Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Impact Evaluation Session VII Sampling and Power Jishnu Das November 2006 Sample Selection in Evaluation Population based representative surveys: Sampling for Impact evaluation Sample representative of whole population Good for learning about the population Not always most efficient for impact evaluation Balance between treatment and control groups Power statistical inference for groups of interest Concentrate sample strategically Survey budget as major consideration In practice, sample size is many times set by budget Concentrate sample on key populations to increase power HDN SAR WBI 2 Purposive Sampling: Risk: We will systematically bias our sample, so results don’t generalize to the rest of the population or other sub-groups Trade off between power within population of interest and population representation Results are internally valid, but not generalizable. HDN SAR WBI 3 Survey - Sampling Population: all cases of interest Sampling frame: list of all potential cases Sample: cases selected for analysis Sampling method: technique for selecting cases from sampling frame Sampling fraction: proportion of cases from population selected for sample (n/N) HDN SAR WBI 4 Sampling Frame Simple Sampling Stratified Sampling Cluster Sampling HDN SAR WBI 5 Sampling Methods Random Sampling Systematic Sampling HDN SAR WBI 6 The Design Effect in Clustering Necessary to take into account when samples are clustered Var cluster deff Var srs HDN SAR WBI 7 Correlación intracluster () DEFF depends on the size of the cluster and the intra-cluster correlation Deff [ 1 ( k 1 )] where intracluster correlation k cluster size deff 1 k 1 deff design effect k cluster size is the degree of homogeneity in the cluster, and is called the “intra-cluster” correlation HDN SAR WBI 8 Tamaño de muestra The necessary sample size will increase in clustered samples n nsrs deff where nsrs size required with simple randomsampling But, you have to have some idea of the intra-cluster coefficient to get at this number! HDN SAR WBI 9 Power Calculations Test significance of a null hypothesis. For example, whether two means are different. HDN SAR WBI 10 Type I and Type II errors Type I error = Power = 1- Type II error = -4 -2 0 2 4 6 x HDN SAR WBI Significance Level 11 Type I and type II errors Type I error: Reject the null hypothesis when it is true Type II error: Accept (fail to reject) the null hypothesis when it is false Significance level probability of rejecting the null when it is true (Type I error) Power probability of rejecting the null when an alternative null is true (1-probability of Type II) We want to minimize both types of errors Increase sample size HDN SAR WBI 12 Type I and Type II errors Type I error = Type II error = Probability you conclude that intervention had no effect when it actually did Power = 1 - Probability that you conclude the intervention had an effect if actually it did not Probabilty of correctly conluding that the intervention had an effect Fix the type I error and use sample size to increase the power HDN SAR WBI 13 Power Calculations for sample size Fix the confidence level and as you increase the size of the sample: Rejection region gets larger The power increases n↑ -4 -2 0 2 x HDN SAR WBI 4 6 -4 -2 0 2 4 6 x 14 What we have so far Clustering increases the required sample size As does the need for statistical testing: if we know The estimated size of the treatment The variance of the distribution HDN SAR WBI We can start making power calculations for evaluations 15 In Practice Many, many analytical statistical results May be simpler to use simulations in Stata or similar package Easily accounts for complicated designs HDN SAR WBI 16 In Practice: An Example Does Information improve child performance in schools? (Pakistan) Randomized Design Interested in villages where there are private schooling options What Villages should we work in? Stratification: North, Central, South Random Sample: Villages chosen randomly from list of all villages with a private school HDN SAR WBI 17 In Practice: An Example How many villages should we choose? Depends on: How many children in every village How big do we think the treatment effect will be What the overall variability in the outcome variable will be HDN SAR WBI 18 In Practice: An Example Simulation Tables Table 1 assumes very high variability in testscores. Number of children in every School 5 10 15 20 Number of Villages (assuming 3 schools per village) 21 27 36 42 60 N,n N,n N,s N,s N,a N,s N,m N,a N,a S,a N,s N,m N,a N,a M,a N,m S,m M,a M,a M,a X,Y: X is for intervention with small effect size; Y for larger effect size N: Significant < 1% of simulations S: Significant < 10% of simulations A: Significant > 99% of simulations HDN SAR WBI 19 In Practice: An Example Simulation Tables Table 1 assumes lower variability in testscores. Number of children in every School 5 10 15 20 Number of Villages (assuming 3 schools per village) 21 27 36 42 60 N,s N,s s,m s,m S,a N,m S,m m,a M,a M,a N,m s,m M,a M,a M,a S,a S,a M,a M,a M,a X,Y: X is for intervention with small effect size; Y for larger effect size N: Significant < 1% of simulations S: Significant < 10% of simulations A: Significant > 99% of simulations HDN SAR WBI 20 A smorgasbord of topics Probability proportional to size sampling to pick clusters Using weights Estimating means vs. Estimating regressions Increasing efficiency using matched randomizations Using evaluations to say something about baseline populations Age targeted programs HDN SAR WBI 21 When do we really worry about this? IF Very small samples at unit of treatment! Suppose treatment in 20 schools and control in 20 schools This is still a small sample IF But there are 400 children in every school Interested in sub-groups (blocks) Sample size requirements increase exponentially IF Using Regression Discontinuity Designs HDN SAR WBI 22