Visually Exploring Multivariate Trends in Patient Cohorts Using Animated Scatter Plots

2011 ◽  
pp. 139-148 ◽  
Author(s):  
Alexander Rind ◽  
Wolfgang Aigner ◽  
Silvia Miksch ◽  
Sylvia Wiltner ◽  
Margit Pohl ◽  
...  
Keyword(s):  
Scatter Plots

Descriptive statistics

2017 ◽  
Author(s):  
Andrew Gelman ◽  
Deborah Nolan
Keyword(s):  
Descriptive Statistics ◽  
Metabolic Rates ◽  
World Record ◽  
Linear Combinations ◽  
Record Times ◽  
Starting Point ◽  
Statistics Course ◽  
Scatter Plots ◽  
Economic Indexes ◽  
The Mean

Descriptive statistics is the typical starting point for a statistics course, and it can be tricky to teach because the material is more difficult than it first appears. The activities in this chapter focus more on the topics of data displays and transformations, rather than the mean, median, and standard deviation, which are covered easily in a textbook and on homework assignments. Specific topics include: distributions and handedness scores; extrapolation of time series and world record times for the mile run; linear combinations and economic indexes; scatter plots and exam scores; and logarithmic transformations and metabolic rates.

scholarly journals Comparison of Metrics Used to Track CLABSIs and CAUTIs Across a Regional Network

2020 ◽  
Vol 41 (S1) ◽  
pp. s178-s179
Author(s):  
Sonali Advani ◽  
Becky Smith ◽  
Jessica Seidelman ◽  
Nicholas Turner ◽  
Christopher Hostler ◽  
...  
Keyword(s):  
Negative Correlation ◽  
Urine Culture ◽  
Bloodstream Infections ◽  
Central Line ◽  
Regional Network ◽  
Community Hospitals ◽  
Scatter Plots ◽  
Preventable Harm ◽  
Device Use ◽  
Tract Infections

Background: The standardized infection ratio (SIR) is the nationally adopted metric used to track and compare catheter-associated urinary tract infections (CAUTIs) and central-line– associated bloodstream infections (CLABSIs). Despite its widespread use, the SIR may not be suitable for all settings and may not capture all catheter harm. Our objective was to look at the correlation between SIR and device use for CAUTIs and CLABSIs across community hospitals in a regional network. Methods: We compared SIR and SUR (standardized utilization ratio) for CAUTIs and CLABSIs across 43 hospitals in the Duke Infection Control Outreach Network (DICON) using a scatter plot and calculated an R2 value. Hospitals were stratified into large (>70,000 patient days), medium (30,000–70,000 patient days), and small hospitals (<30,000 patient days) based on DICON’s benchmarking for community hospitals. Results: We reviewed 24 small, 11 medium, and 8 large hospitals within DICON. Scatter plots for comparison of SIRs and SURs for CLABSIs and CAUTIs across our network hospitals are shown in Figs. 1 and 2. We detected a weak positive overall correlation between SIR and SUR for CLABSIs (0.33; R2 = 0.11), but no correlation between SIR and SUR for CAUTIs (−0.07; R2 = 0.00). Of 15 hospitals with SUR >1, 7 reported SIR <1 for CLABSIs, whereas 10 of 13 hospitals with SUR >1 reported SIR <1 for CAUTIs. Smaller hospitals showed a better correlation for CLABSI SIR and SUR (0.37) compared to medium and large hospitals (0.19 and 0.22, respectively). Conversely, smaller hospitals showed no correlation between CAUTI SIR and SUR, whereas medium and larger hospitals showed a negative correlation (−0.31 and −0.39, respectively). Conclusions: Our data reveal a weak positive correlation between SIR and SUR for CLABSIs, suggesting that central line use impacts CLABSI SIR to some extent. However, we detected no correlation between SIR and SUR for CAUTIs in smaller hospitals and a negative correlation for medium and large hospitals. Some hospitals with low CAUTI SIRs might actually have higher device use, and vice versa. Therefore, the SIR alone does not adequately reflect preventable harm related to urinary catheters. Public reporting of SIR may incentivize hospitals to focus more on urine culture stewardship rather than reducing device utilization.Funding: NoneDisclosures: None

scholarly journals Can stock–recruitment points determine which spawning potential ratio is the best proxy for maximum sustainable yield reference points?

