QuickPLS Match your task to the file and guide
For a first PLS analysis, choose customer-experience.csv and the 240-case PLS lesson. For an NCA result you can compare with checked answers, choose innovation-necessity.csv. For a first fsQCA analysis, use memberships.csv or open the Guided fsQCA study project.
The map distinguishes a CSV, which supplies data only, from a .qpls project, which also contains saved specifications and results. Row counts describe source datasets, not necessarily the cases included in a particular calculation. Where a project contains several datasets, their counts are listed separately rather than added together.
The fsQCA practice pack contains the 15 files listed in its manifest: six saved projects and nine CSVs. The customer, innovation and delivery files are separate exercises in the practice-answer archive. Its settings JSON is a readable setup record, not an importable project.
Download and extract an archive before opening its files. Keep the original and work in a copy. The six fsQCA projects preserve synthetic teaching results created in QuickPLS 1.03.07; they have not been recalculated for this website.
On a small screen, swipe the table sideways to see every column.
| Task | Filename | Source rows | Open or import | Guide and answer source |
|---|---|---|---|---|
| Fit the first customer model | customer-experience.csv | 240 | Import CSV | PLS-SEM: checked customer-model point estimates |
| Interpret a capability bottleneck | innovation-necessity.csv | 180 | Import CSV | NCA: checked innovation results |
| Check a paper-linked set solution | delivery-memberships.csv | 10 | Import CSV | Delivery reference answers; separate d-case exercise |
| Calculate the first fsQCA truth table | memberships.csv | 10 | Import CSV | fsQCA: membership walkthrough and worked answers |
| Inspect the saved first fsQCA study | fsqca_guided_study.qpls | 10 in each dataset | Open saved project | fsQCA: membership walkthrough; separate raw-score calibration |
| Calibrate raw condition scores | raw-scores.csv | 10 | Import CSV | Calibration methods; compare the saved raw-score example |
| Compare outcome presence and absence | fsqca_comparisons_robustness.qpls | 10 | Open saved project | Outcome asymmetry and robustness: saved comparison results |
| Examine assumptions about unobserved combinations | counterfactual.csv | 2 | Import CSV | Counterfactuals: worked condition combinations |
| Check an observed combination with a missing outcome | counterfactual-conflict.csv | 3 | Import CSV | Counterfactuals: the conflicting-observation exercise |
| Inspect saved counterfactual, necessity and calibration studies | fsqca_research_choices.qpls | 2, 4 and 6 in separate datasets | Open saved project | Counterfactuals, compound necessity and calibration: saved examples |
| Evaluate OR, AND and NOT requirements | necessity.csv | 4 | Import CSV | Compound necessity: hand-checkable memberships |
| Compare definitions of set membership | calibration.csv | 6 | Import CSV | Calibration methods: worked assignments |
| Map nominal categories | categories.csv | 6 | Import CSV | Multi-value QCA: worked category combinations |
| Inspect the saved category mapping | fsqca_multivalue.qpls | 6 | Open saved project | Multi-value QCA: saved mapping and result |
| Prepare time-dependent conditions or inspect panel fit | panel-time.csv | 9 | Import CSV | Temporal QCA and panel set fit: worked observations |
| Inspect the saved temporal and panel analyses | fsqca_temporal_panel.qpls | 9 in each dataset | Open saved project | Temporal QCA and panel set fit: saved results |
| Compare outcomes or check crisp-set formulas | crisp-outcomes.csv | 10 | Import CSV | Multiple outcomes, CNA and exact binomial QCA |
| Inspect the saved multiple-outcome and crisp-set analyses | fsqca_multiple_outcomes_cna.qpls | 10 | Open saved project | Multiple outcomes, CNA and exact binomial QCA: saved results |
- Start the PLS lesson with checked answers
- Download the fsQCA practice pack: 6 projects and 9 CSVs
- Download the file list and file fingerprints (JSON)
- PLS-SEM: checked customer-model point estimates
- NCA: checked innovation results
- Delivery reference answers
- fsQCA: membership walkthrough and worked answers
- Calibration methods
- Outcome asymmetry
- Robustness
- Counterfactuals
- Compound necessity
- Multi-value QCA
- Temporal QCA
- Panel set fit
- Multiple outcomes
- CNA
- Exact binomial QCA
- Download the three separate exercises, settings and checked answers
Open one of six saved fsQCA projects
Choose a project to inspect its saved specification and result before attempting a fresh calculation. The Guided fsQCA project includes raw-scores.csv, memberships.csv and a calibrated version of the raw scores, each with 10 rows. Select the dataset named in the guide.
