Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 111 views

    Sample Size Calculation

    Uploaded by

    astha singh
    This document provides an overview of sample size calculation. It defines key terms like sample, population, sampling error. It presents two main formulas for calculating sample size for descriptive and experimental studies. An example calculation is shown for each. The document recommends using online sample size calculators to aid beginners in determining appropriate sample sizes.

    Copyright:

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

    Sample Size Calculation

    Uploaded by

    astha singh
    111 views13 pages
    This document provides an overview of sample size calculation. It defines key terms like sample, population, sampling error. It presents two main formulas for calculating sample size for descriptive and experimental studies. An example calculation is shown for each. The document recommends using online sample size calculators to aid beginners in determining appropriate sample sizes.

    Original Title

    sample size calculation

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides an overview of sample size calculation. It defines key terms like sample, population, sampling error. It presents two main formulas for calculating sample size for descriptive and experimental studies. An example calculation is shown for each. The document recommends using online sample size calculators to aid beginners in determining appropriate sample sizes.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    111 views13 pages

    Sample Size Calculation

    Uploaded by

    astha singh
    This document provides an overview of sample size calculation. It defines key terms like sample, population, sampling error. It presents two main formulas for calculating sample size for descriptive and experimental studies. An example calculation is shown for each. The document recommends using online sample size calculators to aid beginners in determining appropriate sample sizes.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 13

    SAMPLE SIZE

    CALCULATION

    Presented by :Mr. Preeti


    BASICS OF SAMPLE SIZE CALCULATION
    WHAT IS SAMPLE?
    SAMPLESA
     Proportion of

    The total population.

    WHAT IS SAMPLE SIZE? POPULATION


     Part of a population chosen for experiment or
    analysis.
     Make inferences about a population using sample
    data.
     A widely chosen sample is a good representation of
    the population.
    WHAT IS SAMPLING ERROR?

     WHETHER DAMPLING STATISTIC IS AN ACCURATE


    REPRESENTATION OF THE POPULATION.
     USUALLY MEASURED BY A CONFIDENCE INTERVAL
    95% CONFIDENCE INTERVAL.
     95% OF THE TIMES I WOULD GET THE SAME
    RESULTS.
    CALCULATING SAMPLE SIZE
    1. sample size for Descriptive study: in a hypothesis testing descriptive
    study, an approximate formula (cochran,1977) for determining the
    saple size for a variable expressed as a percentage is:

    SAMPLE SIZE (n)= z² (pq)


    e²
    Desired confidence Z-score
    WHERE,
    level
    n= sample size
    p= variability / standard deviation (it can be taken from 80% 1.28
    previous studies or pilot study.
    q= 1-p
    85% 1.44
    e= Sampling error {se}/ Margin of error {me}/ Acceptable 90% 1.65
    Sample Error
    z= z- score {the number of standard deviations a given
    95% 1.96
    proportion is away from the mean} 99% 2.58

    Must remember:
    • smaller margin of error means larger sample size
    •Higher confidence level means larger sample size
    EXAMPLE CALCULATION
    A health department nutritionist, wishing to conduct a
    survey among a population of teenage girls to
    determine the average daily protein intake
    What information is needed to estimate the sample
    size?
    The nutritionist must provide three items of
    information: the desired width of the confidence
    interval, the level of confidence desired and the
    magnitude of the population variance.
    WHAT SAMPLE SIZE DO I NEED IF …?
     Solution: the nutritionist would like an interval about
    10 unit wide; that is, the estimate should be within
    about 5 unit of the true value in either direction. A
    confidence co-efficient of 95 is decided and on that,
    from past experience, the nutritionist feels that the
    population standard deviation is probably about 20
    grams.
     Summarizing the information: z=1.96, p=20,e= 5
    n= (1.96)² 20(1-20) = 3.84×380 = 1459.9 = 58.39s
    5² 25 25
     2. sample size for experimental study
    in experimental study where testing the hypothesis that
    the difference between two groups, such as
    experimental group and control group is significant or
    not , the following formula my be used:
    n= (α₁+α₂)² (Z₁­α⁄₂+Z₁‐β)
    (m₁-m₂)²
    where,
    Z₁­α⁄₂: the level of significance for two tails, when
    researcher considers that intervention may have
    positive or negative effect on outcome variable.
    Otherwise, one tail effect is considered only in one
    direction (Z₁­α)
     Z₁‐β : the power researcher considers for
    detecting the difference, which is generally
    considered 80% or 90%. Z₀.₉₀= 1.28 from
    Gaussian table.
     σ1=SD of the outcome variable in group -1.
     σ2= SD of the outcome variable in group-2.
     m₁= mean of the outcome variable in group-1
     m₂= mean of the outcome variable in group-2
     For example:
    A researcher wants to conduct an experiential study to
    assess the effect of lowering sodium in diet on systolic
    blood pressure (SBP) among hypertensive patients
    visiting OPD of AIIMS, Rishikesh.
    based on similar research conducted at a different
    place or a pilot study, the standard deviation of SBP in
    group with low sodium diet is 11.3 mmHg. If α=0.05
    and β= 0.10, how many persons from each group
    should be studied, if one wants to detect 3.0 mmHg
    difference in SBP in the two groups.
    to estimate the sample size, researcher will
    consider to generalize the findings.
    n= (α₁+α₂)² (Z₁­α⁄₂+Z₁‐β)
    (m₁-m₂)²
    Z₁­α⁄₂: the level of significance, which is considered as
    0.05 for two trails, because researcher considers that
    salt intake increase or decrease the SBP. The
    Z₀.₉₅=1.96.
     Z₁‐β : the power researcher considers for detecting the
    difference, which is considered as 0.10 in this study.
    Z₀.₉₀= 1.28 from Gaussian table.
     σ1=SD of the outcome variable in group -1=11.3 mmHg
     σ2= SD of the outcome variable in group-2=13.0 mmHg
     m₁-m₂= mean difference of the outcome variable in
    group-1 and group-2 =3.0
    n= (11.3+13.0)² (1.96+1.28)² =347
    (3.0)²
    Therefore, a minimum of 347 subjects in each
    group would be required to be included in
    this study. This calculation assumes the
    subjects must be randomized between the
    two group. There may not be any non
    response in such kind of trials. Other
    consideration will be as per mentioned in
    example of estimating sample size for
    descriptive study.
    SAMPLE SIZE CALCULATION
    USING COMPUTER
     The beginner health care professionals may
    find the sample size calculation using
    different formulas. For example, they may
    use the user friendly, free webpage called
    RAOSOFT
    http://www.raosoft.com/samplesize.html
    BIBLIOGRAPHY

     Dr.suresh k.sharma. nursing research &


    statistics.1st edition.newdelhi. Elsevier
    publication:2011.Pp-234-236
     Denise f.polit.Cheryl tatano beck. Essentials
    of nursing research .7th edition. New delhi .
    wolters kluwer publication2010.pp-304-309.

    You might also like