2013 ◽  
Vol 70 (6) ◽  
pp. 1075-1080 ◽  
Author(s):  
Christopher M. Legault ◽  
Elizabeth N. Brooks
Keyword(s):  
Life History ◽  
Mortality Rate ◽  
Maximum Sustainable Yield ◽  
Reference Points ◽  
Sustainable Yield ◽  
Marine Science ◽  
Fishing Mortality ◽  
Scatter Plots ◽  
Stock Recruitment ◽  
Spawning Potential Ratio

Abstract Legault, C. M., and Brooks, E. N. 2013. Can stock–recruitment points determine which spawning potential ratio is the best proxy for maximum sustainable yield reference points? – ICES Journal of Marine Science, 70: 1075–1080. The approach of examining scatter plots of stock–recruitment (S–R) estimates to determine appropriate spawning potential ratio (SPR)-based proxies for FMSY was investigated through simulation. As originally proposed, the approach assumed that points above a replacement line indicate year classes that produced a surplus of spawners, while points below that line failed to achieve replacement. In practice, this has been implemented by determining Fmed, the fishing mortality rate that produces a replacement line with 50% of the points above and 50% below the line. A new variation on this approach suggests FMSY proxies can be determined by examining the distribution of S–R points that are above or below replacement lines associated with specific SPRs. Through both analytical calculations and stochastic results, we demonstrate that this approach is fundamentally flawed and that in some cases the inference is diametrically opposed to the method's intended purpose. We reject this approach as a tool for determining FMSY proxies. We recommend that the current proxy of F40% be maintained as appropriate for a typical groundfish life history.

scholarly journals Quantitative, Multi-institutional Evaluation of MR Thermometry Accuracy for Deep-Pelvic MR-Hyperthermia Systems Operating in Multi-vendor MR-systems Using a New Anthropomorphic Phantom

Cancers ◽  
2019 ◽  
Vol 11 (11) ◽  
pp. 1709 ◽  
Author(s):  
Curto ◽  
Aklan ◽  
Mulder ◽  
Mils ◽  
Schmidt ◽  
...  
Keyword(s):  
Hybrid Systems ◽  
Dose Effect ◽  
Institutional Evaluation ◽  
Anthropomorphic Phantoms ◽  
Contrast Magnetic Resonance ◽  
Scatter Plots ◽  
Conformal Heating ◽  
Probe Measurements ◽  
Eccentric Target ◽  
Good Agreement

Clinical outcome of hyperthermia depends on the achieved target temperature, therefore target conformal heating is essential. Currently, invasive temperature probe measurements are the gold standard for temperature monitoring, however, they only provide limited sparse data. In contrast, magnetic resonance thermometry (MRT) provides unique capabilities to non-invasively measure the 3D-temperature. This study investigates MRT accuracy for MR-hyperthermia hybrid systems located at five European institutions while heating a centric or eccentric target in anthropomorphic phantoms with pelvic and spine structures. Scatter plots, root mean square error (RMSE) and Bland–Altman analysis were used to quantify accuracy of MRT compared to high resistance thermistor probe measurements. For all institutions, a linear relation between MRT and thermistor probes measurements was found with R2 (mean ± standard deviation) of 0.97 ± 0.03 and 0.97 ± 0.02, respectively for centric and eccentric heating targets. The RMSE was found to be 0.52 ± 0.31 °C and 0.30 ± 0.20 °C, respectively. The Bland-Altman evaluation showed a mean difference of 0.46 ± 0.20 °C and 0.13 ± 0.08 °C, respectively. This first multi-institutional evaluation of MR-hyperthermia hybrid systems indicates comparable device performance and good agreement between MRT and thermistor probes measurements. This forms the basis to standardize treatments in multi-institution studies of MR-guided hyperthermia and to elucidate thermal dose-effect relations.

scholarly journals Geochemistry and Fuid-Inclusion Microthermometry of the Farsesh Barite Deposit, Iran

