity in the oxygen is assumed to be linearly related to the amount of impurities in the air measured by pollution count in ppm (parts per million).

    Purity 93.4 92.4 91.7 94.0 93.6 92.9 91.3

    Pollution count(ppm) 1.10 1.36 1.59 1.08 1.21 1.22 1.81 (1) Write down the linear regression model for impurity on pollution count. State the model assumptions explicitly. (2) Write down the normal equations. Slove these to find the estimates of the model parameters.

    ANS (a) Let Y: Pollution count (PPM) X: amount of purity in the oxygen Model: Y = 0 + 1X + , where 0 and 1 are the parameters involved in the regression and is the error term. Assumptions: a) The error term is a random variable with E() = 0 b) The error term has constant variance , say 2 c) The values of are independent d) The error term is normally distributed i.e, ~ N (0, 2)

    The normal equations are given below:

    Solving the above, we get the values of the estimates as


    b1 =

    y = nb + b x xy = b x + b x
    0 1 0 1

    ( x x )( y y ) = 0.2576 and b ( x x )
    2

    = y b1 x = 25.2345

    (b) Let Y: Impurity (100-P) X: PPM b1 = 3.5441 and b0 = 2.4988 (c) Let Y: Purity X: PPM b1 = -3.5441 and b0 = 97 .5012 (d) Let Y: PPM X: Impurity b1 = 0 .2576 and b0 = -0 .5273

    You might also like