T-test
From Wikipedia
Layer 1: General description and previous hypothesized conclusions
General description
Compares a continuous outcome with a normal distribution across a predictor with two (t-test) categories
Examples of Hypothesized conclusions
- van Dijk GM, Veenhof C, Schellevis F, Hulsmans H, Bakker JP, Arwert H, Dekker J, Lankhorst GJ, Dekker J.Comorbidity, limitations in activities and pain in patients with osteoarthritis of the hip or knee. BMC Musculoskelet Disord. 2008 Jun 26;9 (1):95
- There is association between limitations in activities and pain in elderly patients with knee or hip OA using a comprehensive inventory of comorbidity
- Abegg M, Tappeiner C, Wolf-Schnurrbusch U, Barthelmes D, Wolf S, Fleischhauer J.Treatment of branch retinal vein occlusion induced macular edema withbevacizumab. BMC Ophthalmol. 2008 Sep 29;8:18
- Anti-VEGF therapy is a treatment option for treatment of BRVO-induced macular edema.
Layer 2: Input
Variable cluster and Research question
Dependent t-test (Paired t test)
when each member of one sample has a unique relationship with a particular member of the other sample (e.g., the same people measured before and after an intervention.This test is used when the samples are dependent; that is, when there is only one sample that has been tested twice (repeated measures) or when there are two samples that have been matched or "paired".
Independent t-test
one-sample t-test
when the population mean is equal to a specified value
two-sample t-test
Equal sample sizes, equal variance: the two sample sizes (that is, the n or number of participants of each group) are equal; it can be assumed that the two distributions have the same variance.
Unequal sample sizes, equal variance:This test is used only when it can be assumed that the two distributions have the same variance.
Unequal sample sizes, unequal variance: This test is used only when the two sample sizes are unequal and the variance is assumed to be different
Outcome
- Distribution
- normal
- continuous
- normal
Predictor
- Distribution
- ------
- nominal, 2 categories
- ------
Layer 3: Output
3a (1): Interpretation of the output provided by the statistician (Stata output)
Interpretation
3a (2): Interpretation of the output provided by the statistician
Interpretation
There was statistically no significant difference in the age of the patients enrolled in the two groups studied.
3b : Tables published in journal articles
van Dijk GM, Veenhof C, Schellevis F, Hulsmans H, Bakker JP, Arwert H, Dekker J, Lankhorst GJ, Dekker J.Comorbidity, limitations in activities and pain in patients with osteoarthritis of the hip or knee. BMC Musculoskelet Disord. 2008 Jun 26;9 (1):95
Interpretation
Table 5 shows the mean differences in scores for limitations in activities and pain between patients that suffer from moderate or severe coexistent diseases (CIRS score ≥ 2) and patients that do not. Most of the moderate or severe diseases and obesity were found to be associated with limitations in activities (WOMAC, SF-36 and timed walking test) or with pain (VAS).
Abegg M, Tappeiner C, Wolf-Schnurrbusch U, Barthelmes D, Wolf S, Fleischhauer J.Treatment of branch retinal vein occlusion induced macular edema withbevacizumab. BMC Ophthalmol. 2008 Sep 29;8:18
Interpretation
The mean follow up interval was 30 ± 11 days. BCVA was 0.68 ± 0.3 and 0.5 ± 0.35 logMAR, before and after injection respectively (p < 0.01, paired t-test). CRT decreased from 454 ± 117 μm to 305 ± 129 μm (p < 0.01, paired t-test)
Layer 4: List of previous QDs
Layer 5: Annotated references
- t-test wikipedia and ANOVA
- Biostatistics: The bare essentials by Norman and Streiner. Second Edition, 2000. B.C. Decker Inc. Hamilaton. London
- Introductory Statistics with R By Peter Dalgaard. Very good second introductory book, with plenty of scripts in the R language so that students can practice with small data sets.



