Scribd Logo
Upload

Welcome to Scribd!

  • 41 views

    13.1 Power Point

    Uploaded by

    krothroc
    This document discusses comparing means between two samples or populations using two-sample statistical tests and procedures. It introduces two-sample z and t confidence intervals and hypothesis tests for comparing the means of two independent samples. Key assumptions of these procedures are that the samples are random and independent with approximately normally distributed populations. The document provides formulas and explanations for conducting two-sample inference tests.

    Copyright:

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

    13.1 Power Point

    Uploaded by

    krothroc
    41 views11 pages
    This document discusses comparing means between two samples or populations using two-sample statistical tests and procedures. It introduces two-sample z and t confidence intervals and hypothesis tests for comparing the means of two independent samples. Key assumptions of these procedures are that the samples are random and independent with approximately normally distributed populations. The document provides formulas and explanations for conducting two-sample inference tests.

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses comparing means between two samples or populations using two-sample statistical tests and procedures. It introduces two-sample z and t confidence intervals and hypothesis tests for comparing the means of two independent samples. Key assumptions of these procedures are that the samples are random and independent with approximately normally distributed populations. The document provides formulas and explanations for conducting two-sample inference tests.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    41 views11 pages

    13.1 Power Point

    Uploaded by

    krothroc
    This document discusses comparing means between two samples or populations using two-sample statistical tests and procedures. It introduces two-sample z and t confidence intervals and hypothesis tests for comparing the means of two independent samples. Key assumptions of these procedures are that the samples are random and independent with approximately normally distributed populations. The document provides formulas and explanations for conducting two-sample inference tests.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    of 11

    Comparing Two Means

    Section 13.1
    Twice As Nice
    • Which of two popular drugs – Lipitor or Pravachol –
    helps lower bad cholesterol? At the end of the PROVE-
    IT Study, researchers compared the mean “bad”
    cholesterol levels for the two groups.
    • Later researchers also compared the proportion of
    subjects in each group who had serious consequences
    within two years of the study.
    • How do small businesses that fail differ from those that
    succeed? Business school researchers compare the asset
    to liability ratios for two samples of firms, one sample of
    failed businesses and one of firms that are still running.
    Hey Man, What’s Your Problem?

    • Comparing two populations or two treatments is


    one of the most common situations encountered in
    statistical practice.

    • We call such situations two-sample problems.


    Two-Sample Problems
    Matched-Pairs vs. Two-Sample
    • Unlike the matched-pairs designs we studied
    earlier, there is no matching of the units in the two
    samples.

    • Also, the two samples can be of different sizes.


    Name Your Procedure
    • Two-sample z confidence interval for μ1 – μ2

    • Two-sample t confidence interval μ1 – μ2

    • Two-sample z test for μ1 – μ2

    • Two-sample t test for μ1 – μ2


    Hypotheses for Two-Sample Tests

    • H0: μ1 – μ2 = 0 (or μ1 = μ2)

    • Ha: μ1 – μ2 <, >, or ≠ 0 (or μ1 <, >, or ≠ μ2)


    SINning With Two-Sample Procedures
    • S – We have an SRS from two distinct
    populations. We measure the same variable for
    both samples.
    • I – One sample has no influence on the other (or
    when sampling w/o replacement, N ≥ 10n for
    each population.)
    • N – Both populations are ~Normally distributed.
    The Math:
    Two-Sample z CI: Two-Sample t CI:
     12  2 2 s 2
    s 2
    ( x1  x2 )  z   ( x1  x2 )  t  1  2
    n1 n2 n1 n2

    Two-Sample z Test: Two-Sample t Test:


    ( x1  x2 )  ( 1   2 ) ( x1  x2 )  ( 1  2 )
    z t
     12  2 2
     s12 s2 2
    n1 n2 
    n1 n2
    df???

    Or if using the table, use whichever of n1 – 1 or n2 – 1 is smaller.


    Stay Out of the Pool!!!
    • When using the calculator, you are asked whether
    the data is “pooled” or not. The “unpooled” test is
    our two-sample test (a test using unequal
    variances.) The “pooled” test is a special case
    where we assume that the populations have equal
    variances. This procedure averages (pools) the
    two sample variances to estimate the common
    population variance. Since population variances
    are hardly ever equal – don’t pool!!!

    You might also like