The prediction of response to selection in breeding programmes when all daughters of selected parents are retained.
Explore the source record for details and available documents.
Animals↗
Biomedical subjects
D Machin
Publications and source records attributed to D Machin.
More thoughts about Salmon.
Explore the source record for details and available documents.
Hospital Administration↗
Incomplete quality of life data in randomized trials: missing items.
Missing data has been a problem in many quality of life studies. This paper focuses upon the issues involved in handling forms which contain one or more missing items, and reviews the alternative procedures. One of the most widely practised approaches is imputation using the mean of all observed items in the same subscale. This, together with the related estimation of the subscale score, is based upon traditional psychometric approaches to scale design and analysis. We show that it may be an inappropriate method for many of the items in quality of life questionnaires, and would result in biased or misleading estimates. We provide examples of items and subscales which violate the psychometric foundations that underpin simple mean imputation. A checklist is proposed for examining the adequacy of simple imputation, and some alternative procedures are indicated.
Female↗
Incomplete quality of life data in randomized trials: missing forms.
Analysing quality of life (QOL) data may be complicated for several reasons, such as: repeated measures are obtained; data may be collected on ordered categorical responses; the instrument may have multidimensional scales, and complete data may not be available for all patients. In addition, it may be necessary to integrate QOL with length of life. The major undesirable effects of missing data, in QOL research, are the introduction of biases due to inadequate modes of analysis and the loss of efficiency due to reduced sample sizes. Currently, there is no standard method for handling missing data in QOL studies. In fact, there are very few references to methods of handling missing data in this context. The aim of this paper is to provide an overview of methods for analysing incomplete longitudinal QOL data which have either been presented in the QOL literature or in the missing data literature. These methods of analysis include complete case, available case, summary measures, imputation and likelihood-based approaches. We also discuss the issue of bias and the need for sensitivity analyses.
Bias↗
Suggestions for the presentation of quality of life data from clinical trials.
Quality of life (QOL) data is complex since it is both multidimensional and longitudinal. This complexity is compounded with its unbalanced nature through missing observations as a consequence of patient non-compliance with assessment schedules, and, for example, in cancer clinical trials data absence due to patient attrition often through death. QOL data poses difficulties for presentation and analysis and hence interpretation. This paper illustrates, using data from a randomized trial of the United Kingdom Medical Research Council Lung Cancer Working Party, a step-by-step approach to presentation of QOL data. This begins with a description of compliance and its relationship with patient attrition caused by death, to a final summary profile to indicate change over time. We recognize that no single summary statistic is likely to be able to encapsulate all the subtleties of QOL data. We stress the importance of examining data graphically before performing detailed analysis and also to facilitate interpretation in the final clinical report. Although a description of analytical methods is not the purpose of this paper, we draw attention to the need for imputing missing values and to the (multi-level) modelling approach to summarizing the data, both essential adjuncts to the less formal methods described here.
Authorship↗
On the standard error of the probability of a particular diagnosis.
Approximate standard errors of the probability of a particular diagnosis are given for the predictive and estimative methods described by Aitchison and Dunsmore. An example used in the detection of carriers of Duchenne muscular dystrophy (DMD) is given for illustration.
Diagnosis↗
The use of logit models to investigate social and biological factors in infant mortality. I: Methodology.
Infant mortality data for England and Wales, cross classified by mother's age, parity and social class, have been published on two occasions, the first giving the relevant data for 1949/50, the second for 1975, some 25 years later. Published analyses of these separate data sets have been based on graphical and tabular methods. This paper describes the statistical methodology appropriate to the use of logit models to investigate these data sets and shows how such models may be used to supplement the more informal approach. The stillbirth data for 1975 are used for illustration. Paper II, which follows, explores the stillbirth data in greater detail, with emphasis on the changes between 1949/50 and 1975. Subsequent papers describe neonatal and post-neonatal deaths using the same framework. A final paper summarizes the overall changes in infant mortality by means of a multilogit model.
Adolescent↗
The use of logit models to investigate social and biological factors in infant mortality. II: Stillbirths.
Infant mortality data for England and Wales cross-classified by mother's age, parity and social class have only been published for 1949/50 and 1975. Appropriate statistical methodology for the analysis of such data has been described in Paper I, which used the 1975 stillbirth data for illustration. This paper examines the stillbirth data from both years by formally incorporating the year of data collection into the statistical model, enabling changes in the age, parity and social class effects with time to be investigated. Despite a marked reduction in stillbirth mortality from 21.1 to 10.1 per thousand over the period, the relative contribution of social class has increased. In particular there has been a relative increase in risk for mothers in the lower social classes. By contrast the effects of age and parity, although remaining important, have diminished over the period.
Adolescent↗
The use of logit models to investigate social and biological factors in infant mortality. III. Neonatal mortality.
Infant mortality data for England and Wales, cross-classified by mother's age, parity and social class have been published on two occasions, the first giving the relevant data for 1949/50, the second for 1975, some 25 years later. Published analyses of these separate data sets have been based on graphical and tabular analysis. This paper develops the methodology from an earlier paper by Murrells et al. to the analysis of the neonatal data.
