Experimental data can broadly be divided in discrete or continuous data. Continuous data are obtained from measurements that are performed as a function of another quantitative variable, e.g., time, length, concentration, or wavelength. The results from these types of experiments are often used to generate plots that visualize the measured variable on a continuous, quantitative scale. To simplify state-of-the-art data visualization and annotation of data from such experiments, an open-source tool was created with R/shiny that does not require coding skills to operate it. The freely available web app accepts wide (spreadsheet) and tidy data and offers a range of options to normalize the data. The data from individual objects can be shown in 3 different ways: (1) lines with unique colors, (2) small multiples, and (3) heatmap-style display. Next to this, the mean can be displayed with a 95% confidence interval for the visual comparison of different conditions. Several color-blind-friendly palettes are available to label the data and/or statistics. The plots can be annotated with graphical features and/or text to indicate any perturbations that are relevant. All user-defined settings can be stored for reproducibility of the data visualization. The app is dubbed PlotTwist and runs locally or online: https://huygens.science.uva.nl/PlotTwist

The recent surge in enthusiasm for simultaneously inferring relationships from extinct and extant species has reinvigorated interest in statistical approaches for modelling morphological evolution. Current statistical methods use the Mk model to describe substitutions between discrete character states. Although representing a significant step forward, the Mk model presents challenges in biological interpretation, and its adequacy in modelling morphological evolution has not been well explored. Another major hurdle in morphological phylogenetics concerns the process of character coding of discrete characters. The often subjective nature of discrete character coding can generate discordant results that are rooted in individual researchers' subjective interpretations. Employing continuous measurements to infer phylogenies may alleviate some of these issues. Although not widely used in the inference of topology, models describing the evolution of continuous characters have been well examine...

Based on the context of your article, your target labels are Efficiency Ratio and Quality Maintenance Ratio, which are continuous variables derived from multiple factors such as fuel consumption, logistics costs, spoilage, and supply chain bottlenecks.

These labels are not binary, as they represent ratios that indicate performance and quality metrics in agricultural logistics and supply chain management. The values of these ratios are continuous and are used for regression tasks, rather than classification tasks with binary outputs.

So, your article is focused on predicting these continuous values rather than performing binary classification.

You said: write description of the dataset along iwth features it is downloaded form EURO crops etc like that

ChatGPT said: ChatGPT The dataset used in this research was obtained from a large-scale agricultural logistics study conducted across European farms, specifically focusing on key regions known for extensive crop production, such as France, Germany, and the Netherlands. The dataset, named EURO Crops Agricultural Logistics Dataset, contains detailed records of various logistical operations, environmental conditions, and product quality metrics across multiple agricultural supply chains. It spans from June 2018 to June 2024, with hourly data collected from IoT-enabled sensors and GPS devices installed on vehicles, storage units, and monitoring stations.

The dataset includes a total of 53,305 records, with data points capturing critical aspects of agricultural logistics operations, such as transportation efficiency, storage conditions, and product quality. The information is collected in real-time through IoT sensors deployed across the logistics network, tracking the movement and conditions of agricultural products. The data also encompasses environmental monitoring systems, providing insights into weather patterns, soil conditions, and crop health.

The key features of the dataset include:

