Nonparametric Techniques Southeast Missouri State 非参数技术东南密苏里州.pptVIP

2 3 5 7 12 16 17 18 21 25 26 Nonparametric Techniques CJ 526 Statistical Analysis in Criminal Justice Parametric v. Nonparametric: Parametric Parametric Dependent Variable: Interval/Ratio Parametric v. Nonparamteric: Nonparametric Nonparametric Dependent Variable: Nominal/ordinal Uses of Nonparametric Techniques Dependent Variable: Nominal/ordinal Nominal Level Data One Sample Chi-Square Test of Goodness of Fit, chisquare test of independence Ordinal Level Data Ranking Less demanding Easier to use Information Derived From an Ordinal Scale 1. Provides information about the direction of difference between scores Greater than, less than 2. Do not need absolute measurement to obtain ranks Information Derived From an Ordinal Scale -- continued Can always convert scores to ranks Mann-Whitney U Test Nonparametric analogue of an Independent t-Test Example: a police administrator wants to know whether gender has an effect on rank-ordered judgments of leadership ability Example -- continued Number of samples: 2 Nature of samples: independent σ Known: no Independent Variable: gender Example -- continued Dependent Variable and its Level of Measurement: judgments of leadership ability Target Population: hospital personnel Inferential Statistical Technique: Mann Whitney Example -- continued H0: Gender will have no effect on rank-ordered leadership ability H1: Gender will have an effect on rankings of leadership ability Decision Rule: If the p-value of the obtained test statistic is less than .05, reject the null hypothesis, two tailed test Example -- continued Obtained Test Statistic: z is used Z = -3.811, p = .0003 Decision: reject the null hypothesis Results Section The results of the Mann-Whitney U Test involving gender as the independent variable and rank-ordered leadership ability as the dependent variable were statistically significant, z = -3.811, p .001. Discussion Section It appears that males were ranked higher in terms of leadership abili