Geologos ◽  
2014 ◽  
Vol 20 (3) ◽  
pp. 201-214 ◽  
Author(s):  
Alireza Zarasvandi ◽  
Nazanin Zaheri ◽  
Houshang Pourkaseb ◽  
Abbas Chrachi ◽  
Hashem Bagheri
Keyword(s):  
Rare Earth ◽  
Rare Earth Elements ◽  
Open Space ◽  
Sea Water ◽  
Shear Zones ◽  
Major And Trace Elements ◽  
Petrographic Analysis ◽  
Two Phase ◽  
Moderate Salinity ◽  
Scatter Plots

Abstract The Permian carbonate-hosted Farsesh barite deposit is located southeast of the City of Aligudarz in the province of Lorestan, Iran. Structurally, this deposit lies in the Zagros metallogenic belt and the Sanandaj-Sirjan Zone. Barite mineralisations occur as open-space flling veins, and as massive and replacement ores along fractures, faults and shear zones of the Permian carbonate host rocks. In order to determine the structure, in addition to pe-trographic and fuid-inclusions studies, an ICP-MS analysis was carried out in order to measure the major as well as the trace and rare earth elements. The Farsesh barite deposit has a simple mineralogy, of which barite is the main mineral, followed by calcite, dolomite, quartz, and opaque minerals such as Fe-oxides. Replacement of bar-ite by calcite is common and is more frequent than space-flling mineralisation. Sulphide minerals are minor and mainly consist of chalcopyrite and pyrite, which are altered by weathering to covellite, malachite and azurite. Petrographic analysis and micro-thermometry were carried out on the two-phase liquid/vapour inclusions in ellipsoidal or irregularly shaped minerals ranging in size from 5–10 µm. The measurements were conducted on fuid inclusions during the heating and subsequent homogenisation in the liquid phase. The low homogenisation temperatures (200–125°C) and low to moderate salinity (4.2–20 eq wt% NaCl) indicate that the barite had precipitated from hydrothermal basinal water with low to moderate salinity. It appears from the major and trace elements that geochemical features such as Ba and Sr enrichment in the barite samples was accompanied by depletion of Pb, Zn, Hg, Cu and Sb. The geochemistry of the rare earth elements, such as low σREE concentrations, LREE-enrichment chondrite-normalised REE patterns, the negative Ce and positive Eu anomalies, the low Ce/La ratio and the positive La and Gd anomalies, suggest that the Farsesh barite was deposited from hydrothermally infuenced sea water. The Farsesh deposit contains low-temperature hydrothermal barite. The scatter plots of the barite (close to sea water) in different areas on the CeN/SmN versus CeN/YbN diagram support the possibility that the barite was formed from seawater-bearing hydrothermal fuids.

scholarly journals Cold trap dehydration in the Tropical Tropopause Layer characterized by SOWER chilled-mirror hygrometer network data in the Tropical Pacific

2012 ◽  
Vol 12 (9) ◽  
pp. 25833-25885 ◽  
Author(s):  
F. Hasebe ◽  
Y. Inai ◽  
M. Shiotani ◽  
M. Fujiwara ◽  
H. Vömel ◽  
...  
Keyword(s):  
Ice Nucleation ◽  
Tropical Pacific ◽  
Cold Trap ◽  
Mixing Ratio ◽  
Back Trajectories ◽  
Tropical Tropopause Layer ◽  
Tropical Tropopause ◽  
Scatter Plots ◽  
Cold Point ◽  
The Tropical Pacific