Vehicle_Type: Categorical data indicating the type of vehicle used for transportation (e.g., Truck, Van). Crop_Type: Categorical data specifying the type of crops being transported (e.g., Wheat, Corn, Rice). Harvest_Date: Date indicating when the crops were harvested. Crop_Yield: Quantitative data showing the total yield of the crop (in kilograms). Storage_Temperature: Continuous data representing the temperature inside the storage unit (in degrees Celsius). Storage_Humidity: Continuous data representing the humidity levels inside the storage unit (in percentage). Fuel_Consumption: Continuous data indicating the amount of fuel used during transportation (in liters per 100 km). Route_Distance: Continuous data showing the total distance covered by the vehicle (in kilometers). Delivery_Time: Continuous data representing the total time taken for the delivery (in hours). Traffic_Level: Continuous data showing the level of traffic congestion on the route (on a scale of 0 to 100). Temperature: Environmental temperature during transportation (in degrees Celsius). Humidity: Environmental humidity during transportation (in percentage). Vehicle_Load_Capacity: The total load capacity of the vehicle (in kilograms). Vibration_Level: Data from sensors measuring the vibration experienced during transportation, which affects crop quality (in arbitrary units). Queue_Time: Time spent in queues or waiting during transit (in hours). Weather_Impact: Index measuring the impact of weather conditions on logistics operations (e.g., heavy rain, wind, etc.). Station_Capacity: Storage capacity of the distribution or logistics station (in kilograms). Operational_Cost: The total cost of logistics operations, including fuel, labor, and storage costs (in USD). Energy_Consumption: Total energy consumption of storage and transportation units (in kWh). IoT_Sensor_Reading_Temperature: Continuous data from IoT sensors monitoring the temperature of the crops during transit (in degrees Celsius). IoT_Sensor_Reading_Humidity: Continuous data from IoT sensors monitoring the humidity of the crops during transit (in percentage). IoT_Sensor_Reading_Light: Continuous data from IoT sensors monitoring light exposure during transportation (in lumens). Warehouse_Storage_Time: Time spent by the crops in warehouse storage before further transportation (in days). Inventory_Levels: Current inventory levels at various storage facilities (in units). Fuel_Costs: Cost of fuel consumed during transportation (in USD per liter). Spoilage_Risk: Probability of spoilage during transportation, based on environmental and operational conditions (as a percentage). The target labels in the dataset include:

Efficiency Ratio: A composite ratio calculated based on fuel consumption, logistics costs, and delivery times, aimed at measuring the overall efficiency of the logistics operation. Quality Maintenance Ratio: A ratio derived from spoi...

A quantitative continuous variable that reflects the risk of tree dieoff during a significant drought period (SPI48 drought = -2).

Many aspects of morphological phylogenetics are controversial in the theoretical systematics literature and yet are often poorly explained and justified in empirical studies. In this paper, I argue that most morphological characters describe variation that is fundamentally quantitative, regardless of whether it is coded qualitatively or quantitatively by systematists. Given this view, three fundamental problems in morphological character analysis (character state definition, delimitation, and ordering) may have a common solution: coding morphological characters as continuous quantitative traits. A new parsimony method (step-matrix gap-weighting, a modification of Thiele's approach) is proposed that allows quantitative traits to be analyzed as continuous variables. The problem of scaling or weighting quantitative characters relative to qualitative characters (and to each other) is reviewed, and three possible solutions are described. The new coding method is applied to data from hoplocer...

Supplementary R scriptsSupplementary R scripts for figures of "Antagonistic coevolution between quantitative and Mendelian traits" by Yamamichi and Ellner.SupplementaryRfile.tar

Files and code for the STM runs, plus code for the enhanced STM continuous-variable graphic

We hypothesized that (1) correlation of (A) the output of instrumentation to generate quantitative continuous measurements of movements and (B) the quantitative measurements of trained examiners using structured ratings of movements would generate the tools to differentiate the movements of (A) Parkinson's disease (PD), (B) parkinsonian syndromes, and health, and (2) continuous quantitative measurements of movements would improve the ratings generated by visual observations of trained raters, and provide pathognomonic signatures to identify PD and parkinsonian syndromes.

A protocol for a low-cost quantitative continuous measurement of movements in the extremities of people with PD (McKay, et al., 2019) was administered to people with PD and multiple system atrophy-parkinsonian type (MSA-P) and age- and sex-matched healthy control participants. Data from instrumentation was saved as WinDaq files (Dataq Instruments, Inc., Akron, Ohio) and converted into Excel files (McKay, et al., 2019) using the WinDaq Waveform Data Browser (Dataq Instruments, Inc., Akron, Ohio).

Participants were asked to sit in a straight-back chair with arms approximately six inches from the wall to minimize the risk of hitting the wall. The examiner sat in a similar chair facing the participant. The examiner asked the technologist and the videographer to begin recording immediately before instructing the participant to perform each item.

Items were scored live by the examiner at the same time that the quantitative continuous measurements of movements were recorded by the instrumentation.

Healthy control participants were matched for age and sex with participants with PD. The key identifies the diagnosis (PD = Parkinson's disease, MSA-P = Multiple system atrophy - parkinsonian type, HC = healthy control, 1 = male, 0 = female). Participants with PD completed a single test session (0002, 0005, 0007-0009, 0012, 0017-0018, and 0021), a test and a retest session (0001, 0003, 0006, 0010-0011, 0013, 0015, 0019, 0022-0023), or a test and two retest sessions (0014). HC participants completed test and retest sessions (0020, 0024-0030). A participant with MSA-P (0004) completed a test session. Individual files for the WinDaq, Excel, and coding forms for each testing are entered in the dataset. The Excel files for the five repetitive items were converted to fast Fourier transforms (FFTs) and continuous wavelet transforms (CWTs) (MatLab).

