メニュー
Interpret quantitative and qualitative findings for Discussion sections. Explain results, relate to literature, and discuss implications.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Write academic abstracts for thesis, journal articles, and conference papers. Follow IMRAD or structured formats with appropriate length.
Guide for quantitative, qualitative, and mixed methods data analysis. Statistical test selection, interpretation, and tool recommendations (SPSS, R, Python).
Check research ethics compliance for human subjects research. Covers consent, confidentiality, risk assessment, and approval requirements.
Academic proofreading for grammar, style, and consistency. Fix common errors while maintaining formal academic tone.
Select and justify research methodology. Compare approaches, choose designs, and write methodology chapters for thesis and research proposals.
Pre-submission checklist for thesis, journal articles, and conference papers. Format verification, requirement compliance, and final polishing.
| name | results-interpreter |
| version | 1.0.0 |
| description | Interpret quantitative and qualitative findings for Discussion sections. Explain results, relate to literature, and discuss implications. |
| allowed-tools | ["Read","Write","Edit"] |
Interpret findings untuk Discussion section. Explain results, relate to literature, dan discuss implications.
Summary of Key Findings
Interpretation of Results
Relation to Literature
Theoretical Implications
Practical Implications
Limitations
Future Research
Conclusion
This study examined [research question]. The main findings were:
(1) [finding 1], (2) [finding 2], and (3) [finding 3]. These results
[support/challenge/extend] existing understanding of [topic].
This study examined the impact of AI-assisted tutoring on mathematics
achievement among Malaysian primary students. The main findings were:
(1) students using AI tutoring scored significantly higher than controls,
(2) the effect was larger for students with lower baseline achievement,
and (3) students reported positive attitudes toward AI integration.
These results extend previous research by demonstrating effectiveness
in a developing country context.
For significant results:
The significant difference in [variable] between [groups] suggests
that [intervention/feature] [mechanism]. This aligns with [theory],
which posits that [explanation].
For non-significant results:
The absence of a significant effect may be attributed to [explanation].
Alternatively, [alternative explanation]. This finding contrasts with
[previous study], possibly due to [methodological difference].
| Finding | Possible Interpretation |
|---|---|
| Unexpected positive result | Ceiling effect, sampling bias |
| No effect found | Insufficient power, wrong population |
| Mixed results | Complex phenomenon, moderating variables |
| Large effect size | Strong intervention, homogeneous sample |
These findings are consistent with Smith (2020), who reported
[similar finding] in [context]. This convergence across [different
contexts/samples/methods] strengthens confidence in [conclusion].
However, these results contrast with Chen (2021), who found [opposite].
This discrepancy may be explained by [methodological/theoretical/contextual
difference]. While Chen studied [population/method], the present research
examined [different approach], suggesting that [nuanced understanding].
This study extends the work of [author] by demonstrating [new finding]
in [new context/population]. Previous research focused on [limited scope];
this study shows [broader application].
| Situation | Phrases |
|---|---|
| Agreement | "These findings corroborate...", "consistent with...", "support the work of..." |
| Partial agreement | "While X found..., this study...", "largely consistent with..." |
| Disagreement | "In contrast to...", "diverges from...", "challenges the assumption..." |
| Extension | "extends...", "builds upon...", "adds to the growing body..." |
These findings have implications for [theory/framework].
Specifically, [result] supports the proposition that [theoretical claim].
This suggests that [theory] may be [applicable/limited] in [context].
These findings have implications for Cognitive Load Theory (Sweller, 2011).
The improved performance in the AI tutoring group supports the proposition
that individualized instruction reduces extraneous cognitive load. This
suggests that AI-adaptive systems may operationalize cognitive load
principles more effectively than traditional one-size-fits-all approaches.
These findings suggest that [practitioners] should consider [recommendation].
Specifically, [specific action] may [expected outcome]. This has particular
relevance for [specific contexts/situations].
From a policy perspective, these results indicate that [policy recommendation].
Stakeholders should [action], particularly given [evidence from findings].
These findings suggest that educators should consider integrating AI tutoring
systems for mathematics instruction. Specifically, schools with limited
resources may benefit from AI systems that provide individualized support
without requiring additional teaching staff. This has particular relevance
for developing countries facing teacher shortages.
| Type | Example | How to Address |
|---|---|---|
| Sampling | Convenience sample | Acknowledge, note generalizability limits |
| Design | No random assignment | Explain impact on causality |
| Measurement | Self-report bias | Note alternative measures |
| Time | Short follow-up | Suggest longitudinal studies |
| Context | Single location | Note need for replication |
This study has several limitations. First, [limitation 1], which may
[affect interpretation]. Second, [limitation 2], limiting [scope].
Third, [limitation 3]. These limitations should be considered when
interpreting [specific findings].
This study has several limitations. First, the quasi-experimental design
without random assignment limits causal inference. Although groups were
matched on key variables, unmeasured confounders may exist. Second, the
single-site sample limits generalizability to other Malaysian schools or
international contexts. Third, the 8-week intervention period precludes
conclusions about long-term retention. These limitations should be
considered when interpreting the sustained effectiveness of AI tutoring.
✅ Do:
❌ Don't:
Future research should address [limitation] by [suggested method].
Additionally, examining [new variable/context] would [contribution].
Longitudinal studies could [benefit].
Future research should address the generalizability limitation by
replicating this study in diverse Malaysian regions and other developing
countries. Additionally, examining the differential effectiveness of AI
tutoring across subject domains would clarify boundary conditions.
Longitudinal studies tracking students beyond 8 weeks could assess
long-term retention and sustained motivation effects.
| Direction | Focus |
|---|---|
| Replication | Different contexts, populations |
| Extension | Longer duration, more variables |
| Methodological | Better designs, measures |
| Theoretical | Test competing explanations |
| Applied | Implementation, scalability |
In conclusion, this study [main contribution]. The findings [key takeaway],
with implications for [theory/practice]. While [acknowledge limitation],
these results [final significance statement].
In conclusion, this study demonstrates that AI-assisted tutoring can
significantly enhance mathematics achievement among Malaysian primary
students. The findings suggest that adaptive learning technology may
help address educational equity challenges in developing contexts, with
implications for both cognitive load theory and instructional design.
While longer-term studies are needed, these results support the
integration of AI systems in resource-constrained educational settings.
| Test | Small | Medium | Large | Interpretation |
|---|---|---|---|---|
| Cohen's d | 0.2 | 0.5 | 0.8 | Mean difference |
| r | 0.1 | 0.3 | 0.5 | Correlation |
| η² | 0.01 | 0.06 | 0.14 | Variance explained |
| R² | 0.02 | 0.13 | 0.26 | Model fit |
| p-value | Interpretation | Report as |
|---|---|---|
| < .001 | Highly significant | p < .001 |
| < .01 | Significant | p < .01 |
| < .05 | Significant | p < .05 |
| < .10 | Marginally significant | p = .07 (report exact) |
| ≥ .10 | Not significant | p = .15 (report exact) |
Note: Always report effect size with p-value!
Participants consistently reported [pattern]. This theme suggests that
[phenomenon] plays a [role] in [context]. This aligns with [theory],
which emphasizes [concept].
Participants consistently reported feeling overwhelmed when AI suggestions
conflicted with their own ideas. This theme suggests that cognitive load
may actually increase when AI outputs require extensive evaluation.
This aligns with Cognitive Load Theory, which emphasizes the importance
of reducing extraneous processing demands.