Adolescent↗
The use of logit models to investigate social and biological factors in infant mortality. IV: Post-neonatal mortality.
Infant mortality data for England and Wales, cross-classified by mother's age, parity and social class have been published on two occasions, the first giving the relevant data for 1949/50, the second for 1975, some 25 years later. Published analyses of these separate data sets have been based on graphical and tabular analysis. This paper describes the application of logit models using the methodology presented by Murrells et al. to investigate post-neonatal deaths.
Adolescent↗
Multiple comparisons in disease mapping.
Explore the source record for details and available documents.
Adult↗
Pain control in a randomized, controlled, clinical trial comparing moist exposed burn ointment and conventional methods in patients with partial-thickness burns.
Conventional management of partial-thickness burn wounds includes the use of paraffin gauze dressing, frequently with topical silver-based antibacterial creams. Some creams form an overlying slough that renders wound assessment difficult and are painful upon application. An alternative to conventional management, moist exposed burn ointment (MEBO), has been proposed as a topical agent that may accelerate wound healing and have antibacterial and analgesic properties. One hundred fifteen patients with partial-thickness burns were randomly assigned to conventional (n = 58) or MEBO treatment (n = 57). A verbal numerical rating score of pain was made in the morning, after burn dressing, and some 8 hours later. Patient pain profiles were summarized by locally weighted regression smoothing technique curves and the difference between treatments estimated using multilevel regression techniques. Mean verbal numerical rating scale pain levels (cm) in week 1 for all patients were highest at 3.2 for the after dressing assessment, lowest in the evening at 2.6, and intermediate in the morning at 3.0. This pattern continued at similar levels in week 2 and then declined by a mean of 0.5 in all groups in week 3. There was little evidence to suggest a difference in pain levels by treatment group with the exception of the postdressing pain levels in the first week when those receiving MEBO had a mean level of 0.7 cm (95% confidence interval, 0.2 to 1.1) lower than those on conventional therapy. MEBO appeared to bring greater pain relief for the postdressing assessment during the first week after burns. This initial relief, together with comparable pain levels experienced on other occasions, indicates that MEBO could be an alternative to conventional burns management.
Administration, Topical↗
Analysis of thermal parameters obtained during phase III trials of hyperthermia as an adjunct to radiotherapy in the treatment of breast carcinoma.
An analysis of 351 HT treatment sessions administered to 101 patients receiving radiotherapy and hyperthermia (RT + HT) who were entered into Phase III concurrent randomized trials for recurrent (BrR) and intact (BrI) breast tumours is presented. A complete response (CR) was recorded in 50 of 84 (59.5%) fields in the case of recurrent breast patients and in 10 of 17 (59%) fields in the case of the intact breast patients. In comparison, 15 of 60 (25%) patients entered into BrR who received RT alone and 8 of 12 (66.7%) patients receiving RT alone entered into BrI trial achieved CR. A set of thermal parameters is defined and evaluated on a treatment by treatment basis. Patient and tumour characteristics influential on CR are identified and thermal parameters which have additional prognostic value are investigated. Multivariate logistic analysis of the non-thermal data showed that maximum depth of tumour, presence or history of disease outside the treated area and RT regimen were most influential on CR. Tumour volume (cm3) (OR = 0.996, 95% CI = 0.993-1.004, p = 0.08) was not a strong prognostic covariate; tumour area and linear dimensions were even less significant (p = 0.41). The cumulative minimum thermal isoeffect dose (equivalent minutes at 43 degrees C) accrued over the 1st, 1st and 2nd, and 1st, 2nd and 3rd treatment sessions was the only thermal parameter to exhibit an association with CR consistently, Other thermal parameters found to contribute to the predictive models were MINTIME > 42 degrees C calculated for the first treatment session and %sensors > 43 degrees C (peak) calculated for the 2nd treatment session.
Aged↗
Risk factors and transfusion requirements in aortic surgery.
An audit of heterologous blood usage was made on 169 of 185 successive patients undergoing aortic surgery with a view to identifying factors determining individual transfusion requirements. The use of knitted prostheses was associated with 1.4 units, and aneurysmal disease 1.0 units of extra transfusion. Other factors influencing extra transfusion requirements were presence of hypertension, diabetes mellitus and low preoperative haemoglobin values. Clearly, if appropriate, the use of woven grafts seems worthwhile in terms of reduced transfusion requirements. However, individual prediction of patient transfusion requirements does not appear feasible with the factors studied.
Aortic Aneurysm↗
[Lymphedema after modified radical mastectomy as performed at the Bordet Institute. A report of 60 cases (author's transl)].
Three hundred and fifteen patients who underwent a radical mastectomy between 1969 and 1976 were studied. Nineteen percent developed lymphedema of the upper limb. Ten percent were resistant to all forms of therapy while the pathology gradually subsided in 9%. The causes of lymphedema as well as the preventive and curative methods were statistically studied and compared with those in the literature. Several preventive measures are proposed, in particular, the modified radical mastectomy.
Female↗