�MONITORIMI DHE VLERËSIMI PËR POLITIKAT E SHTETIT TË SË DREJTËS

Webinar 6

Analizimi i të Dhënave dhe Komponenti i nxënies

Data Analysis Methods for Monitoring

• Quantitative Data for Monitoring
• Descriptive Univariate analysis (helps describe data and help to summarize; univariate mean s one variable)
• The centre and the spread of the data are two commonly used descriptive statistics. Whereas the center describes a typical value, the spread describes the distance of a data point from the centre of the data.
• The interquartile range is the difference between the upper quartile and lower quartile of the data. A quarter (or 25%) of the data lie above the upper quartile and a quarter of the data lie below the lower quartile.
• The standard deviation shows the average difference between each data point and the mean age.
• If all data points are close to the mean, then the standard deviation is low, showing that there is little difference between values. A large standard deviation indicates that there is a larger spread of data.
• Triangulation is the process of comparing several different data sources and methods to corroborate findings and compensate for any weaknesses in the data by the strengths of other data;
• Descriptive Multivariate: analyses of more than one variable (cross-tabulation)

​

• Qualitative data analysis for monitoring is a process aimed at reducing and making sense of vast amounts of qualitative information to patterns that address the M&E questions posed.

Data analysis method for evaluation!

• Program evaluation is concerned with the estimation of the causal effects of policy interventions;

• The causal effect can be evaluated using both experimental and observational data;

​

• Experimental data – one has control over treatment/control unknit selection
• Observational Data: no control over units under. treatment

Causality in observational data

Observational data – causal effect

The back door adjustment

Experimental data – Random Control Treatment (Golden Standard)

• Causal effect = average outcome in treatment group – average outcome in the control group
• When non-randomization is violated
• Causal inference through regression matching control and treatment group based on their characteristics

Difference in difference

• Estimating impact comparing before and after treatment o policy
• Randomization violated in case of experiment data or the impact assessment is based on observational data;
• One needs to isolate the impact from other factors. (example of the impact of minimum wage increase on employment)

Model (diff-in-diff)

Learning

FALEMINDERIT PËR VËMENDJEN!

Këto webinare janë pjesë përbëse e Moduleve të Integrurara për MEL të Politikave të Shtetit të së Drejtës, përgatitur nga Lëvizja Europiane në Shqipëri në kuadër të projektit “Ndërtimi i Partneritetit mbi Çështjet Themelore: Fuqizimi i OSHC-ve për procesin e anëtarësimit në BE” financuar nga Bashkimi Evropian. �