# TSQFUS1: Time & Stress Questionnaire for University Students- Survey Research an

TSQFUS1: Time & Stress Questionnaire for University Students- Survey Research and Design in Psychology- Psychology Lab Report Assignment Task: You are being invited to participate in this survey as part of an official class exercise for “Survey Research and Design in Psychology” (7126), Semester 1, 2018, at the University of Canberra. This survey asks about your university experience so far, stress, time perspective, and time management. Participation is voluntary and you may withdraw at any time. You may also choose to complete some but not all questions. Completion of this 58-item survey is expected to take approximately 15 minutes. Only complete this survey once. The approach to analysis should proceed through three basic steps: Data screening – Summarise in one to two paragraphs how the data was screened and what changes were made. Is enough detail provided for the same steps to be followed by someone else? However, avoid excessive detail (e.g, CaseID number are meaningless to a reader). Sample size assumptions do not belong in this section – instead, this would belong in the section(s) for the corresponding analyses. Psychometric instrument development Conduct EFA of a multidimensional construct (either the time perspective items or the time management items). For each extracted factor, provide reliability analysis (internal consistency – Cronbach’s alpha), composite score descriptive statistics, and correlations between factors. Multiple linear regression – Conduct at least one MLR with at least three IVs to address one hypothesis per IV Qualitative analysis (for 6667 (G) students only) Communicate the depth of your understanding by using your own words; avoid writing results in a robotic (mindless) manner (e.g., avoid overparaphrasing a specific sample write-up) Most statistics should be rounded to two decimal places unless there is particularly useful information communicated by including a third decimal place (e.g., when reporting exact p values). Scope and depth of analysis Additional analyses may be presented. However, it is quite possible to gain maximum marks by conducting one of each of the required analyses. If additional analyses are presented, then they must be clearly related to the research question and hypothesis(es). In marking, some account will be taken of the scope of the analysis undertaken. Where a more advanced analysis is appropriate (given the research questions(s) and/or hypothesis(es)) and is well conducted, this could represent higher quality work than a simpler analysis. However, there’s much also to be said for parsimony(keep it simple and get it right) by focusing on doing a good job of fulfilling the minimum requirements. The best reports are usually not the most complex ones. If in doubt, go with analyses which meet the minimum criteria, which relate to the research question and/or hypotheses, and which you are confident about accurately conducting, interpreting and presenting. Psychometric instrument development Report the results of at least one EFAof a multidimensional survey construct (either time perspective or time management) The minimum requirement is to report one EFA. However, it may be of interest to conduct a factor analysis of another set of items (e.g., stress) in order to develop other composite scores for further analysis. In this case, present one EFA (of other time perspective or time management) in full and briefly summarise the results of the other EFA, perhaps with relevant output in an appendix. Indicate the type of EFA used (Type of extraction? Type of rotation?) Explain the extent to which EFA assumptions were met, but not excessively (e.g., one indicator of factorability is quite sufficient; more is redundant) Sample size (incl. cases:variables ratio) Linearity (e.g., check at least some scatterplots, particularly for bivariate outliers or non-linear relations) Factorability of correlation matrix (either examine item correlations, report about anti-correlation matrix diagonals, or use a global diagnostic, either KMO or Bartlett’s – but do not report all of these as they are redundant) Focus on the final model but summarise the steps taken to get there (e.g., How many factors were extracted initially? What models/factors structures were examined? To what extent was the expected structure evident?) % of variance explained (for the initial and final model(s)) Label and describe each factor Which items were retained and/or dropped and the reasons why Table of factor loadings and communalities (for the final model) Reliability analysis(Internal consistency – (Cronbach’s alpha)) for each factor Calculation of Composite scoresto represent each factor Table of descriptive statistics for the composite scores Table of correlationsbetween composite scores Multiple linear regression Report the results of at least one MLR with at least three predictors – can use any variables in, or derived from, the supplied data set (if they meet the assumptions for MLR) Reiterate the purpose (research question and/or hypotheses) of the MLR Mention the type of MLR Describe the IVs and DVs, and any manipulations of the variables (e.g., recoding or creating an interaction term). If its not already clear from the Method, clarify the direction of scoring. Explain the extent to which assumptions were met (e.g., multicollinearity, multivariate outliers) Present the correlations between the items (can be part of the MLR coefficients table – see sample write-ups for examples). Demonstrate understanding of the directions of any relationships (e.g., if there is a positive correlation between X and Gender, what does this mean? Are higher values of X associated with males or females?) Report amount of variance explained ( R 2 and Adjusted R 2 (and the R 2 change at each step if a hierarchical MLR is being conducted), along with inferential tests ( F (df), p ) Report significance, size, direction and relative contribution of each IV. Table showing the correlations and MLR coefficients, including B for intercept & IVs and Beta (β), and the statistical significance (e.g., t , p ), and semi-partial correlations squared ( sr 2 ) for each IV and explain the direction and size of the results.