Abstract. A network of balloon-born radiosonde observations employing chilled-mirror hygrometers for water and electrochemical concentration cells for ozone has been operated since late 1990s in the Tropical Pacific trying to capture the progress of dehydration for the air parcels advected horizontally in the Tropical Tropopause Layer (TTL). The analyses of this dataset are made on isentropes taking advantage of the conservative properties of tracers in adiabatic motion. The existence of ice particles is diagnosed by lidars simultaneously operated with sonde flights. Characteristics of the TTL dehydration are presented on the basis of individual soundings and statistical features. Supersaturations close to 80% in the relative humidity with respect to ice (RHice) have been observed in subvisible cirrus clouds located near the cold point tropopause at extremely low temperatures around 180 K. Further observational evidence is needed to confirm the credibility of such high values of RHice. The progress of TTL dehydration is reflected in isentropic scatter plots between the sonde-observed mixing ratio (OMR) and the minimum saturation mixing ratio (SMRmin) along the back trajectories associated with the observed air mass. The supersaturation exceeding the critical value of the homogeneous ice nucleation (OMR > 1.6 × SMRmin) is frequently observed on 360 and 365 K surfaces indicating that the cold trap dehydration is under progress in the TTL. The near correspondence between the two (OMR ~ SMRmin) on 380 K on the other hand implies that this surface is not significantly cold for the advected air parcels to be dehydrated. Above 380 K, the cold trap dehydration would scarcely function while some moistening in turn occurs before the air parcels reach the lowermost stratosphere at around 400 K where OMR is generally smaller than SMRmin.

scholarly journals Comparison of SMMR and SSM/I passive microwave data collected over Antarctica

1993 ◽  
Vol 17 ◽  
pp. 131-136 ◽  
Author(s):  
Kenneth C. Jezek ◽  
Carolyn J. Merry ◽  
Don J. Cavalieri
Keyword(s):  
Brightness Temperature ◽  
Microwave Radiometer ◽  
Correlated Data ◽  
Data Sets ◽  
Microwave Brightness Temperature ◽  
Brightness Temperatures ◽  
Scatter Plots ◽  
Microwave Imager ◽  
Highly Correlated ◽  
The Antarctic

Spaceborne data are becoming sufficiently extensive spatially and sufficiently lengthy over time to provide important gauges of global change. There is a potentially long record of microwave brightness temperature from NASA's Scanning Multichannel Microwave Radiometer (SMMR), followed by the Navy's Special Sensor Microwave Imager (SSM/I). Thus it is natural to combine data from successive satellite programs into a single, long record. To do this, we compare brightness temperature data collected during the brief overlap period (7 July-20 August 1987) of SMMR and SSM/I. Only data collected over the Antarctic ice sheet are used to limit spatial and temporal complications associated with the open ocean and sea ice. Linear regressions are computed from scatter plots of complementary pairs of channels from each sensor revealing highly correlated data sets, supporting the argument that there are important relative calibration differences between the two instruments. The calibration scheme was applied to a set of average monthly brightness temperatures for a sector of East Antarctica.

scholarly journals Relationship Between Carcass Weight, Muscle, Fat, and Predicted Lean Yield for Commercial Pigs in Ontario

2019 ◽  
Vol 3 (2) ◽  
Author(s):  
R. S. Barducci ◽  
Z. Zhou ◽  
D. Tulpan ◽  
B. M. Bohrer
Keyword(s):  
Negative Correlation ◽  
Correlation Coefficients ◽  
Carcass Weight ◽  
Linear Regression Models ◽  
Strong Negative Correlation ◽  
Statistical Software ◽  
Carcass Parameters ◽  
Scatter Plots ◽  
Positive Correlations ◽  
Meaningful Relationships

