Comparative Analysis of Evolving Software Systems Using the Gini Coefficient

Software metrics offer us the promise of distilling useful information from vast amounts of software in order to track development progress, to gain insights into the nature of the software, and to identify potential problems. Unfortunately, however, many software metrics exhibit highly skewed, non-Gaussian distributions. As a consequence, usual ways of interpreting these metrics --- for example, in terms of "average" values --- can be highly misleading. Many metrics, it turns out, are distributed like wealth --- with high concentrations of values in selected locations. We propose to analyze software metrics using the Gini coefficient, a higher-order statistic widely used in economics to study the distribution of wealth. Our approach allows us not only to observe changes in software systems efficiently, but also to assess project risks and monitor the development process itself. We apply the Gini coefficient to numerous metrics over a range of software projects, and we show that many metrics not only display remarkably high Gini values, but that these values are remarkably consistent as a project evolves over time.

ANOGI: Stata module to generate Analysis of Gini

anogi computes the "Analysis of Gini" for population sub-groups proposed by Frick et al. (2006; Sociological Methods and Research 34/4).

Transmission of Chlamydia trachomatis through sexual partnerships: a comparison between three individual-based models and empirical data

Chlamydia trachomatis is the most common bacterial sexually transmitted infection (STI) in many developed countries. The highest prevalence rates are found among young adults who have frequent partner change rates. Three published individual-based models have incorporated a detailed description of age-specific sexual behaviour in order to quantify the transmission of C. trachomatis in the population and to assess the impact of screening interventions. Owing to varying assumptions about sexual partnership formation and dissolution and the great uncertainty about critical parameters, such models show conflicting results about the impact of preventive interventions. Here, we perform a detailed evaluation of these models by comparing the partnership formation and dissolution dynamics with data from Natsal 2000, a population-based probability sample survey of sexual attitudes and lifestyles in Britain. The data also allow us to describe the dispersion of C. trachomatis infections as a function of sexual behaviour, using the Gini coefficient. We suggest that the Gini coefficient is a useful measure for calibrating infectious disease models that include risk structure and highlight the need to estimate this measure for other STIs.

Adjuvant treatment of premenopausal women with endocrine-responsive early breast cancer: design of the TEXT and SOFT trials

OBJECTIVES In 2003 the International Breast Cancer Study Group (IBCSG) initiated the TEXT and SOFT randomized phase III trials to answer two questions concerning adjuvant treatment for premenopausal women with endocrine-responsive early breast cancer: 1-What is the role of aromatase inhibitors (AI) for women treated with ovarian function suppression (OFS)? 2-What is the role of OFS for women who remain premenopausal and are treated with tamoxifen? METHODS TEXT randomized patients to receive exemestane or tamoxifen with OFS. SOFT randomized patients to receive exemestane with OFS, tamoxifen with OFS, or tamoxifen alone. Treatment was for 5 years from randomization. RESULTS TEXT and SOFT successfully met their enrollment goals in 2011. The 5738 enrolled women had lower-risk disease and lower observed disease-free survival (DFS) event rates than anticipated. Consequently, 7 and 13 additional years of follow-up for TEXT and SOFT, respectively, were required to reach the targeted DFS events (median follow-up about 10.5 and 15 years). To provide timely answers, protocol amendments in 2011 specified analyses based on chronological time and median follow-up. To assess the AI question, exemestane + OFS versus tamoxifen + OFS, a combined analysis of TEXT and SOFT became the primary analysis (n = 4717). The OFS question became the primary analysis from SOFT, assessing the unique comparison of tamoxifen + OFS versus tamoxifen alone (n = 2045). The first reports are anticipated in mid- and late-2014. CONCLUSIONS We present the original designs of TEXT and SOFT and adaptations to ensure timely answers to two questions concerning optimal adjuvant endocrine treatment for premenopausal women with endocrine-responsive breast cancer. Trial Registration TEXT: Clinicaltrials.govNCT00066703 SOFT: Clinicaltrials.govNCT00066690.