None of the files underwent filtering.

Healthy participants exhibited some of the features of disease.

The data provide the basis to determine how a session may predict future performance.

Quantitative Research AI Market Outlook

According to our latest research, the global Quantitative Research AI market size reached USD 1.82 billion in 2024, reflecting robust expansion in the adoption of artificial intelligence for quantitative analysis across industries. The market is expected to grow at a CAGR of 27.6% during the forecast period, with the forecasted market size anticipated to reach USD 16.34 billion by 2033. This significant growth is driven by the increasing demand for advanced data analytics, automation in research processes, and the expanding scope of AI technologies in both academic and commercial quantitative research.

The primary growth driver for the Quantitative Research AI market is the surging volume of data generated across industries and the need for sophisticated tools to extract actionable insights. Organizations are increasingly leveraging AI-powered quantitative research tools to process large datasets efficiently, identify patterns, and predict future trends with higher accuracy. These capabilities are particularly valuable in sectors such as financial services, healthcare, and market research, where data-driven decision-making is critical. The integration of machine learning algorithms and natural language processing further enhances the ability of AI systems to handle complex quantitative tasks, reducing the time and resources required for traditional research methodologies.

Another significant factor contributing to market growth is the rising adoption of cloud-based AI solutions. Cloud deployment offers scalability, flexibility, and cost-effectiveness, enabling organizations of all sizes to access advanced quantitative research tools without the need for substantial upfront investments in infrastructure. The proliferation of AI-as-a-Service (AIaaS) models has democratized access to powerful quantitative research capabilities, allowing even small and medium enterprises (SMEs) to benefit from AI-driven insights. Additionally, continuous advancements in AI hardware, such as specialized processors and accelerators, are further propelling the market by improving the performance and efficiency of AI applications in quantitative research.

The increasing focus on personalized and precision-driven research in industries such as healthcare and finance is also fueling the demand for AI-based quantitative research solutions. In healthcare, for instance, AI-driven quantitative analysis is transforming clinical trials, epidemiological studies, and patient data management, leading to more accurate diagnoses and treatment plans. Similarly, financial institutions are leveraging AI for quantitative trading, risk assessment, and fraud detection. The growing recognition of AI's potential to enhance research accuracy, reduce human error, and accelerate discovery is prompting organizations to invest heavily in quantitative research AI technologies.

From a regional perspective, North America currently dominates the Quantitative Research AI market, accounting for the largest share in 2024, followed closely by Europe and Asia Pacific. The presence of leading technology providers, a mature research ecosystem, and substantial investments in AI R&D are key factors supporting market growth in these regions. Asia Pacific is expected to witness the fastest CAGR during the forecast period, driven by rapid digital transformation, increasing government initiatives to promote AI adoption, and the emergence of innovative startups. Meanwhile, Latin America and the Middle East & Africa are gradually catching up, supported by growing awareness and investments in AI-powered research solutions. These regional dynamics underscore the global nature of the market and the diverse opportunities for growth across different geographies.

Component Analysis

The Component segment of the Quantitative Research AI market is broadly categorized into Software, Hardware, and Services, each playing a vital role in the overall ecosystem. Software represents the largest share of the market, as AI-driven quantitative research platforms and analytics tools are fundamental to the digital transformation of research methodologies. These software solutions encompass machine learning frameworks, data visualization tools, statistical analysis packages, and specialized AI algorithms tailored for quantitative research. The continuous evolution of AI software, coupled with advancements i

