Fracture types that were excluded were Smith or Barton volarly displaced fractures, severely comminuted fractures extending into the diaphysis, multiple extremity fractures, and fractures requiring open surgical reduction or bone grafting. It is important that you describe clearly and concisely the process by which you identified and recruited your subjects and whether they finished the study.
You were able to obtain full accountability of all your subjects. To illustrate this in your manuscript you provide a schematic summary of the study showing the number and disposition of participants at each stage, Figure 9. The schematic summary includes You then describe the nature and duration of your follow-up effort.
This comes directly from your protocol. For example, you may state something like this:. A research nurse from each site approached each potential subject to inquire about their interest and eligibility in volunteering for this study.
This inquiry included a series of questions to confirm eligibility, a description of the study, its importance in orthopedic patient care, the responsibilities for participating, and the potential benefits of participating.
Study aids focused for study education and support included a patient information booklet and a toll free telephone number for advice in case of complications or questions regarding follow up visits.
Patients were followed immediately after injury to 12 months after initial management. This included a baseline evaluation and planned visits at 3, 6, and 9 weeks, and 3, 6, and 12 months after injury. Patients received telephone reminders for upcoming study visits no less frequently than once every two months. Study data was entered during the course of the study from the CRF to a secure central database through an internet portal.
Data entry was validated i. Monitoring of the study occurred regularly both remotely and through site visits. This included ensuring all CRFs were completed without missing data, that CRFs matched source documentation, and that all scheduled and unscheduled visits were documented.
The following prognostic variables were identified in the Trauma registry and verified by the patient baseline questionnaire: Furthermore, the following short term outcome measures were obtained from the Trauma Registry: Lastly, we provided in the study packet the following generic and disease specific patient reported outcomes that the patients were instructed in over the phone and by written instruction in the study packet: SF Composed of 8 subscales measuring physical and mental health 36 items.
For each subscale, scores range from 0 to points. The higher the score the higher the function. Scores are normalized and range from 0 to points.
The higher the score, the higher the function. In a real scenario, you might consider putting more detail in the schematic. For example, you may include the number of patients who received external fixation or Kirschner wires. As best as you could account for them, you documented reasons for ineligibility, unwillingness to participate, and loss to follow-up or withdrawal. For continuous variables, means and standard deviations were computed.
In addition, minimum, maximum, and range will be reported for both types of variables. Missing, extreme, and variable distributions were explored. For primary aims, the differences in PRWE scores between injectable cement and standard of care groups were tested first with t-tests and then with analysis of variance ANOVA to control for potential confounding variables.
Another primary aim was to develop and validate a prediction rule. Developing prediction models can be very complicated statistically. Teaching the principles is beyond the scope of this module. However, a possible explanation for this process could be the following:.
The optimal point at which to dichotomize the outcome was chosen by running a series of logistic regression analyses to identify the dichotomous variables possessing the most explanatory power. In the end, the data was normally distributed so we dichotomized each score at the mean value. We felt the mean scores represented pain and activities of daily living scores that were functional and satisfactory.
The other two outcomes that we attempted to predict were malunion and redisplacement. We first estimated the association between each prognostic factor and each outcome bivariate analysis. The initial multivariate model included all candidate predictors. Final models were determined by prognostic factors that accounted for the majority of the variance R2 value.
Statistical assumptions were verified graphically. Models were examined to determine if multicollinearity was present using condition number and variance inflation factors. Furthermore, outliers and influential values were identified using studentized residuals and Cook distances. A modified bootstrap approach random sampling with replacement was used to obtain several internal validation samples. The overall prediction model was applied to these samples and a coefficient of determination R2 was calculated as an indicator of the performance of the proposed prediction model.
For secondary aims, the differences in SF scores, mean time to union, and mean time to return to previous work between injectable cement and standard of care groups were tested first with t-tests and then with analysis of variance ANOVA to control for potential confounding variables. We exceeded this number through rigorous follow-up methods.
Your results section should be quick and to the point. In other words, there should not be too much explaining or justifying your findings. This is left for your discussion.
