RESEARCH DISCIPLINE
EdD Statistics Support
for Action Research and Improvement Cycles
For a Doctor of Education project built on your own school, district or program: local data analyzed with intervals that suit a small site, improvement cycles compared fairly, and tables that a committee can follow and a practitioner can use.
No Commitment Required
Strictly Confidential
In-House PhD-Level Statisticians
Fixed Project Fee
Same-Day Response
What Is Different About Analyzing EdD Data?
EdD statistics support serves a practitioner doctorate in which the data come from the researcher’s own setting: a school, a district office, a college unit or a training program. The sample is whoever the setting contains, so the analysis estimates what happened there, with intervals that show how little one site can settle, and does not claim to describe education in general. Cycles of change add a further layer, each with its own measures. Analysis at the scale of one setting is the work of OnlineSPSS, a specialist statistical consultancy for academic, clinical and professional research, whose in-house PhD-level statisticians fit each model to the number of people it holds. Naming the problem of practice and judging what the evidence means for the setting are the researcher’s own work.
WHEN TO ENGAGE
Cycles of Action and the Data Each Produces
A practitioner study runs through a proposal, one or more cycles of action and a final defense, and what it needs from statistics differs in each.
Problem of Practice Named The problem is defined and the measures are not yet chosen, so what can be measured at your site, how often and on how many people is settled against the question.
Baseline Data Collected Records, surveys or observation scores from before the change are in hand, and the analysis must show what they say, and how reliably, before any comparison is possible.
Cycle Results Back An intervention cycle is complete and its outcomes are in, and the comparison with the baseline or an earlier cycle must be made honestly for a small, non-random group.
Defense Approaching The findings chapter is drafted and a committee member has queried the sample size, the comparison or the claim about impact, so the response has to come from the data.
ANALYSIS FOR A SINGLE SITE
Statistics for School-Based and Program Data
The work follows the cycles of the study, with every comparison shown beside its interval and the number of people behind it.
Planning the Measures
An EdD dissertation analysis starts from the measures a site can sustain, with the respondents, the repeat measures and the comparison fixed in the plan.
Survey and Rating Data
Staff and family surveys are screened for response rate and nonresponse, items are scored by a stated rule, and results are reported by group with confidence intervals.
Comparing Cycles
Outcomes before and after a change, or across successive cycles, are compared within the same participants where they are the same and as separate groups where they are not.
Learners in Classrooms
Learners within classrooms share a teacher and conditions, so Linear Mixed Models (Multilevel Modeling) is considered, and with few classrooms the claim may stay at classroom level.
Cycle-by-Cycle Records
Action research data analysis keeps each cycle's measures, numbers and decisions on one record, so a reader can see what changed between cycles and why.
Reporting for Education
Findings follow the conventions of Education research and the learning questions of Educational Psychology, within Education & Social Sciences.
SINGLE-SITE RISKS
Limits That a Practitioner Study Must Acknowledge
A practitioner is close to the data, which is an advantage for meaning and a hazard for inference, and each risk below is handled in the analysis itself.
New Test Form, Apparent Gain A rise in scores is read as progress although the assessment form, its cut scores or the cohort taking it changed between the baseline and the later cycle.
Volunteers as Comparison Teachers or classes who volunteered are compared with those who did not, though the volunteers may already differ in motivation, so the groups are not a fair test.
Few Classrooms, Many Learners Hundreds of learners from four classrooms are analyzed as independent observations, which overstates precision when learners in a class resemble one another.
Attrition Between Cycles Participants who leave or skip the later survey are dropped, so the later cycle describes a more stable group than the first, and comparing it with the full baseline group can overstate the gain.
Responses to a Known Researcher Colleagues or learners answer a survey run by their own principal or teacher, and their answers may lean favorable, so anonymity and the response rate are reported.
Benchmark Without Interval Results are set against a state benchmark with no interval or comparison group, so a reader cannot tell a real change from ordinary year-to-year variation.
DELIVERABLES
Materials That Serve the Committee and the Site
The same results are documented twice, in the detail a committee examines and in a form the school or program can act on.
Measures and Sampling Plan A plan for each measure, the people who provide it, the timing across cycles and the comparisons to be made, fixed before data are collected.
Scored Data and Codebook The cleaned dataset with a codebook of scoring rules, missing-value codes and exclusions, each recorded with the reason it was applied.
Cycle Comparison Tables Outcomes for each cycle with 95% confidence intervals and the number of participants behind every estimate, set side by side.
Scale Scoring Summary For each scale, how it was scored and how consistent it was in your sample, with the interval for that estimate.
Practitioner Summary Sheet A one-page statement of the findings in plain terms for the school or program, with the uncertainty shown and the limits of a single site named.
Cycle-by-Cycle Script An annotated script, organized by cycle, that rebuilds every table from the source records.
ILLUSTRATIVE EXAMPLE
An Attendance Outreach Cycle at One Middle School
An illustration of how an improvement cycle on a non-test outcome is read against several months of baseline data.
