RMB: ONE SAMPLE WILCOXON WEEK 6

Question 1

Wilcoxon signed rank test

Answer 1

• One-sample Wilcoxon signed rank test is a nonparametric alternative method of one-sample t-test, which is used to test whether the location (median) of the measurement is equal to a specified value.
• when normal assumption is not satisfied, it is a powerful alternative of one-sample t-test
• Needs ordinal, interval or ratio data

Question 2

Using median in Wilcoxon signed rank

Answer 2

• This test is used to test a hypothesis about one population median > The median is the midpoint of the distribution: 50% below, 50% above
• Null hypothesis: Median = some value, m > median is = to the value m
• Alternative hypothesis: Median ¹ m (two-sided hypothesis) > median is not equal to m (non directional?)
• Median > m (one-sided hypothesis) > median will be greater than m (directional)
• Median < m (one-sided hypothesis) > median will be less than m (directional)
• We want to know if our sample is part of a larger sample (so distinct + significant from population) or just part of the population

Question 3

Calculating a Wilcoxon signed rank test

Answer 3

Calculate the difference between each observation and the interest value (m), (E.G. 100 mg/dl.)

2. You should exclude any difference = 0 (don’t include differences of zero)
3. To classify and order (ranking) differences by magnitude/size, not taken into account the sign (whether it is positive/negative)
4. Sum the rankings of positive differences.
5. Sum the rankings of negative differences.
6. Select the smallest of these sums and call it T.
   - This T value is searched in the critical values table from Wilcoxon signed rank test. We can read the table in the row corresponding to differences non-zero. Each row has ranges different of values corresponding to different p-values. > we don’t need to do this if we are using SPSS (more info how in onenote)

Question 4

One sample wilcoxon signed rank test

Answer 4

• ONE sample Wilcoxon signed rank test compares your sample with the median of a known larger sample OR population > When we know the median of the large comparison sample/population (E.g. Are 1st year psychologist more intelligent than the norm)

Question 5

Reporting one sample wilcoxon test in APA format

Answer 5

• need to know only the p value > The analysis demonstrated that the sample was significantly different from the population (P=0.007)
  Alternatively some suggest that you also add a T value (test statistic) from the SPSS output > e.g. The analysis demonstrated that the sample was significantly different from the population (T = 782.5, P=0.007)