Scribd Logo
Upload

Welcome to Scribd!

  • 28 views

    13-Inference About A Population

    Uploaded by

    Sharlize Veyen Ruiz
    This document discusses two statistical tests: 1) inference about population proportions, which is used to test if the difference between two sample proportions is statistically significant, and 2) inference about correlation coefficients, which is used to determine if the relationship between two variables is statistically significant. It provides examples of how to perform hypothesis tests to evaluate the significance of differences in proportions and correlations. Key steps include stating the null and alternative hypotheses, determining the test statistic and critical value, and making a decision to reject or fail to reject the null based on comparing the test statistic and critical value.

    Copyright:

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

    13-Inference About A Population

    Uploaded by

    Sharlize Veyen Ruiz
    28 views5 pages
    This document discusses two statistical tests: 1) inference about population proportions, which is used to test if the difference between two sample proportions is statistically significant, and 2) inference about correlation coefficients, which is used to determine if the relationship between two variables is statistically significant. It provides examples of how to perform hypothesis tests to evaluate the significance of differences in proportions and correlations. Key steps include stating the null and alternative hypotheses, determining the test statistic and critical value, and making a decision to reject or fail to reject the null based on comparing the test statistic and critical value.

    Original Description:

    Inference about Population

    Original Title

    13-Inference About a Population

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses two statistical tests: 1) inference about population proportions, which is used to test if the difference between two sample proportions is statistically significant, and 2) inference about correlation coefficients, which is used to determine if the relationship between two variables is statistically significant. It provides examples of how to perform hypothesis tests to evaluate the significance of differences in proportions and correlations. Key steps include stating the null and alternative hypotheses, determining the test statistic and critical value, and making a decision to reject or fail to reject the null based on comparing the test statistic and critical value.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    28 views5 pages

    13-Inference About A Population

    Uploaded by

    Sharlize Veyen Ruiz
    This document discusses two statistical tests: 1) inference about population proportions, which is used to test if the difference between two sample proportions is statistically significant, and 2) inference about correlation coefficients, which is used to determine if the relationship between two variables is statistically significant. It provides examples of how to perform hypothesis tests to evaluate the significance of differences in proportions and correlations. Key steps include stating the null and alternative hypotheses, determining the test statistic and critical value, and making a decision to reject or fail to reject the null based on comparing the test statistic and critical value.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 5

    Lesson 13.

    Inference About Population Proportion

    A. Inference about a Proportion

    This is used to test the significance if the difference between two sample
    proportions.

    Example:

    A sample survey of a TV program shows that 80 of 200 men and 75 of


    250 women dislike the same program. We want to decide whether the difference
    between the two sample proportions, 80/200 = 0.40 and 75/250 = 0.30, is
    significant or not at 0.05 level of significance.

    Step 1. Make assumptions

    - Respondents randomly selected

    - Distribution is normal

    Step 2. State the hypothesis

    Ho: There is no significant difference between the two sample proportions.


    ( P1 = P2 )

    Ha: There is significant difference between the two sample proportions.


    ( P1 ≠ P2 )

    Step 3. Set a critical region

    Sampling distribution = Z distribution ; n > 30

    Level of significance = 0.05 (two tailed)

    Z (.05) = + / - 1.96

    Step 4. Compute the test statistic

    Z = P1 - P2

    √ P1q1/n1 + P2q2 /n2


    Where:

    P1 = 80 / 200 = 0.40

    P2 = 75 / 250 = 0.30

    q1 = 1 - P1 = 1 - 0.40 = 0.60

    q2 = 1 - P2 = 1 - 0.30 = 0.70

    n1 - 200, n2 = 250

    Z = 0.40 - 0.30

    √ 0.40 (0.6) / 200 + 0.30(0.7) /250

    = 0.10 / √ 0.0012 + .00084

    = 0.10 / 0.045

    Z = 2. 22

    Step 5. Make a decision

    Z computed = 2.22 > Z critical = 1.96

    Therefore. Reject Ho.

    There is significant difference between the two sample proportions.men


    and women viewership.

    B. Inferences About Correlation Coefficients: rxy , rho, rpb,

    This is used when you are not only interested in looking into the degree of
    the relationship between two variables but also wants to find out whether the
    relationship between the set variables is significant or not.
     For variables treated with Pearson Product Moment Correlation ( r xy) ,
    Spearman’s Rank Correlation (rho ) and Point Biserial Correlation
    (rpb), the significance of these correlation coefficients can be
    determined by using the formula.

    t = r / √ n - 2/ 1 - r2

    where: r can be r xy , rho, rpb

    Example:

    Assessing that the correlation coefficient computed between performance


    and length of service is rxy = 0.73 from a sample of 17 respondents.

    Ho: There is no significant relationship computed between performance


    and length of service.

    Ha: There is significant relationship computed between performance


    and length of service.

    t = r / √ n-2 / 1 - r2

    = 0.73 √ 17 - 2 / 1 - (0.73)2

    = 0.73 ( 5.67)

    = 4.14

    t critical at 0.05 = 2.131 ( two tailed)

    t computed = 4.14 > 2.131

    Therefore, Reject Ho, there is a significant relationship between


    performance and length of service.

    Another way to determine the relationship is significant or not is to


    compare the computed correlation coefficient with the correlation coefficient
    required at 0.05 probability level making use of Appendix C with degree of
    freedom n -2.
    Example: If the computed correlation coefficient is 0.73 fro 17 respondents ( df=
    17 - 2 = 15) , the correlation coefficient required at 0.05 = 0.4821. The computed
    r is greater than r (.05, 15). Then the relationship between performance and
    length of service is indeed significant at 0.05 probability level.

    Exercise 13

    1. Globe Telecommunication is trying to decide whether some new lines in a


    large community should be installed underground. Because a small surcharge
    will be added to telephone bills to pay for the extra installation costs, the
    company has decided to survey customers and proceed only if the survey
    strongly indicates that more than 60% of all customers favor underground
    installation. If 118 of 160 customers surveyed favor underground installation in
    spite of the surcharge, what should the company do? Test using 0.05 level of
    significance.

    2. A study was made to determine whether military cadets who scored high on
    conduct also tended to do well academically. A random sample of of 5 cadets
    showed the following scores on conduct X and academic average Y .

    A. Calculate the Pearson Correlation Coefficient

    B. What is the degree of correlation?

    C. Test the significance of r , follow the steps in hypothesis testing.( Use the
    value if degree of correlation from the table of correlation from previous lesson).

    Conduct Academic
    Cadet
    X Ave. Y

    Aiza 76 3.2

    Faye 52 2.3

    Joselle 78 3.7

    Joanna 44 4

    Monique 100 1.8

    You might also like