ILLUSTRATIVE EXAMPLE · LEARNER ATTENDANCE ACTION RESEARCH · UNITED STATES
An EdD candidate who worked as a school counselor started family outreach for learners with frequent absences and wanted to know whether the share of learners who were chronically absent changed during the first outreach cycle.
The plan fixed the outcome and the comparison before the cycle began: the proportion of learners chronically absent in each month, with six months of baseline records and the same months of the previous year as a reference. The complication was the record itself. Absences are higher in winter whatever the school does, and the district changed how excused absences were coded midway through the baseline. The analysis recoded the earlier months to the new rule, checked how much the result depended on that choice, and set the cycle months beside the same months a year earlier, with an interval for each monthly proportion. With so few time points no fitted trend break was claimed. The change was described as what was observed after the outreach began, not as the effect of the outreach.
Outcome: The candidate received the measures plan, the monthly attendance series with 95% confidence intervals across baseline and cycle, the comparison with the previous year, a note on the coding change with its sensitivity check, the practitioner summary sheet and the script.
This example does not describe a real client or project. We never share details of actual client work, in line with the confidentiality we promise every researcher. This illustrative example is included to show the type, scope, and standard of work involved in this kind of analysis.
SOFTWARE
Software Matched to School and Program Records
Local data come as spreadsheets, survey exports and district files, and a committee member who wants to rerun a table should be able to open the file it came from.
HOW WE ASSESS YOUR PROJECT
We Review Your Actual Research
Your assessment is based on a review of your actual research materials and analytical requirements, not a generic project category.
You Submit Your Project Details
Share whatever is available at the current stage, such as the research aim, protocol or proposal, dataset, variable list, manuscript or statistical requirements.
We Review Your Research and Define the Scope
Your statistically trained Research Coordinator reviews the materials to understand the study design, research questions, data structure, analytical requirements and expected deliverables. If clarification is needed, additional documents or information can be requested before the assessment is finalized.
Your Analysis Is Completed and Delivered
Once the scope and fixed project fee are agreed, the in-house statistician completes the work and the Research Coordinator remains the communication point through delivery, with the analysis, deliverables and timeline as agreed.
RESEARCH RESPONSIBILITY
The Next Cycle Is Planned Locally
Choosing the problem, designing the cycles and deciding what to change belong to the practitioner-researcher, and the estimates inform those decisions without making them.
Agreed Statistical Support OnlineSPSS provides the agreed methodological, analytical and statistical reporting support, defined in a scope that is confirmed before any work begins.
No Intellectual Contribution OnlineSPSS does not claim any intellectual contribution to your research. Authorship of the dissertation in practice, report or article remains yours.
Your Research Decisions The problem of practice, the design of each cycle, the interpretation of the findings for your setting and the conclusions remain yours, with overall responsibility.
Confidential Handling Research data and project details are handled confidentially, project information is not published, and an NDA is available where required.
FREQUENTLY ASKED QUESTIONS
Single-Site Data, Cycles and Committee Questions
District records, a change that reached every class and findings meant for fellow practitioners are where EdD analyses differ most from a conventional dissertation.
Where does statistics fit in an EdD study?
EdD statistics support covers the quantitative side of a practitioner doctorate: the plan for measures and sample, the cleaning and scoring of local data, comparisons across cycles or groups with confidence intervals, and the tables for the dissertation. Interviews or journals from the same cycles can be analyzed alongside the numbers when the agreed scope includes them.
Can school or district records serve as EdD data?
Often, and many practitioner studies rely on them. Records kept for administration were not designed for the research question, so definitions such as attendance or course completion are checked for changes across years, small groups are reported with care because a few learners may be identifiable, and permissions and data agreements remain the researcher’s to obtain.
How is a comparison made when the intervention reached every class?
With no concurrent comparison group, the options are earlier cohorts, several baseline measurements that show the trend before the change, or staggered start dates across classrooms. Each rules out some alternative explanations and not others, so the report states which ones remain, and the conclusion is worded as what was observed after the change.
How should a result from my own site be reported so that it is useful to practitioners?
The estimate and its interval are given in the units of the outcome, such as points on the assessment, and set against a difference that would matter in practice, named before the analysis. The characteristics of the setting and the learners are described so that another practitioner can judge whether the result might transfer.
How do you protect my research data and confidentiality?
Your data and project details are handled confidentially, and project information is not published. Researcher names and institutions are not used publicly without permission. An NDA is available where required and can be arranged before sensitive materials are shared. Read more about confidentiality and data security.
What happens when I request an assessment, and how long does it take?
You share your research question, design and relevant materials, such as the problem-of-practice statement, the measures, the data file and the plan for your cycles, and a statistically trained Research Coordinator reviews the request and responds the same day. The analysis, deliverables, timeline and one fixed project fee are then confirmed before any work begins, so the timeline follows from the agreed scope.
Still have a question? Find more answers in our full FAQ.
NEXT STEP
Data From One Site
Deserve Honest Intervals
A single school, district office or program can answer a local question well when each estimate shows how few people stand behind it, and the analysis is planned around that fact.
No Commitment Required
Strictly Confidential
Fixed Project Fee
In-House PhD-Level Statisticians
Same-Day Response
Serving Researchers Since 2014