A new process capability index for multiple quality characteristics based on principal components

This paper presents a new multivariate process capability index (MPCI) which is based on the principal component analysis (PCA) and is dependent on a parameter (Formula presented.) which can take on any real number. This MPCI generalises some existing multivariate indices based on PCA proposed by several authors when (Formula presented.) or (Formula presented.). One of the key contributions of this paper is to show that there is a direct correspondence between this MPCI and process yield for a unique value of (Formula presented.). This result is used to establish a relationship between the capability status of the process and to show that under some mild conditions, the estimators of this MPCI is consistent and converge to a normal distribution. This is then applied to perform tests of statistical hypotheses and in determining sample sizes. Several numerical examples are presented with the objective of illustrating the procedures and demonstrating how they can be applied to determine the viability and capacity of different manufacturing processes.

Trends in the skewness of the body mass index distribution among urban Australian adults, 1980 to 2007

Purpose We analyzed the changes in the body mass index (BMI) distribution for urban Australian adults between 1980 and 2007.

Methods We used data from participants of six consecutive Australian nation-wide surveys with measured weight and height between 1980 and 2007. We used quantile regression to estimate mean BMI (for percentiles of BMI) and prevalence of severe obesity, modeled by natural splines in age, date of birth, and survey date.

Results Since 1980, the right skew in the BMI distribution for Australian adults has increased greatly for men and women, driven by increases in skew associated with age and birth cohort/period. Between 1980 and 2007, the average 5-year increase in BMI was 1 kg/m2 (0.8) for the 95th percentile of BMI in women (men). The increase in the median was about a third of this, and for the 10th percentile, a fifth of this. We estimated that for the cohort born in 1960 around 31% of men and women were obese by age 50 years compared with 11% of the 1930 birth cohort.

Conclusions There have been large increases in the right skew of the BMI distribution for urban Australian adults between 1980 and 2007, and birth cohort effects suggests similar increases are likely to continue.

Estimating the proportion of metabolic health outcomes attributable to obesity: a cross-sectional exploration of body mass index and waist circumference combinations

BACKGROUND: Recent evidence suggests that a substantial subgroup of the population who have a high-risk waist circumference (WC) do not have an obese body mass index (BMI). This study aimed to explore whether including those with a non-obese BMI but high risk WC as 'obese' improves prediction of adiposity-related metabolic outcomes.

METHODS: Eleven thousand, two hundred forty-seven participants were recruited. Height, weight and WC were measured. Ten thousand, six hundred fifty-nine participants with complete data were included. Adiposity categories were defined as: BMI(N)/WC(N), BMI(N)/WC(O), BMI(O)/WC(N), and BMI(O)/WC(O) (N = non-obese and O = obese). Population attributable fraction, area under the receiver operating characteristic curve (AUC), and odds ratios (OR) were calculated.

RESULTS: Participants were on average 48 years old and 50 % were men. The proportions of BMI(N)/WC(N), BMI(N)/WC(O), BMI(O)/WC(N) and BMI(O)/WC(O) were 68, 12, 2 and 18 %, respectively. A lower proportion of diabetes was attributable to obesity defined using BMI alone compared to BMI and WC combined (32 % vs 47 %). AUC for diabetes was also lower when obesity was defined using BMI alone (0.62 vs 0.66). Similar results were observed for all outcomes. The odds for hypertension, dyslipidaemia, diabetes and CVD were increased for those with BMI(N)/WC(O) (OR range 1.8-2.7) and BMI(O)/WC(O) (OR 1.9-4.9) compared to those with BMI(N)/WC(N).

CONCLUSIONS: Current population monitoring, assessing obesity by BMI only, misses a proportion of the population who are at increased health risk through excess adiposity. Improved identification of those at increased health risk needs to be considered for better prioritisation of policy and resources.

Changing guards: time to move beyond body mass index for population monitoring of excess adiposity

With the obesity epidemic, and the effects of aging populations, human phenotypes have changed over two generations, possibly more dramatically than in other species previously. As obesity is an important and growing hazard for population health, we recommend a systematic evaluation of the optimal measure(s) for population-level excess body fat. Ideal measure(s) for monitoring body composition and obesity should be simple, as accurate and sensitive as possible, and provide good categorization of related health risks. Combinations of anthropometric markers or predictive equations may facilitate better use of anthropometric data than single measures to estimate body composition for populations. Here, we provide new evidence that increasing proportions of aging populations are at high health-risk according to waist circumference, but not body mass index (BMI), so continued use of BMI as the principal population-level measure substantially underestimates the health-burden from excess adiposity.

