CRIM 320 Lecture Notes - Box Plot, Skewness, Saskatchewan Highway 3

• School: Simon Fraser University
• Department: Criminology
• Course: CRIM 320
• Professor: Patrick Lussier

Document Summary

What to do before conducting a statistical analysis. Increase power of statistical analysis (i. e. , explained variance) Minimize type i and type ii errors. Minimize risk of biased estimation of population parameters. Generally don"t know why the data is missing. If missing values are random, then not a validity threat: not critical if <5% of a particular variable is missing (n>100, otherwise, might not be able to generalize results , example: mmpi and reading abilities. 0 means absence of information, in cambridge data set under missing, you can"t leave the 0 in your analysis, spss doesn"t know, if you"re running statistical analysis 0 will get analyzed as a value by spss. Patterns of missing data: spss/analyze/missing value analysis/patterns. Maternal attitude (overprotective, cruel, passive, etc. : chi-square, t-test, anova etc, determine whether your two groups are statistically different, report those analyses in your study. Prepare data for statistical analyses: you may decide to drop a variable from your study.