Active surveillance for rheumatic heart disease in endemic regions: a systematic review and meta-analysis of prevalence among children and adolescents

BACKGROUND Rheumatic heart disease accounts for up to 250 000 premature deaths every year worldwide and can be regarded as a physical manifestation of poverty and social inequality. We aimed to estimate the prevalence of rheumatic heart disease in endemic countries as assessed by different screening modalities and as a function of age. METHODS We searched Medline, Embase, the Latin American and Caribbean System on Health Sciences Information, African Journals Online, and the Cochrane Database of Systematic Reviews for population-based studies published between Jan 1, 1993, and June 30, 2014, that reported on prevalence of rheumatic heart disease among children and adolescents (≥5 years to <18 years). We assessed prevalence of clinically silent and clinically manifest rheumatic heart disease in random effects meta-analyses according to screening modality and geographical region. We assessed the association between social inequality and rheumatic heart disease with the Gini coefficient. We used Poisson regression to analyse the effect of age on prevalence of rheumatic heart disease and estimated the incidence of rheumatic heart disease from prevalence data. FINDINGS We included 37 populations in the systematic review and meta-analysis. The pooled prevalence of rheumatic heart disease detected by cardiac auscultation was 2·9 per 1000 people (95% CI 1·7-5·0) and by echocardiography it was 12·9 per 1000 people (8·9-18·6), with substantial heterogeneity between individual reports for both screening modalities (I(2)=99·0% and 94·9%, respectively). We noted an association between social inequality expressed by the Gini coefficient and prevalence of rheumatic heart disease (p=0·0002). The prevalence of clinically silent rheumatic heart disease (21·1 per 1000 people, 95% CI 14·1-31·4) was about seven to eight times higher than that of clinically manifest disease (2·7 per 1000 people, 1·6-4·4). Prevalence progressively increased with advancing age, from 4·7 per 1000 people (95% CI 0·0-11·2) at age 5 years to 21·0 per 1000 people (6·8-35·1) at 16 years. The estimated incidence was 1·6 per 1000 people (0·8-2·3) and remained constant across age categories (range 2·5, 95% CI 1·3-3·7 in 5-year-old children to 1·7, 0·0-5·1 in 15-year-old adolescents). We noted no sex-related differences in prevalence (p=0·829). INTERPRETATION We found a high prevalence of rheumatic heart disease in endemic countries. Although a reduction in social inequalities represents the cornerstone of community-based prevention, the importance of early detection of silent rheumatic heart disease remains to be further assessed. FUNDING UBS Optimus Foundation.

A Swiss paradox? Higher income inequality of municipalities is associated with lower mortality in Switzerland.

It has long been surmised that income inequality within a society negatively affects public health. However, more recent studies suggest there is no association, especially when analyzing small areas. This study aimed to evaluate the effect of income inequality on mortality in Switzerland using the Gini index on municipality level. The study population included all individuals >30 years at the 2000 Swiss census (N = 4,689,545) living in 2,740 municipalities with 35.5 million person-years of follow-up and 456,211 deaths over follow-up. Cox proportional hazard regression models were adjusted for age, gender, marital status, nationality, urbanization, and language region. Results were reported as hazard ratios (HR) with 95 % confidence intervals. The mean Gini index across all municipalities was 0.377 (standard deviation 0.062, range 0.202-0.785). Larger cities, high-income municipalities and tourist areas had higher Gini indices. Higher income inequality was consistently associated with lower mortality risk, except for death from external causes. Adjusting for sex, marital status, nationality, urbanization and language region only slightly attenuated effects. In fully adjusted models, hazards of all-cause mortality by increasing Gini index quintile were HR = 0.99 (0.98-1.00), HR = 0.98 (0.97-0.99), HR = 0.95 (0.94-0.96), HR = 0.91 (0.90-0.92) compared to the lowest quintile. The relationship of income inequality with mortality in Switzerland is contradictory to what has been found in other developed high-income countries. Our results challenge current beliefs about the effect of income inequality on mortality on small area level. Further investigation is required to expose the underlying relationship between income inequality and population health.

Adjuvant ovarian suppression in premenopausal breast cancer.

