The risk factors for stunting incidence involve categorical data in both the response and predictor variables. Therefore, we developed a sparse categorical principal component logistic regression model capable of handling data with multicollinearity. The parameters of the sparse categorical principal component logistic regression model were estimated using the maximum likelihood method and the Newton-Raphson iterative approach. The analysis yielded a likelihood ratio value of 144.81 and a chi-square statistic value of 11.07, indicating that all factors included in the model are statistically significant. The results highlight that medical history, inadequate complementary feeding, formula feeding, lack of complementary feeding programs, and lack of iron supplementation for mothers are highly associated with the risk of stunting in toddlers. This emphasizes the need for attention to maternal nutrition from pregnancy through breastfeeding, as well as the nutrition of the toddler. Some important points proposed in this method are:•Stunting data consists of categorical variables containing multicollinearity.•The method applied is sparse logistic regression combined with categorical principal component analysis.•Analysis of risk factors for stunting in toddlers is based on the child's own condition, as well as parental factors, namely age, education, and intake of additional food and supplementary tablets during pregnancy.

This paper is a longitudinal study using a nonparametric regression model to identify changes in platelet count from dengue fever. Changes in platelet counts were analyzed based on treatment time and hematocrit count factors. The estimator method proposed is spline polynomial truncated bipredictor. Based on the results of the simultaneous model estimation, we obtained GCV = 714.72 and R2 = 95.9%, it means the model is feasible to explain and identify changes in platelet count based on the time of treatment and the number of hematocrit from DBD patients. Based on the data, there are four patterns of platelet change based on time of treatment and three patterns of platelet change based on hematocrit that are different from each other.Abstrak:Paper ini merupakan studi longitudinal dengan menggunakan model regresi nonparametrik untuk mengidentifikasi perubahan jumlah trombosit demam berdarah. Perubahan jumlah trombosit dianalisis berdasarkan faktor waktu perawatan dan jumlah hematokrit. Metode estimator yang diusulkan adalah spline polynomial truncated bi prediktor. Berdasarkan hasil taksiran model simultan diperoleh GCV = 714,72 dan R² = 95,9%, artinya model layak untuk menjelaskan dan mengidentifikasi perubahan jumlah trombosit berdasarkan waktu perawatan dan jumlah hematokrit pasien DBD. Berdasarkan data, terdapat empat pola perubahan trombosit berdasarkan waktu perawatan dan tiga pola perubahan trombosit berdasarkan hematokrit yang berbeda satu sama lain.

Estimates from confidence intervals are more powerful than point estimates, because there are intervals for parameter values used to estimate populations. In relation to global conditions, involving issues such as type 2 diabetes mellitus, it is very difficult to make estimations limited to one point only. Therefore, in this article, we estimate confidence intervals in a truncated spline model for type 2 diabetes data. We use a non-parametric regression model through a multi-variable spline linear estimator. The use of the model results from the irregularity of the data, so it does not form a parametric pattern. Subsequently, we obtained the interval from beta parameter values for each predictor. Body mass index, HDL cholesterol, LDL cholesterol and triglycerides all have two regression coefficients at different intervals as the number of the found optimal knot points is one. This value is the interval for multivariable spline regression coefficients that can occur in a population of type 2 diabetes patients.

Penalized spline criteria involve the function of goodness of fit and penalty, which in the penalty function contains smoothing parameters. It serves to control the smoothness of the curve that works simultaneously with point knots and spline degree. The regression function with two predictors in the non-parametric model will have two different non-parametric regression functions. Therefore, we propose the use of two smoothing parameters in the bi-variate predictor non-parametric regression model. We demonstrated its ability through longitudinal data simulation studies with a comparison of one smoothing parameter. It was done on several numbers of subjects with repeated measurements. The generalized cross validation value which is a measure of the model's ability is poured through the box plot. The results show that the use of two smoothing parameters is more optimal than one smoothing parameter. It was seen through a smaller generalized cross validation value on the use of two smoothing parameters. Application of blood sugar level data for patients with two smoothing parameters produced a penalized spline bi-variate predictor regression model with several segments of change patterns. There are five patterns at the time of treatment and blood pressure with the number of smoothing parameters is two, namely 0.39 and 0.73.

Background: Blood sugar and lifestyle problems have long been problems in diabetes. There has also been a lot of research on that. However, we see that diabetic patients are still increasing even though many patients are not aware of the start of the disease occurrence. Therefore, we consider it very important to examine these two main problems of diabetes by using a more flexible statistical approach to obtain more specific results regarding the patient's condition. Objective: The form of data for type 2 diabetes patients is repeated measurements so that it is approached through longitudinal studies. We investigated various intervals of pattern change that can occur in blood glucose, namely fasting, random, and 2 hours after meals based on blood pressure and carbohydrate diets in diabetic patients in South Sulawesi Province, Indonesia. Methods: This research is a longitudinal study proposing a flexible and accurate statistical approach. It is a weighted spline multi-response nonparametric regression model. This model is able to detect any pattern of changes in irregular data in large dimensions. The data were obtained from Hasanuddin University Teaching Hospital in South Sulawesi Province, Indonesia. The number of samples analyzed was 418 from 50 patients with different measurements. Results: The optimal spline model was obtained at 2 knots for blood pressure and 3 knots for carbohydrate diets. There are three blood pressure intervals that give different patterns of increase in patient blood glucose levels, namely below 126.6 mmHg, 126.6-163.3 mmHg, and above 163.3 mmHg. It was found that blood sugar rose sharply at blood pressure above 163.3 mmHg. Furthermore, there are four carbohydrate diet intervals that are formed, which are below 118.6 g, 118.6-161.8 g, 161.8-205 g, and above 205 g. The result is that blood sugar decreased significantly at intervals of carbohydrate diet 161.8-205 g. Conclusion: Blood glucose increases with a very high increase in blood pressure, whereas for a carbohydrate diet, there is no guarantee that a high diet will be able to reduce blood glucose significantly. This may be affected by the patient's saturation of a very high carbohydrate diet. Keywords: Blood glucose, blood pressure, carbohydrate diet, multi-response, nonparametric regression, spline