ObjectivesGreater knowledge of variance and relationships of pork carcass parameters could be used to improve performance, efficiency, and profitability of the pork industry. Previous research has investigated the correlation between pork carcass parameters; however, there are still many misunderstandings, particularly in commercially representative pigs. Thus, the purpose of this study was to examine the correlation and variance of carcass weight, fat depth, muscle depth, and predicted lean yield in commercial pigs.Materials and MethodsThe second largest commercial pig slaughter facility in Ontario slaughtered approximately 1.5 million pigs in 2018. Carcass data (hot carcass weight, fat depth, muscle depth, and predicted lean yield) from 1025,572 pigs was used for this study with pigs slaughtered on each production day of 2018 (between January 2, 2018 and December 31, 2018). Hot carcass weight was reported immediately following slaughter as a head-on weight, and fat depth and muscle depth were measured with a Destron PG-100 probe (International Destron Technologies, Markham, Ontario). The equation used for predicted lean yield was the Canadian Lean Yield equation (CLY (%) = 68.1863– (0.7833 × fat depth) + (0.0689 × muscle depth) + (0.0080 × fat depth2) – (0.0002 × muscle depth2) + (0.0006 × fat depth × muscle depth). Pearson product moment correlation coefficients were calculated among all parameters using RStudio version 1.1.456 and R version 3.5.1 statistical software. Correlation coefficients were considered significantly different from 0 at P < 0.05. Correlations were considered weak (in absolute value) for r < 0.35, moderate for 0.36 ≤ r ≤ 0.67, and strong for r ≥ 0.68. Linear regression models were created between parameters that had meaningful relationships using the RStudio statistical software. Gnuplot version 5.2 was used to create scatter plots to allow for better visualization of the correlation between meaningful parameters.ResultsThe mean ± standard deviation for fat depth, muscle depth, hot carcass weight, and predicted lean yield were 18.27 ± 4.12 mm, 65.69 ± 9.06 mm, 105.93 ± 8.39 kg, and 61.03 ± 1.91%, respectively. We observed weak positive correlations between fat depth and hot carcass weight (r = 0.27; P < 0.0001), and between muscle depth and hot carcass weight (r = 0.17; P < 0.0001). We obtained a weak negative correlation between predicted lean yield and hot carcass weight (r = –0.21; P < 0.0001). The predicted lean yield equation used for this set of pigs included measurements for fat depth and muscle depth, so strong correlation between these parameters was expected. We obtained a moderate positive correlation between muscle depth and predicted lean yield (r = 0.39; P < 0.0001) and a strong negative correlation between fat depth and predicted lean yield (r = –0.96; P < 0.0001).ConclusionResults from this dataset revealed that hot carcass weight was generally not correlated with fat depth, muscle depth, or predicted lean yield. The conclusion of this study based on the current dataset is that pigs do not reach a weight threshold where they consistently become fatter or heavier muscled.

scholarly journals Spatial and temporal variations of K Ca II line profile shapes in different structures of the solar chromosphere. I. Features of individual profiles

2018 ◽  
Vol 4 (4) ◽  
pp. 3-13
Author(s):  
Ирина Турова ◽  
Irina Turova ◽  
София Григорьева ◽  
Sofiya Grigoryeva ◽  
Ольга Ожогина ◽  
...  
Keyword(s):  
Temporal Variations ◽  
Disk Center ◽  
Spatial And Temporal Variations ◽  
Solar Chromosphere ◽  
Line Profiles ◽  
Thermodynamic Conditions ◽  
Characteristic Points ◽  
Scatter Plots ◽  
The Difference ◽  
Individual Profiles

We have studied Ca II K line profiles, using two time series of spectrograms taken in two regions near the solar disk center. In each of the regions, the spectrograph slit cut out several areas of the quiet region and a plage. For the selected chromospheric structures, we have derived K line profiles and have defined a number of parameters that characterize the spatial and temporal variations of the profiles. The analysis of profile shapes in different structures belonging to the same moment of time has shown that there are structures whose profiles differ only slightly from each other in the photosphere, but differ dramatically in the chromosphere. The structures begin to differ from the level of formation of K1 and continue to differ further in the chromosphere. There are, however, structures which begin to differ at the level of the photosphere and continue to differ in the chromosphere. The difference between profile shapes in different structures is likely to be associated both with different thermodynamic conditions and with different magnetic field topology at a given point at a given time. We have examined temporal variations of the K Ca II line profiles in structural chromospheric elements, which are caused by the process of K2v-grains. In most of the studied areas of the chromospheric structures, the brightening of the K2v peak develops according to the “common” scenario: at the time of maximum bright-ness, the line shifts toward the red side. There are, however, cases when the brightening of the K2v peak occurs with a shift of the line to the violet side or with no shift at all. We have constructed scatter plots for some pairs of profile parameters related to intensities at characteristic points of the profile and their shifts. A correlation has been found between intensities in the center and wings of the K line. The correlation between shifts of the K2v and K2r peaks is very weak or completely absent.

Sign in / Sign up

Export Citation Format

Share Document