This exercise dataset was created for researchers interested in learning how to use the models described in the "Handbook on Impact Evaluation: Quantitative Methods and Practices" by S. Khandker, G. Koolwal and H. Samad, World Bank, October 2009 (permanent URL http://go.worldbank.org/FE8098BI60). Public programs are designed to reach certain goals and beneficiaries. Methods to understand whether such programs actually work, as well as the level and nature of impacts on intended beneficiaries, are main themes of this book. Has the Grameen Bank, for example, succeeded in lowering consumption poverty among the rural poor in Bangladesh? Can conditional cash transfer programs in Mexico and Latin America improve health and schooling outcomes for poor women and children? Does a new road actually raise welfare in a remote area in Tanzania, or is it a "highway to nowhere?" This handbook reviews quantitative methods and models of impact evaluation. It begings by reviewing the basic issues pertaining to an evaluation of an intervention to reach certain targets and goals. It then focuses on the experimental design of an impact evaluation, highlighting its strengths and shortcomings, followed by discussions on various non-experimental methods. The authors also cover methods to shed light on the nature and mechanisms by which different participants are benefiting from the program. The handbook provides STATA exercises in the context of evaluating major microcredit programs in Bangladesh, such as the Grameen Bank. This dataset provides both the related Stata data files and the Stata programs.

The Health Survey for England, 2003-2005: Multilevel Modelling Teaching Dataset has been prepared as a resource for those interested in learning multilevel modelling techniques. It was first presented as part of a workshop entitled 'Introducing multilevel models and applying them to the Health Survey for England using MLwiN'. The HSE teaching dataset is available in both Stata and MLwIN formats and is accompanied by a practical guide that includes the multilevel modelling practical exercises. A separate document provides information on the teaching dataset and materials.

The main dataset is an edited version of the Health Survey for England (HSE) data from 2003, 2004 and 2005 (the full HSEs are at the UK Data Archive under SNs 5098, 5439 and 5675). Details of the recoding of HSE variables for the teaching dataset and how the aggregate data were produced can be found in the documentation.

WARNING – Users should note that this dataset is intended as a learning resource and should not be used for research purposes. In particular the dataset uses adult measures of Body Mass Index (BMI) for children and so the results from the data should not be reported in research contexts.

Centre for Longitudinal Study Information and User Support (CeLSIUS) exists to assist people in UK higher education to analyse the Office for National Statistics Longitudinal Study (ONS LS). CeLSIUS is part of the Economic and Social Research Council's (ESRC) Census Programme for 2006-2011. Part of the service it offers is the provision of web-based tools and extracts, including the subset of the ONS LS.

Further information about CeLSIUS is available from the CeLSIUS web site and the ESRC Award web page.
Limiting Long-Term Illness: Longitudinal Perspectives, 1971-2006 is an aggregated teaching dataset which has 367 records (i.e. combinations of values of the variables). It is based on 314,493 cases; cases are ONS LS sample members who:

• were enumerated at both of the most recent censuses (1991 and 2001)
• reported that they were without a limiting long-term illness (LLTI) in 1991
• gave a valid response on whether they had a LLTI in 2001
• were aged 20 years or more in 2001

The ONS LS sample provides a random, one per cent sample of the population of England and Wales, clustered by date of birth.

The documentation includes exercises to accompany the dataset with instructions for both SPSS and Stata users. Exercises centre on exploring the dataset by age, gender, activity status, whether respondent has a partner and whether the respondent has a LLTI.

BackgroundEvaluating the effectiveness of Nordic walking in influencing walking ability in patients with peripheral arterial disease.MethodsWe searched 12 databases, including PubMed, Embase, Cochrane library, Web of Science, EBSCO host, Ovid, Scopus, ClinicalTrial.gov, and several top ranked Chinese databases, including China National Knowledge Infrastructure (CNKI), Wanfang Data, CBMdisc, VIP Database, ChiCTR. The search has no starting time limit and the deadline is April 9, 2024. Randomized controlled trials and pseudo-random controlled trials were included. The two authors independently screened the literature and evaluated the quality of the study using the Cochrane risk of bias tool. Meta analysis was conducted using Review Manager 5.4 and Stata 17.0 software.ResultsA total of 8 studies involving 508 patients were included. Meta-analysis results showed that compared with supervised exercise therapy (SET), supervised NW was not associated with an increase in maximum walking distance (MWD) and claudication distance (CD) in PAD patients, whether during treadmill tests or 6-minute walk tests (6-MWT), and the results were not statistically significant. In terms of increasing exercise duration, SET was significantly higher than supervised NW and the results were statistically significant (SMD =  -0.41, 95% Cl: -0.72 to -0.09, Z =  2.54, P =  0.01

Characteristics of the trials that were included. (N = 8).

Characteristics of patients recruited to the included trials. (N = 508).