Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    Wilcoxon Sign Rank Test

    Uploaded by

    a189192
    Notes on Wilcoxon Sign Rank Test

    Copyright:

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

    Wilcoxon Sign Rank Test

    Uploaded by

    a189192
    11 views5 pages
    Notes on Wilcoxon Sign Rank Test

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Notes on Wilcoxon Sign Rank Test

    Copyright:

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

    Wilcoxon Sign Rank Test

    Uploaded by

    a189192
    Notes on Wilcoxon Sign Rank Test

    Copyright:

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

    Explore

    Wilcoxon Signed • It is the first step in the analytic process


    • to explore the characteristics of the data
    Rank Test • to screen for errors and correct them
    • to look for distribution patterns - normal
    Dr Azmi Mohd Tamil distribution or not
    • May require transformation before further
    analysis using parametric methods
    • Or may need analysis using non-parametric
    techniques

    Nonparametric Test
    Choosing an appropriate method
    Procedures
    • Number of groups of observations • Statistic does not depend on population
    • Independent or dependent groups of distribution
    observations • Data may be nominally or ordinally scaled
    • Type of data – Example: Male-female
    • Distribution of data • May involve population parameters such
    • Objective of analysis as median
    • Based on analysis of ranks
    • Example: Wilcoxon rank sum test
    Advantages of
    non-parametric tests Non-parametric Tests
    Variable 1 Variable 2 Criteria Type of Test
    Qualitative Qualitative Sample size < 20 or (< 40 but Fisher Test
    • Used with all scales
    Dichotomus Dichotomus with at least one expected • Easier to calculate
    value < 5)
    Qualitative Quantitative Data not normally distributed Wilcoxon Rank Sum – Developed before wide computer
    Dichotomus Test or U Mann- use
    Whitney Test
    Qualitative Quantitative Data not normally distributed Kruskal-Wallis One • Make fewer assumptions
    Polinomial Way ANOVA Test
    Quantitative Quantitative Repeated measurement of the Wilcoxon Rank Sign
    • Need not involve population
    same individual & item Test parameters
    Continous or Quantitative - Data not normally distributed Spearman/Kendall
    ordinal continous Rank Correlation • Results may be as exact as
    parametric procedures © 1984-1994 T/Maker Co.

    Disadvantages of
    Non-parametric Tests Wilcoxon Signed Rank Test
    • May waste information • Two groups of paired observations
    – If data permit using parametric © 1984-1994 T/Maker Co.

    procedures
    – Example: Converting data
    from ratio to ordinal scale

    • Difficult to calculate by hand


    for large samples
    • Tables not widely available
    Example Step 2
    nores bps1 bps2
    237 147 131
    • Calculate the
    • Whether there
    835 166 150
    251 159 147 difference
    is any 809 150 139 between the two
    241 170 160
    difference of 233 164 155
    values.
    the systolic 272 154 145

    blood pressure 239 186 178 • Rank them


    taken at 2
    261 155 147
    accordingly,
    246 176 170

    different time 247 186 181 ignoring + or -.


    254 155 150
    for 36 patients. 258 151 147 • Total up the + & -
    288
    829
    152
    115
    148
    111
    separately
    257 162 159

    Refer to Table A7.


    Step 3 Look at n=33.

    • Total up the ranks of the positives and the Take the smallest value
    negatives. These are T+ dan T-. T+=152. Critical value for
    • T+ = 152 and T- = 409 n = 33 (3 zero values) for
    • Take the smaller value i.e. 152 and refer to significance at 0.05 is 171.
    the appropriate table. Critical value for n = 33
    (3 zero values so 36 - 3) for significance at
    Therefore 152 < critical
    0.05 is 171. Therefore < critical range. range; 0.02 < p < 0.05
    • Therefore : Null hypothesis rejected.
    • Conclusion: There is a sig difference of blood
    pressure measured at two different times. BP
    before rest is sig higher than after rest.
    SPSS Output
    Ranks

    N Mean Rank Sum of Ranks


    BPS2 - BPS1 Negative Ranks 21a 19.48 409.00
    Pos itive Ranks 12b 12.67 152.00
    Ties 3c
    Total 36
    a. BPS2 < BPS1
    b. BPS2 > BPS1
    c. BPS2 = BPS1

    Te st Statis ticsb

    BPS2 - BPS1
    Z -2.300a
    A symp. Sig. (2-tailed) .021
    a. Based on positive ranks.
    b. Wilcoxon Signed Ranks Tes t

    Presentation Take Home Message


    • Never sufficient to present the results • Both parametric & non-parametric
    solely as a p value methods can be used for continuous data
    • Median and quartiles should be given • Parametric methods are preferred if all
    assumptions are met
    • For small samples, the median and range
    • Reasons
    can be given
    – Amenable to estimation and confidence
    interval
    – Readily extended to the more complicated
    data structures
    Take Home Message
    • We should carry out either parametric or non-
    parametric test on a set of data, not both.
    • When there are doubts of the validity of the
    assumptions for the parametric method, a non
    parametric analysis is carried out
    • If the assumptions are met, the two methods
    should give very similar answers
    • If the answers differ, then the non-parametric
    method is more likely to be reliable

    You might also like