values cut off dates Returning to the Field The questionnaires with

# Values cut off dates returning to the field the

This preview shows page 23 - 29 out of 44 pages.

values, cut-off dates ( · Returning to the Field – The questionnaires with unsatisfactory responses may be returned to the field, where the interviewers recontact the respondents. · Assigning Missing Values – If returning the questionnaires to the field is not feasible, the editor may assign missing values to unsatisfactory responses. · Discarding Unsatisfactory Respondents – Respondents with unsatisfactory responses are simply discarded. Descriptive statistics Statistics that quantitatively describe or summarize features of a collection of information (learn about the population from a sample ( Measures of central tendency Mean (metric data ( Median (ordinal onwards ( Measures of variability (at least ordinal data ( Range Interquatile range (ordinal onwards ( Variance (metric ( Standard deviation (metric ( Coefficient of variation (metric ( W8 – Statistics and hypothesis testing How to make hypothesis Sample: What you calculate from the sample Population: The true values of RQ (unknown ( Relational Correlation coefficient Measure of the sign (direction) and strength of the linear relationship between two or more variables < 0 = positive > 0 = negative Nominal/ordinal data (categorical, 2 or more categories ( Chi square test of proportion · Compare the sample proportions of individuals within different groups to population proportions (sample representativeness) RQ: Is customers’ gender ratio different from 50% ? H0: The gender ratio for HP customer is 50% H1: The gender ratio for HP customer is different from 50% Interpret: Asymp. Sig FAIL TO REJECT H0 The p-value 0.60 > 0.05. Thus, H0 cannot be rejected. The gender ratio of HP customers is 50%, STOP REJECT H0 The p-value 0.00 < 0.05. Thus, H0 can be rejected. The gender ratio of HP customers is not 50%. Females have a higher proportion, STOP Chi Square Test of Association / cross tabs (relational, categorical data ( · Test the (non-linear) association between categorically scaled variables (two variables) RQ: Is there an association between price sensitivity levels and income groups for HP customers ? H0: There is no association between customers’ price sensitivity levels and income group H1: There is an association between customers’ price sensitivity levels and income group Interpret: Pearson chi-square, nominal by nominal, percentage within FAIL TO REJECT H0 The p-value 0.60 > 0.05. Thus, H0 cannot be rejected. There is no relationship between price sensitivity levels and income groups . REJECT H0 The p-value 0.00 < 0.05. Thus, H0 can be rejected. There is an association between price sensitivity levels and income groups . · As income group increases, less proportion of customers remain price sensitive · The association is moderate. Interval / ratio scaled data One sample T-Test (independent, comparative, metric scale ( · Compare the average value of one variable to a constant RQ: Is HP customers’ average customer satisfaction different from 2.5 ?  #### You've reached the end of your free preview.

Want to read all 44 pages?

• Two '16
• • • 