The Research choices and calibration project holds separate 2-case, 4-case and 6-case exercises. The Temporal and panel project contains the 9-row source and its generated teaching columns. These are separate datasets, not additional independent observations to combine.
The last column below counts saved calculations. Read the selected result's settings and case decisions before comparing its numbers with another analysis.
Download and open a saved project
Choose one .qpls download below. In QuickPLS, use File → Open Project… (Ctrl+O) and select that file. A saved project includes the datasets, specifications and calculations described in the guide.
Select the exercise within the project
Use the task-to-file map and the guide to identify the intended dataset and named specification. Read its existing result before calculating. Do not combine the separate datasets or treat the saved-calculation count as a case count.
Make a working copy before revising it
Use File → Save Project Copy… to keep the downloaded original. In the working copy, give a revised specification a clear name and keep the original result available for comparison.
On a small screen, swipe the table sideways to see every column.
| Project | What you can practise | Saved calculations |
|---|---|---|
| Guided fsQCA study | Follow calibration and case decisions through to a saved solution. | 2 |
| Outcomes and robustness | Compare outcome presence with absence and test alternative analysis choices. | 5 |
| Research choices and calibration | Explore assumptions, compound necessity and calibration choices. | 7 |
| Multi-value categories | Define categories and read a multi-value truth table. | 1 |
| Temporal and panel diagnostics | Prepare time-based variables and compare fit across groups or periods. | 3 |
| Multiple outcomes, CNA and crisp checks | Compare separate outcomes, inspect CNA and run crisp-set checks. | 5 |
Use a small data file to practise the setup yourself
Import a CSV when you want to perform the setup yourself. It contains neither a model nor a saved calculation. The files below are the nine data-only exercises in the fsQCA practice pack; use the guide named in the map above.
For the main fsQCA walkthrough, memberships.csv supplies ten cases with existing memberships. Apply the guide's explicit missing-value and crossover decisions before comparing its answers. raw-scores.csv instead teaches calibration. delivery-memberships.csv is another separate exercise, with d-case identifiers and independently checked reference answers; it is not the m-case file used in the main walkthrough.
Choose the file and its guide
Use the task-to-file map above. Download the named CSV and open its matching guide. Note the expected case count and whether the file contains raw scores, existing memberships, categories or unit-and-time records.
Open the import preview
In a writable project, choose File → Import Data… (Ctrl+I), then Choose data file… and select the CSV. In Review & import, check Header row, the separator and Decimal convention against the file. Check column names and values in the preview.
Import and confirm the cases
Click Import dataset and confirm Dataset imported and verified. Compare the imported count with the Cases column below. Follow the exercise guide for variable roles and missing-value decisions; importing the data does not create the study specification or calculation.
Continue with the specified exercise
For memberships.csv, follow the main fsQCA baseline linked below and apply its recorded missing-value and crossover exclusions before comparing answers. Use the calibration guide for raw-scores.csv. Keep delivery-memberships.csv and its d-case reference answers separate from the m-case walkthrough.
On a small screen, swipe the table sideways to see every column.
