Scribd Logo
Upload

Welcome to Scribd!

  • 41 views

    Analysis of Association

    Uploaded by

    popat vishal
    This document discusses different methods for analyzing the association between attributes. It defines key terms like attribute, positive/negative association, and complete association/disassociation. Several methods are described for determining the nature and degree of association between attributes: the comparison method compares observed and expected frequencies; the proportion method expresses associations as proportions rather than numbers; Yule's coefficient of association provides a quantitative measure between +1 and -1; and Pearson's coefficient of contingency is used when attributes have more than two classes. Examples are provided to illustrate complete association and each of the analysis methods.

    Copyright:

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

    Analysis of Association

    Uploaded by

    popat vishal
    41 views12 pages
    This document discusses different methods for analyzing the association between attributes. It defines key terms like attribute, positive/negative association, and complete association/disassociation. Several methods are described for determining the nature and degree of association between attributes: the comparison method compares observed and expected frequencies; the proportion method expresses associations as proportions rather than numbers; Yule's coefficient of association provides a quantitative measure between +1 and -1; and Pearson's coefficient of contingency is used when attributes have more than two classes. Examples are provided to illustrate complete association and each of the analysis methods.

    Original Description:

    sa

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses different methods for analyzing the association between attributes. It defines key terms like attribute, positive/negative association, and complete association/disassociation. Several methods are described for determining the nature and degree of association between attributes: the comparison method compares observed and expected frequencies; the proportion method expresses associations as proportions rather than numbers; Yule's coefficient of association provides a quantitative measure between +1 and -1; and Pearson's coefficient of contingency is used when attributes have more than two classes. Examples are provided to illustrate complete association and each of the analysis methods.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    41 views12 pages

    Analysis of Association

    Uploaded by

    popat vishal
    This document discusses different methods for analyzing the association between attributes. It defines key terms like attribute, positive/negative association, and complete association/disassociation. Several methods are described for determining the nature and degree of association between attributes: the comparison method compares observed and expected frequencies; the proportion method expresses associations as proportions rather than numbers; Yule's coefficient of association provides a quantitative measure between +1 and -1; and Pearson's coefficient of contingency is used when attributes have more than two classes. Examples are provided to illustrate complete association and each of the analysis methods.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    of 12

    Topic: Analysis Of Association

    Meaning
    The term association is applied to
    attributes and association studies
    the degree of relationship between
    attributes.
    Attribute: An attribute is a quality
    of characteristics, which cannot be
    measured, but identified and
    counted.
    Eg: blindness, literacy, honesty,
    integrity etc.

    Notations
    The english capital letters A, B etc are
    use to denote the presence of various
    attributes.
    The greek letters , etc are use to
    denote the absence of various attributes.
    Positive or negative association.
    The attributes denoted by A, B etc are
    called positive attribute.
    The attributes denoted by , etc are
    called negative attributes.

    Complete association or
    disassociation
    If all As are Bs and all Bs are As than
    there is perfect positive or complete
    association between the two attributes.
    Eg: (A)=(B)
    If none of the As in B or none of the Bs
    in A, then it is said to perfect negative
    or complete disassociation.
    Eg: (AB)=0

    Methods of association

    Comparison method
    Proportion method
    Yules coefficient of association
    Karl pearsons coefficient of
    contingency

    comparison method
    Under this method the observed
    frequencies and expected frequencies
    are compared.
    Positively associated: (AB)>(A)(B)N
    Negatively associated:
    (AB)<(A)(B)N
    Independently associated:
    (AB)=(A)(B)N

    total

    60

    140

    200

    240

    560

    800

    300

    700

    1000

    total

    Proportion method
    In this method instead of expressing in actual
    numbers, it is expressed in proportions.
    Independent association: AB(B)=A or
    AB(A)=B() or A(A)=() or
    B(B)=()
    Positively associated: AB(B)>A or
    AB(A)>B() or A(A)>() or
    B(B)>()
    Negatively associated: AB(B)<A or
    AB(A)<B() or A(A)<() or
    B(B)<()

    Yules coefficient of
    association
    This method not only gives the nature
    but also the degree of association.
    Yules coefficient of association is
    denoted by the symbol Q
    Formula:
    Q=(AB)()-(A)(B)(AB)()+(A)(B)
    The value of Q lies between +1 and -1.

    Pearsons coefficient of
    contingency
    This method is used where qualitative
    data is classified into more than two
    classes.
    Formula: C = ZZ+N
    C=coefficient of contingency
    Z=chi-square value which is(O-E)E
    Where O=observed frequency
    E= expected frequency
    N= number of items

    Z
    C=

    Z+N

    Thank you

    You might also like