How do I do dissertation data analysis?
Data Analysis Plan Overview
Dissertation methodologies require a data analysis plan. Your dissertation data analysis plan should clearly state the statistical tests and assumptions of these tests to examine each of the research questions, how scores are cleaned and created, and the desired sample size for that test. The selection of statistical tests depend on two factors: (1) how the research questions and hypotheses are phrased and (2) the level of measurement of the variables. For example, if the question examines the impact of variable x on variable y, we are talking about regressions, if the question seeks associations or relationships, we are into correlation and chi-square tests, if differences are examined, then t-tests and ANOVA’s are likely the correct test.
Aligning theoretical framework, gathering articles, synthesizing gaps, articulating a clear methodology and data plan, and writing about the theoretical and practical implications of your research are part of our comprehensive dissertation editing services.
Level of Measurement
The level of measurement is the second factor used in selecting the correct statistical test. If the research question will examine the impact of X on Y variable, and that outcome variable Y is scale, a linear regression is the correct test. For example, what is the impact of Income on Savings (as a scale variable), the linear regression is the test. If that outcome variable Y is ordinal, then an ordinal regression is the correct test (e.g., what is the impact of Income on Savings (with Savings as an ordinal $0-$100, $101-$1000, $1001-$10,000, variable), then an ordinal regression is the correct test. If the research question examines relationships, and the X and Y variable are categorical, then chi-square is the appropriate test. The main point is that both the phasing of the research question and the level of measurement of the variables dictate the selection of the test. This video on decision trees may be useful.
Statistical Assumptions in Data Analysis Plan
Part of the data analysis plan is to document the assumptions of a particular statistical test. Most assumptions fall into the normality, homogeneity of variance, and outlier bucket of assumptions. Other tests have additional assumptions. For example, in a linear regression with several predictors, the variance inflation factor needs to be assessed to determine that the predictors are not too highly correlated. This data analysis plan video may be helpful.
Composite Scores and Data Cleaning
Data analysis plans should discuss any reverse coding of the variables and the creation of composite or subscale scores. Before creating composite scores, alpha reliability should be planned to be examined. Data cleaning procedure should be documented. For example, the removal of outliers, transforming variables to meet normality assumption, etc.
Sample Size and Power Analysis
After selecting the appropriate statistical tests, data analysis plans should follow-up with a power analysis. The power analysis determines the sample size for a statistical test, given an alpha of .05, a given effect size (small, medium, or large) at a power of .80 (that is, an 80% chance of detecting differences or relationships if in fact difference are present in the data. This power analysis video may be helpful.