Pitfall trapping does not reliably index the diet or prey resources of Masked Lapwings

Vertebrate ecologists often assess invertebrate prey resources using techniques which sample invertebrate assemblages, and assume such sampling reflects the diet of their focal species. We compare the invertebrate assemblages as recorded by pitfall traps for Masked Lapwing Vanellus miles breeding territories in Phillip Island, Australia, and show that these differ from assemblages recorded in the stomach contents of local Masked Lapwings. Pitfalls traps did not reveal any difference in assemblages between sites where Masked Lapwings bred, and sites where they did not. Thus, pitfall trapping alone is unlikely to adequately index prey availability for Masked Lapwings.

A new industry concentration index

We propose and analyse a new concentration index alternative to the Herfindahl-Hirschman Index (HHI). This new index emphasises the concept of competitive balance. It is designed to preserve the convexity property of the HHI when a merger involves one of the m largest firms, but to decrease and thus to indicate an increase in competition when a merger is purely among the (n − m) smallest firms.

The Counterweight Programme: prevalence of CVD risk factors by body mass index and impact of a 10% weight change

Objectives

To examine relationships between body mass index (BMI), prevalence of physician-recorded cardiovascular disease (CVD) risk factors in primary care, and changes in risk with 10% weight change.

Methods

The Counterweight Project conducted a baseline cross-sectional survey of medical records of 6150 obese (BMI ≥ 30 kg/m2), 1150 age- and sex-matched overweight (BMI 25 to <30 kg/m2), and 1150 age- and sex-matched normal weight (BMI 18.5 to <25 kg/m2) controls, in primary care. Data were collected for the previous 18 months to examine BMI and disease prevalence, and then modelled to show the potential effect of 10% weight loss or gain on risk.

Results

Obese patients develop more CVD risk factors than normal weight controls. BMI ≥ 40 kg/m2 exhibits increased prevalence of type 2 diabetes mellitus (DM), odds ratio (OR) men: 6.16 (p < 0.001); women: 7.82 (p < 0.001) and hypertension OR men: 5.51 (p < 0.001); women: 4.16 (p < 0.001). Dyslipidaemia peaked around BMI 35 to <37.5 kg/m2, OR men: 3.26 (p < 0.001); women 3.76 (p < 0.001) and CVD at BMI 37.5 to <40 kg/m2 in men, OR 4.48 (p < 0.001) and BMI ≥ 40 kg/m2 in women, OR 3.98 (p < 0.001).

A 10% weight loss from the sample mean of 32.5 kg/m2 reduced the OR for type 2 DM by 30% and CVD by 20%, while 10% weight gain increased type 2 DM risk by more than 35% and CVD by 20%.

Conclusion

Obesity plays a fundamental role in CVD risk, which is reduced with weight loss. Weight management intervention strategies should be a public health priority to reduce the burden of disease in the population.

Influence of body mass index on prescribing costs and potential cost savings of a weight management programme in primary care

Objectives Prescribed medications represent a high and increasing proportion of UK health care funds. Our aim was to quantify the influence of body mass index (BMI) on prescribing costs, and then the potential savings attached to implementing a weight management intervention.

Methods Paper and computer-based medical records were reviewed for all drug prescriptions over an 18-month period for 3400 randomly selected adult patients (18–75 years) stratified by BMI, from 23 primary care practices in seven UK regions. Drug costs from the British National Formulary at the time of the review were used. Multivariate regression analysis was applied to estimate the cost for all drugs and the ‘top ten’ drugs at each BMI point. This allowed the total and attributable prescribing costs to be estimated at any BMI. Weight loss outcomes achieved in a weight management programme (Counterweight) were used to model potential effects of weight change on drug costs. Anticipated savings were then compared with the cost programme delivery. Analysis was carried out on patients with follow-up data at 12 and 24 months as well as on an intention-to-treat basis. Outcomes from Counterweight were based on the observed lost to follow-up rate of 50%, and the assumption that those patients would continue a generally observed weight gain of 1 kg per year from baseline.

