Research Methods

Research Methods

Evaluating research
1. 1. Identification of the source
  1. when, where, peer reviewed?
2. 2. Analysis of argument
  1. Theory? alternatives? concepts defined? hypothesis and questions appropriate?
3. 3. Examination of methodology
  1. Particpants representative? sample? design? reliability and validity
4. 4. Evaluation of results
  1. Appropriate stats? reliable and clearly presented results? results support hypothesis?
5. 5. Analysis of conclusions and interpretations
  1. Conclusions logical? overly speculative? alternative explanations explored? does it just re-state the results?
Experimental designs
1. Independent and dependent variables
2. 1 tailed vs 2 tailed hypotheses
  1. 1 tailed - know the direction of outcome
  2. 2 tailed - don't know direction of outcome e.g. is there a difference at all?
3. Error - influence of other variables other than the IV
4. experimental designs involving groups of participants
  1. Between participants
    1. 1 factor e.g. mood level and 2 or more conditions e.g. 30 mins exercise vs no exercise
    2. Matched - when there are likely to be errors
  2. Within participants/repeated measures
    1. Each participant takes part in all conditions - looking at changes within person
  3. More complex designs
    1. Multi-level
      1. more than 2 conditions from the IV
    2. Factorial - more than one IV
    3. Multivariate - more than one DV measured
    4. Mixed - within and between participants measured
    5. Covariate - covarying factors on DV subtracted out
5. Single participants
  1. AB design - A (baseline) B (intervention)
  2. ABAB design. Gap of time in between and repeated
  3. Multiple baseline - lots of baselines taken then measured over time with intervention
  4. Changing criterion design - changing intervention and measuring over time
Describing and displaying data
1. Descriptive vs Inferential statistics
2. Nominal data - labels, names
3. Ordinal - 1st, 2nd, agree disagree
4. Interval vs ratio - equal data. ratio has true zero
5. Measures of central tendancy - mean, median, mode
6. Measures of spread - range, variance, SD
7. Frequency distributions
Statistical tests of difference
1. 1 independent variable 2 conditions
  1. Wilcoxon matched-pairs signed ranks test
    1. nonparametric
    2. ordinal data
    3. experimental design - repeated
  2. Mann-Whitney U test
    1. experimental design - independent
    2. ordinal data
    3. nonparametric
  3. Related t-Test
    1. experimental design - repeated
    2. interval/ratio data
    3. normal distribution
  4. unrelated t-Test
    1. experimental design - independent
    2. normal distribution
    3. interval/ratio data
2. there are others but ill have a job remembering those>>>
Correlation and regression
1. positive vs negative vs no correlation
2. regression
  1. predicting score using the correlation (once you know X you can predict Y)
Multivariate analysis
1. ANOVA
  1. Analysis of Variance
    1. A method of statistical analysis for analysing experiments where there are two or more variables. Also examines any interactions between variables
  2. one-way related ANOVA
    1. repeated measures or matched perform under all conditions of the variable
  3. one way unrelated ANOVA
    1. unrelated participants perform under each condition
  4. two-way related ANOVA
    1. complex parametric test examining interaction between 2 variables e.g noise level of child am vs pm and how well they do maths
  5. two way unrelated ANOVA
    1. unrelated - which treatment works best and is the SLT experienced or not?
  6. two way mixed ANOVA
Statistical tests for Nominal data
1. Binomial sign test
  1. each condition 50% - better or worse? yes or no?
2. Binomial test
  1. 2 conditions + expected and observed - significant difference?
3. Fisher's exact test
  1. 2 independent samples compared for a correlation
4. Chi-square test
  1. Like fisher's exact test but bigger data and goodness of fit
tests of correlation/association
1. chi-square
  1. nominal
  2. non-parametric
2. spearman's rho
  1. ordinal
  2. non-parametric
3. pearson's r
  1. interval/ratio
  2. parametric

Next up

Description

Resource summary

Similar

	Created by Kayleigh Wain over 10 years ago