| File | Cases | Exercise |
|---|---|---|
| memberships.csv | 10 | Practise a truth table with pre-calibrated memberships; the guide explains which rows to exclude. |
| raw-scores.csv | 10 | Convert raw measurements into set membership using the exercise’s calibration anchors. |
| counterfactual.csv | 2 | Explore assumptions about combinations that are absent from a two-case example. |
| counterfactual-conflict.csv | 3 | Understand why a missing outcome does not make a recorded combination impossible. |
| necessity.csv | 4 | Named OR, AND and NOT hypotheses with hand-checkable fuzzy memberships. |
| calibration.csv | 6 | Crisp, piecewise, bell/valley and indirect assignment exercises. |
| categories.csv | 6 | Explicit nominal condition/outcome category mappings. |
| panel-time.csv | 9 | Prepare three units across three periods; sort the deliberately unordered rows correctly. |
| crisp-outcomes.csv | 10 | Compare an outcome with its opposite and practise crisp-set and CNA checks. |
- Download the set-membership exercise (CSV)
- Download the raw-score exercise (CSV)
- Download the counterfactual exercise (CSV)
- Download the conflicting-configuration exercise (CSV)
- Download the compound-necessity exercise (CSV)
- Download the calibration exercise (CSV)
- Download the nominal-category exercise (CSV)
- Download the unit-and-time exercise (CSV)
- Download the crisp-outcome exercise (CSV)
- Create a writable project and practise importing
- Continue the memberships.csv baseline
Change one choice and explain the difference
Read the original settings and result first. Save a separate named specification, change one justified choice and calculate it. Compare the included cases, truth-table decisions and solution alternatives. Keep the original result available so you can see what changed.
Follow the exercise's stated rule for a missing answer or a membership exactly at the crossover, 0.5. Do not silently replace the value. If a solution changes, go back to the affected cases and explain why.
Which data and screenshots belong to your exercise?
The manifest records filenames, CSV row counts, columns and file hashes. A hash identifies the exact bytes of a file. The project rows in the map also use the dataset counts recorded inside each saved project.
The practice-answer archive contains results calculated by QuickPLS code outside the desktop app, with independent reference checks for the customer PLS and innovation NCA exercises. The delivery fsQCA exercise has reference answers only; that file was not calculated in QuickPLS for the archive. The archive does not document new runs of the Microsoft Store app.
Read each screenshot's example description before comparing values. The paper tutorials supply their own synthetic practice data, not automatically the original data from the cited paper.
Build a model and write up the findings
These longer workshops take you from preparing data to interpreting a result and writing a short report. Start with the complete file. Use the missing-data and data-entry challenges as separate exercises so you can return to the original data.
The 360-case research workshop uses Quality, Trust, Satisfaction and Loyalty, each with three named indicators. Draw Quality → Satisfaction, Trust → Satisfaction and Satisfaction → Loyalty. Other columns support group and weighted analyses. Read the variable guide before assigning them: a case weight or group code is not another questionnaire indicator.
The 120-case observed-variable workshop uses x, z, m and y for regression and mediation, with a separate binary outcome. Its reference downloads contain independent calculations for regression, logistic regression and unrotated PCA. Match the variables, cases and calculation definitions before comparing your app results with those references.
The first PLS lesson uses the separate 240-case customer-experience file. Choose one exercise and follow its own instructions and answer table. The same construct names in two files do not make their results interchangeable.
Choose what you want to learn next
Choose a goal from the table, then follow the linked method guide. Finish by explaining one result in your own words and locating the saved calculation that produced it.
If your answer differs from the guide, compare the file, included cases, variable assignments and settings first. A weak but valid finding is something to interpret, not a reason to keep changing the data until a test passes.
On a small screen, swipe the table sideways to see every column.
| What you want to learn | Start with | What you should be able to explain |
|---|---|---|
| Build and assess a construct model | The research workshop and PLS-SEM or CB-SEM guide. | Your indicator assignments, proposed paths, measurement checks and main estimates. |
| Interpret uncertainty | A saved model, then its matching bootstrap guide. | The estimate, confidence interval, test direction and usable resample count. |
| Explain an indirect relationship | The mediation guide and the stated model for the selected exercise. | Direct, specific indirect and total effects, their uncertainty and the assumptions behind the interpretation. |
| Compare prediction | Two compatible models using the same research-workshop cases and outcomes. | Which observations were tested, the baseline used and how errors differ for each outcome. |
| Investigate data quality | The complete observed-variable file and its separate challenge. | Which entries were wrong, how the source established the correction and how the result changed. |
| Analyse sets and combinations | The existing fsQCA practice projects and their matching CSVs above. | Calibration, truth-table choices, solution alternatives, consistency, coverage and the cases behind the finding. |