Week 5 Confused questions and socially biased answers? Avoiding Problem Questions Type Example 1. Ambiguous 2. Based on assumptions 3. Draw on memory 4. Double 5. Leading 6. Presuming 7. Hypothetical 8. Sensitive 9. Offensive 10. Jargon Below are examples of questions which fail one of the above tests – put them in the categories and as you do so think why they are flawed? a. Do you like Snow Patrol and Fat Boy Slim? b. Do you not agree that anti terror legislation should be strengthened? c. How old are you? d. If you had £1000 how would you spend it? e. When you were at school how many times did you get a detention? f. Does your child sleep in their own bed? g. Do you spend a great deal of time on an essay? h. Do you think you need a face-lift? i. Do you think the council has an adequate mission statement? j. Do you think staff will be empowered through quality enhancement?   Think of this research topic: Gender Pay Discrimination: Empirical Evidence from the UK Discussion 1. Think about what you have learnt in the past five weeks a. What kind of literature do you need to read? b. What is the theoretical framework? 2. Assume the data collection method is to use a survey; now work as a group of three to design the questionnaire (8-10 minutes) with at least four questions? Who should be your respondents? What is your dependent variable? How are you going to measure it? What are your explanatory variables? How do you know? What kind of questions are you going to ask in order to collect information? How to measure them?   Work sheet for UK delivery Input these information in SPSS 20 ID gender age Industry How satisfied with pay? 1 Male 16-19 retail neutral 2 Female 30-39 manufacture dissatisfied 3 Female 50-59 education Very satisfied 4 Male Over 65 manufacture satisficed 5 Male 20-29 retail Very satisfied 6 Female 16-19 education dissatisfied 7 Male 40-49 education Very satisfied 8 Female 30-39 manufacture neutral 9 Female 50-59 retail satisfied 10 male 16-19 manufacture Very dissatisfied Based on the value of variables, it can be grouped as categorical and continuous variable • Categorical variables • Nominal variables are variables that have two or more categories, but which do not have an intrinsic order. Types of property: detached, semi, Terraced, bungalow • Dichotomous variables are nominal variables which have only two categories or levels. Are you a student? Yes/No • Ordinal variables are variables that have two or more categories just like nominal variables only the categories can also be ordered or ranked. How happy with your grade rating from 1 to 5: not at all to very much. • Continuous variables: quantitative variables, such as age, height, profit, price We therefore need to code this wording information into numbers accordingly Gender: dichotomous variable. 1 male, 0 female. Age: we try to keep continuous variable, therefore, use the mid-point to recode it. 16-19, 17.5; 20-19, 24.5; 30-39, 34.5; 40-49, 44.5; 50-65, 57; over 65, 70. Industry: nominal variable. 1 retail, 2 manufactures, 3 education Level of satisfaction with pay: ordinal variable. Likert-scale data, 1 very dissatisfied, 2 dissatisfied; 3 neutral; 4 satisfied; 5 very satisfied. Some scholars code it as -2 very dissatisfied; -1 dissatisfied; 0 neutral; 1 satisfied; 2 very satisfied in order to test normal distribution.