Despite strong interest in how noise affects marine mammals, little is known about the most abundant and commonly exposed taxa. Social delphinids occur in groups of hundreds of individuals that travel quickly, change behavior ephemerally, and are not amenable to conventional tagging methods, posing challenges in quantifying noise impacts. We integrated drone-based photogrammetry, strategically-placed acoustic recorders, and broad-scale visual observations to provide complimentary measurements of different aspects of behavior for short- and long-beaked common dolphins. We measured behavioral responses during controlled exposure experiments (CEEs) of military mid-frequency (3-4 kHz) active sonar (MFAS) using simulated and actual Navy sonar sources. We used latent-state Bayesian models to evaluate response probability and persistence in exposure and post-exposure phases. Changes in sub-group movement and aggregation parameters were commonly detected during different phases of MFAS CEEs but not control CEEs. Responses were more evident in short-beaked common dolphins (n=14 CEEs), and a direct relationship between response probability and received level was observed. Long-beaked common dolphins (n=20) showed less consistent responses, although contextual differences may have limited which movement responses could be detected. These are the first experimental behavioral response data for these abundant dolphins to directly inform impact assessments for military sonars. Methods We used complementary visual and acoustic sampling methods at variable spatial scales to measure different aspects of common dolphin behavior in known and controlled MFAS exposure and non-exposure contexts. Three fundamentally different data collection systems were used to sample group behavior. A broad-scale visual sampling of subgroup movement was conducted using theodolite tracking from shore-based stations. Assessments of whole-group and sub-group sizes, movement, and behavior were conducted at 2-minute intervals from shore-based and vessel platforms using high-powered binoculars and standardized sampling regimes. Aerial UAS-based photogrammetry quantified the movement of a single focal subgroup. The UAS consisted of a large (1.07 m diameter) custom-built octocopter drone launched and retrieved by hand from vessel platforms. The drone carried a vertically gimballed camera (at least 16MP) and sensors that allowed precise spatial positioning, allowing spatially explicit photogrammetry to infer movement speed and directionality. Remote-deployed (drifting) passive acoustic monitoring (PAM) sensors were strategically deployed around focal groups to examine both basic aspects of subspecies-specific common dolphin acoustic (whistling) behavior and potential group responses in whistling to MFAS on variable temporal scales (Casey et al., in press). This integration allowed us to evaluate potential changes in movement, social cohesion, and acoustic behavior and their covariance associated with the absence or occurrence of exposure to MFAS. The collective raw data set consists of several GB of continuous broadband acoustic data and hundreds of thousands of photogrammetry images. Three sets of quantitative response variables were analyzed from the different data streams: directional persistence and variation in speed of the focal subgroup from UAS photogrammetry; group vocal activity (whistle counts) from passive acoustic records; and number of sub-groups within a larger group being tracked by the shore station overlook. We fit separate Bayesian hidden Markov models (HMMs) to each set of response data, with the HMM assumed to have two states: a baseline state and an enhanced state that was estimated in sequential 5-s blocks throughout each CEE. The number of subgroups was recorded during periodic observations every 2 minutes and assumed constant across time blocks between observations. The number of subgroups was treated as missing data 30 seconds before each change was noted to introduce prior uncertainty about the precise timing of the change. For movement, two parameters relating to directional persistence and variation in speed were estimated by fitting a continuous time-correlated random walk model to spatially explicit photogrammetry data in the form of location tracks for focal individuals that were sequentially tracked throughout each CEE as a proxy for subgroup movement. Movement parameters were assumed to be normally distributed. Whistle counts were treated as normally distributed but truncated as positive because negative count data is not possible. Subgroup counts were assumed to be Poisson distributed as they were distinct, small values. In all cases, the response variable mean was modeled as a function of the HMM with a log link: log(Responset) = l0 + l1Z t where at each 5-s time block t, the hidden state took values of Zt = 0 to identify one state with a baseline response level l0, or Zt = 1 to identify an “enhanced” state, with l1 representing the enhancement of the quantitative value of the response variable. A flat uniform (-30,30) prior distribution was used for l0 in each response model, and a uniform (0,30) prior distribution was adopted for each l1 to constrain enhancements to be positive. For whistle and subgroup counts, the enhanced state indicated increased vocal activity and more subgroups. A common indicator variable was estimated for the latent state for both the movement parameters, such that switching to the enhanced state described less directional persistence and more variation in velocity. Speed was derived as a function of these two parameters and was used here as a proxy for their joint responses, representing directional displacement over time.
To assess differences in the behavior states between experimental phases, the block-specific latent states were modeled as a function of phase-specific probabilities, Z t ~ Bernoulli (pphaset), to learn about the probability pphase of being in an enhanced state during each phase. For each pre-exposure, exposure, and post-exposure phase, this probability was assigned a flat uniform (0,1) prior probability. The model was programmed in R (R version 3.6.1; The R Foundation for Statistical Computing) with the nimble package (de Valpine et al. 2020) to estimate posterior distributions of model parameters using Markov Chain Monte Carlo (MCMC) sampling. Inference was based on 100,000 MCMC samples following a burn-in of 100,000, with chain convergence determined by visual inspection of three MCMC chains and corroborated by convergence diagnostics (Brooks and Gelman, 1998). To compare behavior across phases, we compared the posterior distribution of the pphase parameters for each response variable, specifically by monitoring the MCMC output to assess the “probability of response” as the proportion of iterations for which pexposure was greater or less than ppre-exposure and the “probability of persistence” as the proportion of iterations for which ppost-exposre was greater or less than ppre-exposure. These probabilities of response and persistence thus estimated the extent of separation (non-overlap) between the distributions of pairs of pphase parameters: if the two distributions of interest were identical, then p=0.5, and if the two were non-overlapping, then p=1. Similarly, we estimated the average values of the response variables in each phase by predicting phase-specific functions of the parameters: Mean.responsephase = exp(l0 + l1pphase) and simply derived average speed as the mean of the speed estimates for 5-second blocks in each phase.