BACKGROUND Suppression of ovarian estrogen production reduces the recurrence of hormone-receptor-positive early breast cancer in premenopausal women, but its value when added to tamoxifen is uncertain. METHODS We randomly assigned 3066 premenopausal women, stratified according to prior receipt or nonreceipt of chemotherapy, to receive 5 years of tamoxifen, tamoxifen plus ovarian suppression, or exemestane plus ovarian suppression. The primary analysis tested the hypothesis that tamoxifen plus ovarian suppression would improve disease-free survival, as compared with tamoxifen alone. In the primary analysis, 46.7% of the patients had not received chemotherapy previously, and 53.3% had received chemotherapy and remained premenopausal. RESULTS After a median follow-up of 67 months, the estimated disease-free survival rate at 5 years was 86.6% in the tamoxifen-ovarian suppression group and 84.7% in the tamoxifen group (hazard ratio for disease recurrence, second invasive cancer, or death, 0.83; 95% confidence interval [CI], 0.66 to 1.04; P=0.10). Multivariable allowance for prognostic factors suggested a greater treatment effect with tamoxifen plus ovarian suppression than with tamoxifen alone (hazard ratio, 0.78; 95% CI, 0.62 to 0.98). Most recurrences occurred in patients who had received prior chemotherapy, among whom the rate of freedom from breast cancer at 5 years was 82.5% in the tamoxifen-ovarian suppression group and 78.0% in the tamoxifen group (hazard ratio for recurrence, 0.78; 95% CI, 0.60 to 1.02). At 5 years, the rate of freedom from breast cancer was 85.7% in the exemestane-ovarian suppression group (hazard ratio for recurrence vs. tamoxifen, 0.65; 95% CI, 0.49 to 0.87). CONCLUSIONS Adding ovarian suppression to tamoxifen did not provide a significant benefit in the overall study population. However, for women who were at sufficient risk for recurrence to warrant adjuvant chemotherapy and who remained premenopausal, the addition of ovarian suppression improved disease outcomes. Further improvement was seen with the use of exemestane plus ovarian suppression. (Funded by Pfizer and others; SOFT ClinicalTrials.gov number, NCT00066690.).

Adjuvant exemestane with ovarian suppression in premenopausal breast cancer.

BACKGROUND Adjuvant therapy with an aromatase inhibitor improves outcomes, as compared with tamoxifen, in postmenopausal women with hormone-receptor-positive breast cancer. METHODS In two phase 3 trials, we randomly assigned premenopausal women with hormone-receptor-positive early breast cancer to the aromatase inhibitor exemestane plus ovarian suppression or tamoxifen plus ovarian suppression for a period of 5 years. Suppression of ovarian estrogen production was achieved with the use of the gonadotropin-releasing-hormone agonist triptorelin, oophorectomy, or ovarian irradiation. The primary analysis combined data from 4690 patients in the two trials. RESULTS After a median follow-up of 68 months, disease-free survival at 5 years was 91.1% in the exemestane-ovarian suppression group and 87.3% in the tamoxifen-ovarian suppression group (hazard ratio for disease recurrence, second invasive cancer, or death, 0.72; 95% confidence interval [CI], 0.60 to 0.85; P<0.001). The rate of freedom from breast cancer at 5 years was 92.8% in the exemestane-ovarian suppression group, as compared with 88.8% in the tamoxifen-ovarian suppression group (hazard ratio for recurrence, 0.66; 95% CI, 0.55 to 0.80; P<0.001). With 194 deaths (4.1% of the patients), overall survival did not differ significantly between the two groups (hazard ratio for death in the exemestane-ovarian suppression group, 1.14; 95% CI, 0.86 to 1.51; P=0.37). Selected adverse events of grade 3 or 4 were reported for 30.6% of the patients in the exemestane-ovarian suppression group and 29.4% of those in the tamoxifen-ovarian suppression group, with profiles similar to those for postmenopausal women. CONCLUSIONS In premenopausal women with hormone-receptor-positive early breast cancer, adjuvant treatment with exemestane plus ovarian suppression, as compared with tamoxifen plus ovarian suppression, significantly reduced recurrence. (Funded by Pfizer and others; TEXT and SOFT ClinicalTrials.gov numbers, NCT00066703 and NCT00066690, respectively.).