Results The minimum annual cost of all drug prescriptions at BMI 20 kg/m2 was £50.71 for men and £62.59 for women. Costs were greater by £5.27 (men) and £4.20 (women) for each unit increase in BMI, to a BMI of 25 (men £77.04, women £78.91), then by £7.78 and £5.53, respectively, to BMI 30 (men £115.93 women £111.23), then by £8.27 and £4.95 to BMI 40 (men £198.66, women £160.73). The relationship between increasing BMI and costs for the top ten drugs was more pronounced. Minimum costs were at a BMI of 20 (men £8.45, women £7.80), substantially greater at BMI 30 (men £23.98, women £16.72) and highest at BMI 40 (men £63.59, women £27.16). Attributable cost of overweight and obesity accounted for 23% of spending on all drugs with 16% attributable to obesity. The cost of the programme was estimated to be approximately £60 per patient entered. Modelling weight reductions achieved by the Counterweight weight management programme would potentially reduce prescribing costs by £6.35 (men) and £3.75 (women) or around 8% of programme costs at one year, and by £12.58 and £8.70, respectively, or 18% of programme costs after two years of intervention. Potential savings would be increased to around 22% of the cost of the programme at year one with full patient retention and follow-up.

Conclusion Drug prescriptions rise from a minimum at BMI of 20 kg/m2 and steeply above BMI 30 kg/m2. An effective weight management programme in primary care could potentially reduce prescription costs and lead to substantial cost avoidance, such that at least 8% of the programme delivery cost would be recouped from prescribing savings alone in the first year.

Adoção de produtos e serviços baseados em tecnologia pelo consumidor : uma avaliação da aplicabilidade da Technology Readiness Index no contexto brasileiro

O estudo do comportamento de adoção de produtos e serviços baseados em tecnologia pelo consumidor tem representado um dos principais desafios para a área de marketing, pois, em meio à intensa proliferação destes produtos, diversos estudos apontam a crescente frustração do consumidor para interagir com a tecnologia. Tais evidências são especialmente importantes à medida que as crenças do consumidor estão positivamente relacionadas a sua aceitação ou resistência em adotar produtos e serviços tecnológicos. Nesse contexto, a prontidão para tecnologia emerge como constructo fundamental para o entendimento das atitudes do consumidor diante da tecnologia, e diz respeito à propensão dos indivíduos a adotar produtos e serviços tecnológicos a partir de condutores e inibidores mentais relacionados ao otimismo, inovatividade, desconforto e insegurança. A Technology Readiness Index (TRI) é o instrumento de medida desenvolvido por Parasuraman (2000) e Parasuraman & Colby (2001), para mensuração da prontidão para tecnologia dos consumidores. Este estudo teve como objetivo avaliar a aplicabilidade da TRI no contexto brasileiro, por meio da reaplicação do instrumento de medida a uma amostra de 731 consumidores, maiores de 18 (dezoito) anos, na cidade de Porto Alegre. Embora se tenha verificado uma estrutura subjacente à prontidão para tecnologia ligeiramente modificada, com 6 fatores, considera-se a TRI um instrumento válido para mensuração da prontidão para tecnologia dos consumidores. A qualidade da TRI foi comprovada através do exame da validade de conteúdo e de constructo. A validade de constructo foi verificada via avaliação da unidimensionalidade, confiabilidade, validade convergente e discriminante de cada dimensão da escala. Tal avaliação foi complementada com o exame da associação dos escores dos respondentes da TRI com as questões sobre posse e uso de produtos e serviços tecnológicos. Este estudo oferece algumas evidências sobre a capacidade da TRI de distinguir usuários de não usuários destes produtos e de predizer comportamentos de adoção.

Purchasing power parity: the choice of price index

Looking closely at the PPP argument, it states that the currencies purchasing power should not change when comparing the same basket goods across countries, and these goods should all be tradable. Hence, if PPP is valid at all, it should be captured by the relative price indices that best Öts these two features. We ran a horse race among six di§erent price indices available from the IMF database to see which one would yield higher PPP evidence, and, therefore, better Öt the two features. We used RER proxies measured as the ratio of export unit values, wholesale prices, value added deáators, unit labor costs, normalized unit labor costs and consumer prices, for a sample of 16 industrial countries, with quarterly data from 1975 to 2002. PPP was tested using both the ADF and the DFGLS unit root test of the RER series. The RER measured as WPI ratios was the one for which PPP evidence was found for the larger number of countries: six out of sixteen when we use DF-GLS test with demeaned series. The worst measure of all was the RER based on the ratio of foreign CPIs and domestic WPI. No evidence of PPP at all was found for this measure.