STEP 1: Create variables
Run frequency tables for the new variables to check that they are accurate
Run a frequency table of your dummy variable to check that it is accurate
Run a reliability analysis using the following 10 variables:
COMPUTE FEAR=q25afearmurder + q25bfearrape + q25cfearweapon + q25dfearhome + q25efearcar + q25ffearmugged + q25gvandal + q25hconned + q25ibeggar + q25jbeaten. EXECUTE.
measures of central tendency and dispersion for this new variable
o Dependent variable:
Punitive attitudes additive scale
Run a reliability analysis for the following 8 variables
The alpha coefficient for the eight items is .832, suggesting that the items have relatively high internal consistency. Cronbach's alpha is a measure of internal consistency, that is, how closely related a set of items are as a group. It is considered to be a measure of scale reliability. A "high" value for alpha does not imply that the measure is unidimensional. It simply provides you with an overall reliability coefficient for a set of variables hence statistical test need to be done to determine the reliability of the combined data.
Compute variable called PUNITIVE
COMPUTE PUNITIVE =q2asentences + q2crepeat+q2dpolice + q2eprivilege + q2flocking + q2gchain + q2icastrate + q2kmandatory. EXECUTE.
measures of central tendency and dispersion for this new variable to check the accuracy.
STEP 2: Check variables
The statistics to be used require normal distribution of all variables.
STEP 3: Check for outliers
STEP 4: Check for representativeness of sample
one-sample t-test
goodness of fit chi-square test
STEP 5: Bivariate association/correlation
independent samples t-test for the variable PUNITVE
STEP 6: Multivariate analysis
The fear factor has a positive value which implies that for 0 change in fear there will be a value of 30.33
Coefficient of correlation is less than 0.5 hence the relationship between the variables is very low.