Introduction Continuous monitoring of critically ill children is essential for the timely identification of deteriorating vital signs. However, monitoring is often intermittent in low-resource settings, affecting the quality of care. This study assessed the implementation barriers and facilitators of a locally adapted, robust, low-cost continuous monitoring system (IMPALA) in Malawi. Methods A mixed-method implementation study of the IMPALA system in the paediatric High-dependency unit of a tertiary hospital from November 2022 to October 2023. Data were collected through over 300 hours of observations, in-depth interviews with 14 healthcare providers and nine caregivers of admitted children, and questionnaire-based surveys from 24 healthcare providers and 72 caregivers. Qualitative data were analysed thematically using inductive and deductive approaches. Descriptive statistics (frequencies, percentages, means, and standard deviations) were calculated for categorical and continuous variables. Results Healthcare providers and caregivers indicated that the IMPALA monitors improved care by providing the ability to measure reliably multiple vital signs, with long-lasting (4 hours) backup power and alarm provisions. Healthcare providers reported spending less time on child monitoring after the introduction of IMPALA (1.8 hours per day pre-IMPALA (95% CI: 1.19-2.48) compared to 3.3 hours post-IMPALA (95% CI: 2.36-4.23; p <0.00). Still, they recognised alarm fatigue, limitations in knowledge of the technology, and staff shortages as barriers to the use of IMPALA. Some caregivers expressed concerns about the reliability of the monitoring system. Conclusion The continuous monitoring device was well-received overall by healthcare providers and caregivers. It was perceived to save time and improve the quality of care. Opportunities to further enhance engagement with the device include strengthening caregivers’ knowledge and involvement to address their mistrust or misconceptions about the device, minimising false alarms, and providing ongoing training to healthcare providers so that new, existing, and rotating staff know how to engage with the device.

BackgroundFailure to recognize acute deterioration in hospitalized patients may contribute to cardiopulmonary arrest, unscheduled intensive care unit admission and increased mortality.PurposeIn this systematic review we aimed to determine whether continuous non-invasive respiratory monitoring improves early diagnosis of patient deterioration and reduces critical incidents on hospital wards.Data SourcesStudies were retrieved from Medline, Embase, CINAHL, and the Cochrane library, searched from 1970 till October 25, 2014.Study SelectionElectronic databases were searched using keywords and corresponding synonyms ‘ward’, ‘continuous’, ‘monitoring’ and ‘respiration’. Pediatric, fetal and animal studies were excluded.Data ExtractionSince no validated tool is currently available for diagnostic or intervention studies with continuous monitoring, methodological quality was assessed with a modified tool based on modified STARD, CONSORT, and TREND statements.Data SynthesisSix intervention and five diagnostic studies were included, evaluating the use of eight different devices for continuous respiratory monitoring. Quantitative data synthesis was not possible because intervention, study design and outcomes differed considerably between studies. Outcomes estimates for the intervention studies ranged from RR 0.14 (0.03, 0.64) for cardiopulmonary resuscitation to RR 1.00 (0.41, 2.35) for unplanned ICU admission after introduction of continuous respiratory monitoring,LimitationsThe methodological quality of most studies was moderate, e.g. ‘before-after’ designs, incomplete reporting of primary outcomes, and incomplete clinical implementation of the monitoring system.ConclusionsBased on the findings of this systematic review, implementation of routine continuous non-invasive respiratory monitoring on general hospital wards cannot yet be advocated as results are inconclusive, and methodological quality of the studies needs improvement. Future research in this area should focus on technology explicitly suitable for low care settings and tailored alarm and treatment algorithms.

