> For the complete documentation index, see [llms.txt](https://ailyze.gitbook.io/ailyze-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ailyze.gitbook.io/ailyze-docs/methods-and-best-practices/choosing-the-right-analysis-approach.md).

# Choosing the Right Analysis Approach

This page helps you make Evidano's handful of high-stakes choices correctly the first time — so you land on the right workflow, report structure, and theme strategy for your project.

Evidano asks a few questions that shape everything downstream. Think of this page as the decision tree.

## Decision 1: Which workflow fits your data?

| Your data                       | Workflow                                                 |
| ------------------------------- | -------------------------------------------------------- |
| Documents (one item per file)   | **"Analyze docx/pdf files"**                             |
| Spreadsheet (rows of responses) | **"Analyze xlsx/csv files"**                             |
| Audio or video                  | Transcribe first, then analyze the documents             |
| Live web content                | Collect first, then analyze the spreadsheet or documents |

Not sure which button to press? See [Choose your workflow](/ailyze-docs/getting-started/choose-your-workflow.md).

## Decision 2: Whole survey, or selected columns?

This is the biggest spreadsheet choice:

* **Whole survey (all columns)** — analyze the *whole survey*. You get an **Overall** dashboard (every question summarized) *plus* a deep thematic project for each open-ended column. Pick this for survey reports and cross-tabs.
* **Selected columns only** — deeply code *specific* open-ended questions. Pick this for focused content analysis, such as one "Why did you cancel?" field.

{% hint style="info" %}
Rule of thumb: reporting on the whole **survey** → all columns; mining one **question** → selected columns.
{% endhint %}

## Decision 3: Which report structure? (documents)

| Structure                                | Each section is                    | Choose when                                        |
| ---------------------------------------- | ---------------------------------- | -------------------------------------------------- |
| **"Themes + linked research questions"** | a theme tied to a question         | Academic; you want themes mapped to your questions |
| **"Questions only"**                     | a question                         | Industry; you want answers per question            |
| **"Themes only"**                        | a theme                            | Pure exploratory coding                            |
| **"Questions + themes"**                 | a theme *or* a question (separate) | You need both deliverables                         |

A [theme](/ailyze-docs/reference/glossary.md#theme) is a top-level pattern in your data; a research question is one you set out to answer. Evidano labels two of these cards **"Preferred for academic use cases"** and **"Preferred for industry use cases"** — use those hints.

## Decision 4: Let Evidano suggest themes, or supply your own?

You can let Evidano read your data and suggest themes for you, or you can give it your own list of themes to apply. (Researchers call the first approach [inductive](/ailyze-docs/reference/glossary.md#inductive-coding) and the second [deductive](/ailyze-docs/reference/glossary.md#deductive-coding) — but you won't see those words anywhere in the app.)

| What you want                      | What to do                                                                                 |
| ---------------------------------- | ------------------------------------------------------------------------------------------ |
| Explore, with no fixed list        | Choose **"Use AI to Identify top themes and sub-themes"**                                  |
| Apply a framework you already have | Choose **"Use my own themes and sub-themes"** and type or paste it in                      |
| A bit of both                      | Let Evidano suggest, then edit the [codebook](/ailyze-docs/reference/glossary.md#codebook) |
| The same themes across studies     | Reuse a previous codebook with **"Use Previous"**                                          |

More on this: [Discover themes and patterns](/ailyze-docs/analyze-data/discover-themes-and-patterns.md).

## Decision 5: To segment, or not?

If you need to compare groups (department, region, plan, cohort, before/after), plan your [segments](/ailyze-docs/reference/glossary.md#segment) up front:

* Spreadsheets: put your grouping columns into **Segments** (the all-columns path).
* Documents: turn on **"Compare segments"** (needs multiple files or a focus group).

See [Compare groups](/ailyze-docs/analyze-data/compare-groups-segments.md).

## Decision 6: Name a methodology? (documents)

If your work must name a method (theses, publications), choose **"Include methodology"** and pick a [methodology](/ailyze-docs/reference/glossary.md#methodology) from Evidano's library (for example, Reflexive Thematic Analysis, IPA, or Grounded Theory). For applied work, you can **"Skip"** it.

## Putting it together: quick recipes

* **PhD interview study:** documents → *Themes + linked research questions* → include a methodology → let Evidano suggest themes, then curate the codebook → reuse it for later waves.
* **Customer feedback survey (NPS, a customer-loyalty score):** spreadsheet → all columns → segment by plan or channel → let Evidano suggest themes.
* **Single open-ended question:** spreadsheet → selected columns → let Evidano suggest themes, or use your own codebook.
* **Product reviews from the web:** collect → spreadsheet → selected columns on the review text → segment by rating or version.

## Next steps

* [Choose your workflow](/ailyze-docs/getting-started/choose-your-workflow.md)
* [Qualitative research best practices](/ailyze-docs/methods-and-best-practices/qualitative-research-best-practices.md)
* [Survey research best practices](/ailyze-docs/methods-and-best-practices/survey-research-best-practices.md)
* [How to read your results](/ailyze-docs/analyze-data/how-to-read-your-results.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ailyze.gitbook.io/ailyze-docs/methods-and-best-practices/choosing-the-right-analysis-approach.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.