Presentation is loading. Please wait.

Presentation is loading. Please wait.

FRAMING RESEARCH QUESTIONS The PICO Strategy. PICO P: Population of interest I: Intervention C: Control O: Outcome.

Similar presentations


Presentation on theme: "FRAMING RESEARCH QUESTIONS The PICO Strategy. PICO P: Population of interest I: Intervention C: Control O: Outcome."— Presentation transcript:

1 FRAMING RESEARCH QUESTIONS The PICO Strategy

2 PICO P: Population of interest I: Intervention C: Control O: Outcome

3 PICO P: Population of interest Patient characteristics or the problem to be addressed I: Intervention Exposure to be considered–treatments/ tests C: ControlControl or comparison intervention treatment/placebo/standard of care O: Outcome Outcome of interest: what you are trying to measure, improve or affect; may be disease-oriented or patient –oriented.

4 PICO- Controls The “C”, Controls, is the the only optional component in the PICO question. Can look at an intervention without exploring an alternative. May not be an alternative.

5 What type of question is being asked? Therapy/ prevention Diagnosis Etiology Prognosis

6 What type of question is being asked? Therapy/ prevention Questions of treatment in order to achieve an outcome Diagnosis Questions of identification of a disorder in a patient with specific symtoms. Etiology/ Harm Questions of negative impact from an intervention or exposure. Prognosis Questions of progression of a disease or the likelihood of a disease occurring.

7 How large was the treatment effect? Most RCTs look at a dichotomous outcome: (“yes” or “no”, did death occur or not, did a patient suffer an event or not?). Can express impact of treatment as Relative Risk: The risk of events among patients on the new treatment, relative to that risk among patients in the control group.

8 Relative Risk If RR=1 risk in treatment group (exposed) equals risk in non-treatment group (non-exposed). If RR>1 risk in treatment group (exposed) is greater than in non- treatment group (non-exposed); positive association, possibly causal. If RR<1 risk in treatment group (exposed less than risk in non-exposed); negative association, possibly protective.

9 P values A probability statement. Statistical inference. Null hypothesis (Ho) generally presumes two groups, exposures, or treatments are not different. The experiment generally sets out to prove that there is a difference in the intervention and control group (or to compare them). H1. If the null hypothesis is true, what is the probability of the observed statistic (result) or a more extreme result occurring? P values answer this: Small p values provides good evidence against the null hypothesis, or says that a statistically significant difference exists.

10 The significance of a test: When P>0.10, the observed difference is not significant. When 0.05< P< 0.10, the observed difference is said to be marginally significant. When 0.01<P<0.05, the observed difference is said to be significant. When P<0.01, the observed difference is said to be highly significant.

11 Confidence Intervals (CI): Another form of statistical inference: estimation. Point estimate provides a single estimate of a parameter. Interval estimation provides a range of values (confidence interval) that seeks to capture that parameter. This interval extends a margin of error (“wiggle room”) above and below the point estimate

12 What does a 95% CI mean? The confidence level of a confidence interval refers to the success rate of the method in capturing the parameter it seeks. 95% CI is the level of confidence: it says that we are 95% confident that the true value of the parameter we are looking at is within our confidence interval.


Download ppt "FRAMING RESEARCH QUESTIONS The PICO Strategy. PICO P: Population of interest I: Intervention C: Control O: Outcome."

Similar presentations


Ads by Google