"A protocol for a low-cost quantitative continuous measurement of movements in the extremities of people with PD (McKay, et al., 2019) was administered to people with PD . . . and age- and sex-matched healthy control participants" (Harrigan, et al., Quantitative continuous measurement of movements in the extremities, 2020). "Healthy control participants were matched for age and sex with participants with PD. Participants with PD completed a single test session . . . , a test and a retest session . . . , or a test and two retest sessions . . . . HC participants completed test and retest sessions " (Harrigan, et al., Quantitative continuous measurement of movements in the extremities, 2020). Thirty-two trained raters who were certified in the Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) (Goetz, et al., 2008) were presented the output of the ten participants with PD who completed a single test session (Pilot Test and Retest). Raters were presented two sets of 40 quizzes containing five representations for scoring of (A) output signals and FFTs and (B) CWTs (Pilot Test and Retest). Each quiz contained the panels of the x, y, and z representations of the finger and wrist or the toe and ankle of the five repetitive tasks. Each panel to be scored included six images corresponding to the signals of the three dimensions of the two accelerometers on a single extremity. The laterality of the representations was not stated. Raters were presented five sets of six images of the original signal and the fast Fourier transform (FFT) or the continuous wavelet transforms (CWTs). Raters were presented either five panels of output signals and FFTs or CWTs. Panels did not include output signals and FFTs and CWTs simultaneously. Raters were instructed to score (A) output signals and FFTs and (B) CWTs analogously to the clinical coding forms as indicated the the instructions in the data. The raters also completed the output of the ten participants with PD and eight HCs who completed a two test session (CWT Test and Retest). Raters were presented two sets of 72 quizzes containing five representations for scoring of (CWTs (Pilot Test and Retest). Each quiz contained the panels of averaged signals of the x, y, and z representations of the finger and wrist or the toe and ankle of the five repetitive tasks. Each panel to be scored included two images corresponding to the signals of the three dimensions of the two accelerometers on a single extremity. The laterality of the representations was not stated. Raters were asked to complete ratings independently at convenient times during the week.

As our generation and collection of quantitative digital data increase, so do our ambitions for extracting new insights and knowledge from those data. In recent years, those ambitions have manifested themselves in so-called “Grand Challenge” projects coordinated by academic institutions. These projects are often broadly interdisciplinary and attempt to address to major issues facing the world in the present and the future through the collection and integration of diverse types of scientific data. In general, however, disciplines that focus on the past are underrepresented in this environment – in part because these grand challenges tend to look forward rather than back, and in part because historical disciplines tend to produce qualitative, incomplete data that are difficult to mesh with the more continuous quantitative data sets provided by scientific observation. Yet historical information is essential for our understanding of long-term processes, and should thus be incorporated into our efforts to solve present and future problems. Archaeology, an inherently interdisciplinary field of knowledge that bridges the gap between the quantitative and the qualitative, can act as a connector between the study of the past and data-driven attempts to address the challenges of the future. To do so, however, we must find new ways to integrate the results of archaeological research into the digital platforms used for the modeling and analysis of much bigger data.

Planet Texas 2050 is a grand challenge project recently launched by The University of Texas at Austin. Its central goal is to understand the dynamic interactions between water supply, urbanization, energy use, and ecosystems services in Texas, a state that will be especially affected by climate change and population mobility by the middle of the 21st century. Like many such projects, one of the products of Planet Texas 2050 will be an integrated data platform that will make it possible to model various scenarios and help decision-makers project the results of resent policies or trends into the future. Unlike other such projects, however, PT2050 incorporates data collected from past societies, primarily through archaeological inquiry. We are currently designing a data integration and modeling platform that will allow us to bring together quantitative sensor data related to the present environment with “fuzzier” data collected in the course of research in the social sciences and humanities. Digital archaeological data, from LiDAR surveys to genomic information to excavation documentation, will be a central component of this platform. In this paper, I discuss the conceptual integration between scientific “big data” and “medium-sized” archaeological data in PT2050; the process that we are following to catalog data types, identify domain-specific ontologies, and understand the points of intersection between heterogeneous data sets of varying resolution and precision as we construct the data platform; and how we propose to incorporate digital data from archaeological research into integrated modeling and simulation modules.

