How one early design mismatch spreads across the whole study 1. Why these mistakes belong together Some research mistakes arrive alone. This cluster does not. When the research question, hypothesis, and variables do not align, the problem is rarely isolated to one sentence in the…
Author: Zlatko Kovačić
Director of Wellington based My Statistical Consultant Ltd company. Retired Associate Professor in Statistics.
Has a PhD in Statistics and over 35 years experience as a university professor, international researcher and government consultant.
When the Research Question Is Too Broad, Vague, or Overloaded
The upstream design mistake that quietly destabilizes the rest of the study Opening: the first mistake often happens before the study really begins Many weak empirical studies do not begin with a bad dataset or an inappropriate analytic technique. They begin with a research question…
Why Smart Research Still Goes Wrong
A new mini-series on the design mistakes that quietly undermine quantitative, qualitative, and mixed methods studies Why this series? Many research projects do not fail because researchers are careless, unintelligent, or unfamiliar with statistical software. They fail much earlier and much more quietly: at the…
Why Linear Mixed Models Are Usually the Better Choice for Pre–Post Experimental and Control Group Data
A student’s proposal, and a familiar methodological problem A student recently contacted me with a thesis proposal built around a very common design: one experimental group, one control group, and two measurements for each participant, one before and one after the intervention. The student proposed…
Education Research by Design: Questions, Hypotheses, Data, and Methods
This is the first post in a new mini-series on RQ–RH–D–M across fields. The purpose of the series is to give readers a compact, practical toolkit showing how research questions (RQ), research hypotheses (RH) or working propositions, data (D), and methodology (M) can be aligned…
The Research Tetrad: Why Consistency Between Questions, Hypotheses, Data, and Methodology Is Everything
Intuitive introduction to the problem This is Part IV in the blog series on research design foundations. The earlier posts focused on research questions and research hypotheses across quantitative, qualitative, and mixed methods designs. This post takes the next natural step: it explains why those…
Research Questions That Actually Work, Part III: How to Write a Good Mixed Methods Research Question
From parallel strands to an integrated research design This is the third post in the series Research Questions That Actually Work. The first post focused on quantitative research questions and the discipline of measurable design. The second examined qualitative research questions and the logic of…
Research Questions That Actually Work, Part II: How to Write a Good Qualitative Research Question
From broad curiosity to meaningful and interpretable inquiry This is the second post in the series Research Questions That Actually Work. The first post examined quantitative research questions and the logic of measurable, answerable design. This post turns to qualitative research questions, where the central…
Research Questions That Actually Work, Part I: How to Write a Good Quantitative Research Question
From broad interest to measurable, answerable design Many weak empirical studies do not fail because the software is wrong or the regression is badly coded. They fail earlier, when a broad topic is mistaken for a quantitative research question. A student says, “I want to…
Using Sample Size Calculator application
The following video tutorial gives a brief overview of the Sample Size Calculator application. The Sample Size Calculator is an interactive Shiny application which allows you to calculate sample size when estimating population mean value or population proportion. [su_youtube_advanced url=”https://www.youtube.com/watch?v=7juKRR-Kahs” rel=”no”]