An Ever Closer Union? The Nationalisation of Political Parties in Switzerland, 1991–2015

The contribution of this research note is a systematic description of levels of party nationalisation in Switzerland, using results from the elections to the Swiss National Council between 1991 and 2015. Party nationalisation is understood as the territorial homogeneity of a party's electoral performance and measured using the inverted and standardised Gini index. Our results indicate a trend towards more nationalisation in the Swiss party system over the time period covered, and distinct patterns for single parties. The SVP and the GLP have made big leaps towards stronger nationalisation, with the former closing in on the levels of the SP and the FDP, while the CVP remains a weakly nationalised party, considering its size.

MOREMATA: Stata module (Mata) to provide various functions

This package includes various Mata functions. kern(): various kernel functions; kint(): kernel integral functions; kdel0(): canonical bandwidth of kernel; quantile(): quantile function; median(): median; iqrange(): inter-quartile range; ecdf(): cumulative distribution function; relrank(): grade transformation; ranks(): ranks/cumulative frequencies; freq(): compute frequency counts; histogram(): produce histogram data; mgof(): multinomial goodness-of-fit tests; collapse(): summary statistics by subgroups; _collapse(): summary statistics by subgroups; gini(): Gini coefficient; sample(): draw random sample; srswr(): SRS with replacement; srswor(): SRS without replacement; upswr(): UPS with replacement; upswor(): UPS without replacement; bs(): bootstrap estimation; bs2(): bootstrap estimation; bs_report(): report bootstrap results; jk(): jackknife estimation; jk_report(): report jackknife results; subset(): obtain subsets, one at a time; composition(): obtain compositions, one by one; ncompositions(): determine number of compositions; partition(): obtain partitions, one at a time; npartitionss(): determine number of partitions; rsubset(): draw random subset; rcomposition(): draw random composition; colvar(): variance, by column; meancolvar(): mean and variance, by column; variance0(): population variance; meanvariance0(): mean and population variance; mse(): mean squared error; colmse(): mean squared error, by column; sse(): sum of squared errors; colsse(): sum of squared errors, by column; benford(): Benford distribution; cauchy(): cumulative Cauchy-Lorentz dist.; cauchyden(): Cauchy-Lorentz density; cauchytail(): reverse cumulative Cauchy-Lorentz; invcauchy(): inverse cumulative Cauchy-Lorentz; rbinomial(): generate binomial random numbers; cebinomial(): cond. expect. of binomial r.v.; root(): Brent's univariate zero finder; nrroot(): Newton-Raphson zero finder; finvert(): univariate function inverter; integrate_sr(): univariate function integration (Simpson's rule); integrate_38(): univariate function integration (Simpson's 3/8 rule); ipolate(): linear interpolation; polint(): polynomial inter-/extrapolation; plot(): Draw twoway plot; _plot(): Draw twoway plot; panels(): identify nested panel structure; _panels(): identify panel sizes; npanels(): identify number of panels; nunique(): count number of distinct values; nuniqrows(): count number of unique rows; isconstant(): whether matrix is constant; nobs(): number of observations; colrunsum(): running sum of each column; linbin(): linear binning; fastlinbin(): fast linear binning; exactbin(): exact binning; makegrid(): equally spaced grid points; cut(): categorize data vector; posof(): find element in vector; which(): positions of nonzero elements; locate(): search an ordered vector; hunt(): consecutive search; cond(): matrix conditional operator; expand(): duplicate single rows/columns; _expand(): duplicate rows/columns in place; repeat(): duplicate contents as a whole; _repeat(): duplicate contents in place; unorder2(): stable version of unorder(); jumble2(): stable version of jumble(); _jumble2(): stable version of _jumble(); pieces(): break string into pieces; npieces(): count number of pieces; _npieces(): count number of pieces; invtokens(): reverse of tokens(); realofstr(): convert string into real; strexpand(): expand string argument; matlist(): display a (real) matrix; insheet(): read spreadsheet file; infile(): read free-format file; outsheet(): write spreadsheet file; callf(): pass optional args to function; callf_setup(): setup for mm_callf().