Presentation is loading. Please wait.

Presentation is loading. Please wait.

PEP-PMMA Training Session Statistical inference Lima, Peru Abdelkrim Araar / Jean-Yves Duclos 9-10 June 2007.

Similar presentations


Presentation on theme: "PEP-PMMA Training Session Statistical inference Lima, Peru Abdelkrim Araar / Jean-Yves Duclos 9-10 June 2007."— Presentation transcript:

1 PEP-PMMA Training Session Statistical inference Lima, Peru Abdelkrim Araar / Jean-Yves Duclos 9-10 June 2007

2 Why statistical inference? Distributive estimates obtained from surveys are not exact population values. The estimates normally follow a known asymptotic distribution. The parameters of that distribution can be estimated using sample information (including sampling design). Statistically, we can then peform hypothesis tests and draw confidence intervals.

3 Statistical inference Assume that our statistic of interest is simply average income, and its estimator follows a normal distribution:

4 Statistical inference A centred and normalised distribution can be obtained:

5 Hypothesis testing There are three types of hypotheses that can be tested: 1.An index is equal to a given value: Difference in poverty equals 0 Inequality equals to 20% 2.An index is higher than a given value: Inequality has increased between two periods. 3.An index is lower than a given value: Poverty has increased between two periods.

6 The interest of the statistical inferences The outcome of an hypothesis test is a statistical decision The conclusion of the test will either be to reject a null hypothesis, H 0 in favour of an alternative, H 1, or to fail to reject it. Most hypothesis tests involving an unknown true population parameter  fall into three special cases: 1.H 0 : μ = μ 0 against H 1 : μ ≠ μ 0 2.H 0 : μ ≤ μ 0 against H 1 : μ > μ 0 3.H 0 : μ ≥ μ 0 against H 1 : μ < μ 0

7 The interest of the statistical inferences The ultimate statistical decision may be correct or incorrect. Two types of error can occur: Type I error, occurs when we reject H 0 when it is in fact true; Type II error, occurs when we fail to reject H 0 when H 0 is in fact false. Power of the test of an hypothesis H 0 versus H 1 is the probability of rejecting H 0 in favour of H 1 when H 1 is true. P-value is the smallest significance level for which H 0 would be rejected in favour of some H 1.

8 Hypothesis tests Reject H 0 : μ = μ 0 versus H 1 : μ ≠ μ 0 if and only if :

9 Hypothesis tests Reject H 0 : μ ≤ μ 0 versus H 1 : μ > μ0 if and only if :

10 Hypothesis tests Reject H 0 : μ > μ 0 versus H 1 : μ ≤ μ0 if and only if :

11 Confidence intervals Loosely speaking, a confidence interval contains all of the values that “cannot be rejected” in a null hypothesis. Three types of confidence intervals can be drawn:


Download ppt "PEP-PMMA Training Session Statistical inference Lima, Peru Abdelkrim Araar / Jean-Yves Duclos 9-10 June 2007."

Similar presentations


Ads by Google