Introduction to the Process of Research Chapter 7: Putting It All Together: From Process to Product RSCH 202 – Module 7 Chapter 7: Putting It All Together: From Process to Product 7.1: Arriving at a research question 7.2: Validation of the research question, or questions: Preliminary literature review 7.3: From variable selection and preliminary literature review to identification of potential sample 7.4: From sample identification and variables to formal literature review 7.5: Onward to data sources and collection techniques 7.6: From data sources to analysis 7.7: Quantitative and qualitative differences 7.8: From write-up to dissemination 2 7.1: Arriving at a Research Question The research question drives the research. Research questions can arise from many places: existing theories constructs other research events around you 3 7.2: Validation of the research question, or questions: Preliminary Literature Review Previous research gives you a base for starting your investigation Focused and operationaizable research question find out what is already known about the topic determine what variables are important to examine 4 7.3: From variable selection and preliminary literature review to identification of potential sample The literature - both theoretical and applied serves as a starting point and an indicator of a direction to follow. identify variables that are germane to the research questions identify potential subjects or measurements 5 7.4: From sample identification and variables to formal literature review The literature review should: • be organized in a logical manner • never be rambling presentations of past studies in the order they were found • lead from the broad to the specific where the hypothesis drops out of the review naturally. • be like winding your way down through a funnel, from the broad top part, ever narrowing, to the final point of dispensing what was placed in the funnel the hypothesis 6 7.5: Onward to data sources and collection techniques Literature review Variables defined Subjects identified IRB approval Collect data 7 7.6: From data sources to analysis The research question(s) will drive the statistical analysis. Research Questions Data Analysis 8 7.7: Quantitative and qualitative differences A qualitative study would differ from a quantitative study in the following ways: Research Question: qualitative in nature—the how, what, why; more subjective Data sources and collection: qualitative methods of data collection Data analysis: not statistical in nature; look at arrangement of data around what appear to be common themes (content analysis), or let the data speak for itself and see what it presents to you (grounded theory analysis) 9 7.8: From write-up to dissemination Presenting at Conferences Poster Sessions Proceedings & Journals 10 7.8: From write-up to dissemination Types of Journals peer-reviewed editor-reviewed non-peer-reviewed proceedings • Require that your manuscript undergo a review by several experts in the field. • Reviewers ensure that your paper meets the highest research standards • An editor wants to make sure that papers or articles that are published are solid, well-researched, and well-written. • Findings do not go through any review • Conferences publish presented papers • Not peer-reviewed, other than the review that led to acceptance 11 7.8: From write-up to dissemination Preparing the Manuscript Review the submission requirements - usually published on the journal website - and follow them closely, paying attention to the required formatting convention (e.g., APA). Most journals these days will accept electronic submissions, but some still want a printed copy of your manuscript as well Make sure that your paper outlines the research process you followed and that the results support your research question. 12 7.8: From write-up to dissemination Notification About Your Manuscript Outright rejection Acceptance with revisions Acceptance without revisions 13 Type of Data Goal Measurement (From Gaussian Population) Rank , Score, or Measurements (from Non-Gaussian Population) Binomial (Two Possible Outcomes) Survival Time Describe one group Mean, SD Median, interquartile range Proportion Kaplan Meier survival curve Compare one group to a hypothetical value One-Sample t test Wilcoxon test Chi-Square or Bionomial test Compare two unpaired groups Unpaired test Mann-Whitney test Fisher's test (Chi-square for large samples) Log-rank test or Mantel-Haenszel Compare two paried groups Paired t test Wilcoxon test McNemar's test Conditional proportional hazards regression Compare three or more unmatched groups One-way ANOVA Kruskal-Walllis test Chi-square test Cox proportional hazard regression Compare three or more matched groups Repeated-Measures ANOVA Friedman test Cochrane Q Conditional proportional hazards regression Quantify association between two variables Pearson Correlation Spearman correlation Contigency coefficients Predict value from Simple linear regression another measured variable or Nonlinear regression Nonparametric regression Simple logistic regression Cox proportional hazard regression Predict value from several Multiple linear regression measured or bionomial or Multiple nonlinear variables regression Multiple logistic regression Cox proportional hazard regression Flow Chart for Selecting Commonly used Statistical Tests Type of Data? Continuous Discrete, Categorical Type of Question? Chi-square tests one and two sample Relationships Differences Differences between what? -Means. How many treatment groups ? Do you have a true independent variable? Tests for Equal Variances Two Groups More than -No- two groups Yes Fmax test, Brown and Smythe's test, Bartlett's tests Regression Analyses Correlation Analysis Parametric assumptions satisfied? Parametric assumptions satisfied? Parametric Nonparametric -No- No. Pearson's r. Spearman's Rank Correlation Yes Parametric Data transform worked? Data transform worked? Determine Yes Student's unpaired t-test, Paired t-test Yes Parametric No Nonparametric Yes Parametric No Nonparametric Mann-Whitney U or Wilcoxon Rank Sums Test Kruskal-Wallis Test ANOVA Parametircs Assumptions: 1. Independent, unbiased samples 2. Data normally distributed 3. Equal variances If significant, do a post hoc test, e.g. Turkey's or Bonferroni's If significant, do a Dunn's Test
Purchase answer to see full attachment