1 / 15

Writing an APA-Style Research Report

Writing an APA-Style Research Report. Results and Discussion. Results Section. Start on first line after the last line of the Methods section. No hard page break. Type “ Results ” on that first line . Center it. Include tables and/or figures when appropriate.

jersey
Télécharger la présentation

Writing an APA-Style Research Report

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Writing an APA-Style Research Report Results and Discussion

  2. Results Section • Start on first line after the last line of the Methods section. No hard page break. • Type “Results” on that first line. Center it. • Include tables and/or figures when appropriate. • Present descriptive statistics, tests of statistical significance, estimates of effect size, and/or confidence intervals.

  3. Tables and Figures • In a copy manuscript, place them at the end of the manuscript. • In a final manuscript, insert each near the point where you first refer to it.

  4. Descriptive Statistics • As needed to support your conclusions, present means, standard deviations, correlation coefficients, regression parameters, percentages, etc. • See my list of common statistical abbreviations. • Set statistical symbols in italic font (but not Greek letters).

  5. Tests of Statistical Significance • Identify the test statistic employed (such as z, t, F, or 2 ). • Give degrees of freedom and/or sample size. • Report the value of the test statistic and an exact p value. • Indicate whether or not the test is statistically significant. • Emphasize the direction of any significant effect.

  6. T-Test For the defendant, the attractive photograph was rated significantly more attractive (M = 7.86, SD = 1.29) than the unattractive photograph (M = 2.90, SD = 1.74), t(322) = 29.15, p = .000, d = 3.24, 95% CI [2.91, 3.57].

  7. ANOVA A three way factorial ANOVA was employed to evaluate the effects of gender of juror, race of plaintiff, and race of defendant upon certainty of guilt. The significant effects were gender of juror, F(1, 153) = 5.49, p = .020, p2 = .035, 90% CI [.003, .094]; Gender of Juror x Race of Defendant, F(1, 153) = 4.87, p = .029, p2 = .031, 90% CI [.002 .088]; and Gender of Juror x Race of Plaintiff, F(1, 153) = 6.01, p = .015, p2 = .038, 90% CI [.004, .098], with a MSE of 2.90 for each of these effects. Female jurors were significantly more certain of the defendant’s guilt (M = 6.30) than were male jurors (M = 5.70), d = .35, CI.95 = .035, .658. The significant interactions were investigated further by evaluating the simple main effects of race separately for female and male jurors.

  8. ANOVA, Simple Effects White male jurors were significantly more certain of the guilt of black defendants (M = 6.07) than of white defendants (M = 5.29), F(1, 75) = 4.50, MSE = 3.029, p = .037, d = .43, p2 = .057, 95% CI for p2 [.002, .157], and more certain when the plaintiff was white (M = 6.20) than when she was black (M = 5.18), F(1, 75) = 7.48, MSE = 3.029, p = .008, d = .57, p2 = .091, 95% CI for p2 [.014, .202].

  9. Contingency Table Analysis Female jurors returned guilty verdicts significantly more frequently (86%) than did male jurors (70%), 2(1, N = 152) = 5.550, p = .018, odds ratio = 2.63.

  10. Regression Analysis Among nonidealists (n = 91), support for animal rights was significantly related to misanthropy, animal rights = 1.63 + .3 misanthropy, r = .36, p < .001, 95% CI [.17, .53]. When corrected for attenuation due to lack of perfect reliability in the variables, the r = .42. Among idealists (n = 63), the regression line was flat, animal rights = 2.40 + 0.02 misanthropy, r = .02, p = .87. 95% CI = [-0.23, +0.27].

  11. Estimates of Effect Size • Do report estimates of effect size. • Common are Hedges’ Cohen’s d, r2, 2, 2, and odds ratios. • See Strength of Effect Estimates for Simple Statistical Analyses.

  12. Confidence Intervals • Confidence intervals can be used in addition to or in place of tests of statistical significance. • The APA and most statisticians encourage this. • But most editors and reviewers insist on having traditional tests of statistical significance.

  13. Confidence Intervals for Standardized Effect Size Estimates • Often it is more helpful to report confidence intervals around standardized effect size estimates than around unstandardized effect size estimates. • Just recently software has been developed to do this. • There are some complexities that have not yet been worked out to my satisfaction.

  14. Discussion Section • Start on first line after the last line of the Results section. No hard page break. • Type “Discussion” on that first line. • Relate your results to your hypotheses or expectation. • Theoretical and practical implications.

  15. Compare your results to those of others. • Limitations of your study? • Suggestions for additional research. • May be combined with the Results section.

More Related