The flow of the results section should begin with descriptive statistics of study groups, findings with respect to measured risk factors or outcomes analytical statistics and accompanying tables and figures as necessary. A table reporting descriptive or baseline characteristics is typically the first table in your report or manuscript.
The following table is a hypothetical example of your baseline data, Table There are other prognostic and demographic factors that you may or may not choose to include in this table. From this table, we note that the random allocation process worked like it should have, providing a nearly equal distribution of potentially confounding factors. You will want to describe this table in the next. Had there been an unequal distribution of a factor that was also associated with one of your outcomes, you would need to control for this variable in your analysis.
A discussion of potential confounding can be found in Part 2 of the didactic module section 5. You proceed with your analysis of the primary outcomes. Below, you generate a table that compares PRWE scores between the two groups at different time intervals, Table You present 3 and 12 month follow-ups; however, you have data from 9 weeks and 6 months as well that you could include in the table.
Note, from your table above, that the differences in PRWE scores are statistically significant at both follow-up times 3 and 12 months. Both groups demonstrate relatively low scores, which represent relatively high function especially at 12 months.
The differences are clinically significant [ Part 4; section The magnitude of the difference is greatest at 3 months. Though you do not suspect that these differences will be confounded due to an unequal distribution of potential confounders, you run an analysis of variance ANOVA regression and add several prognostic variables to the model.
The following is a table that you present reporting the comparison of rates of your other primary outcomes, Table If you divide the two percentages you get what is called a relative risk RR [ Part 4; section You can calculate a confidence interval for this relative risk by using your statistical program.
You do so and get a range from 1. Note, that this confidence interval does not include 1. Finally, briefly outline what is contained in the rest of the report. Create four sections in the body of the report: Data, Methods, Analysis and Results.
In some situations it may be preferable to combine the Methods section with the Analysis section. If your report contains more than one set of data with independent analysis, repeat these four sections as often as needed. Write a description of the most important data used for analysis in the Data section.
Copy the spreadsheets containing your data and paste these after your written description. In Microsoft Office, simply highlight the cells, copy them, and then paste them into the Word document. Write down the methods you used to gather the data and analysis in the Methods section. Write down your analysis of the data in the Analysis section. Include in this section what was analyzed and the conclusions you made from the analysis.
Insert any charts you created from the data in this section. Create a Conclusions section. Restate the questions you raised in the Introduction, as well as the most relevant results from the analysis. If your report contains more than one set of data or analysis, this is the place to compare the different results as needed. Include any questions or recommendations for additional data as needed.
Include a last Appendix or Appendices section, if needed. If you have hundreds of pages of data, it may be preferable to put it in the appendix rather than in the Data section of the report. Insert any secondary data mentioned in the report in the Appendix, including a reference indicating where the data came from. A published author and professional speaker, David Weedmark has advised businesses and governments on technology, media and marketing for more than 20 years.
He has taught computer science at Algonquin College, has started three successful businesses, and has written hundreds of articles for newspapers and magazines throughout Canada and the United States.
Skip to main content. Writing the Report 1. References 3 Carnegie Mellon University: Writing a Laboratory Report:
What You Need to Write a Data Analysis Report. To write a data analysis report, you need a spreadsheet program to sort your findings and Word or a comparable document-writing program. For a data analysis report, ensure all of your information has been triple-checked for accuracy and that the methods of discovery are comparable to the subject matter.
Writing a data analysis report can seem like more of an art than a science, but there is a framework within which to do it effectively. It doesn’t matter how good the analysis actually is if you don’t write in an easy to read manner. A good data report should be easy to read and free from jargon.
The data analysis report isn’t quite like a research paper or term paper in a class, nor like aresearch article in a journal. It is meant, primarily, to start an organized conversation between you and your client/collaborator. Start by Writing It Right Away. Don’t expect that it will be perfect on the first draft. When you start writing your report, this is all that you should do: write your report. Put into words everything that you know about your data without being concerned of .
Data Analysis Plan Templates Statistics Solutions provides a data analysis plan template based on your selected analysis. You can use this template to develop the data analysis section of your dissertation or research proposal. Write down your analysis of the data in the Analysis section. Include in this section what was analyzed and the conclusions you made from the analysis. Insert any charts you created from the data.