Dataset of tree (.tre) files and R code for running generalized Robinson-Foulds distance (Smith, 2020a;b) analysis.

The .tre files can be read into R (R Core Team., 2023) using the ape::read.tree function (Paradis et al., 2003), full details in R code file.

Paradis, E., Claude, J., & Strimmer, K. (2004). APE: analyses of phylogenetics and evolution in R language. Bioinformatics, 20(2), 289-290.

R Core Team. (2023). R: A Language and Environment for Statistical Computing. (Version 4.2.2). R Foundation for Statistical Computing, Vienna, Austria: https://www.R-project.org/.

Smith, M. R. (2020a). Information theoretic generalized Robinson–Foulds metrics for comparing phylogenetic trees. Bioinformatics, 36(20), 5007-5013. https://doi.org/10.1093/bioinformatics/btaa614

Smith, M. R. (2020b). TreeDist: distances between phylogenetic trees. R package version 2.7.0. doi:10.5281/zenodo.3528124.

A low-cost quantitative continuous measurement of movements in the extremities of people with Parkinson’s disease was developed to enhance the gold-standard structured assessment of people with Parkinson’s disease (PD) assessed by the visual observation by the examiner of the person with PD (Goetz, et al., 2008) with the recorded output of signals to document the three dimensions of the positions in space of the finger and wrist or the toe and ankle of the participant performing tasks that may be impaired by PD (McKay, et al., 2019). The accelerometers were taped to the dorsal surface of the second (middle) phalanx of the index finger and the dorsum of the arm midway between the radius and the ulna two inches from the wrist joint to measure the movements in the upper extremity and to the dorsal surface of the proximal phalanx of the first (big) toe and the anterior surface of the tibia two inches proximal to the medial malleolus to measure the movements of the lower extremity (McKay, et al.,2019). The examiner instructed the participant how to perform each task. The examiner demonstrated the movements. The examiner did not continue to perform the movements while the participant was performing them. The examiner instructed the participant to perform each movement as quickly and fully as possible. The examiner encouraged the participant to execute each motion with the maximal speed and range of motion. The examiner sought to capture at least ten optimal repetitions for each motion. In order to attain a minimum of ten top-notch repetitions the examiner asked the participant to perform many more repetitions. The ten optimal repetitions could later be extracted for further analysis. The data shows trained examiner administering the procedures to a healthy 68-year-old male participant with typical development.

The data from this procedure performed on cohorts of individuals with Parkinson’s disease and multiple system atrophy and healthy age- and sex-matched individuals with typical development have been published (Harrigan, et al., 2020).

Dive into this specially curated dataset on credit card applications 📊.

An interesting approach to privacy has been taken in this dataset– every name and value has been creatively altered to ensure confidentiality 🔒.

What's inside?

A diverse collection of data that's sure to pique your interest. You'll encounter a range of continuous variables, giving you a glimpse into quantitative insights 📈.

Then, there are categorical variables – some with just a handful of options offering a neat, compact view, and others with a plethora of choices, adding layers of complexity and richness.

But here's where it gets even more intriguing – the dataset has been intentionally peppered with additional missing values 💡.

This isn't your average dataset; it's a playground for those who love a good data challenge.

The goal?

To equip you with real-world skills in handling and imputing missing data 🧩. You'll learn to navigate through these informational gaps, employing various imputation techniques to unveil the hidden stories within the data.

This dataset isn't just about understanding credit card applications 💳. It's a journey into the heart of data analysis and machine learning 🤖.

Whether you're a beginner eager to learn the ropes or an experienced data enthusiast looking to refine your skills, this dataset offers a unique opportunity. It challenges you to apply theoretical knowledge to practical scenarios, transforming abstract concepts into tangible skills.

So, if you're ready to test your mettle against real-world data puzzles, this is your chance. Unleash your analytical prowess, explore diverse imputation strategies, and uncover the secrets hidden in incomplete data. Welcome to a world where data tells a story, and you're the storyteller 🌐

This data is based on the Seshat data release in https://zenodo.org/record/6642230 and aims to dissect the time series of each NGA into culturally and institutionally continuous time series. For both continuity criteria, the central continuous time series is marked in the data (central meaning that this is the time interval during which the NGA has crossed a specified threshold between low-complexity and high-complexity societies). Details can be found in v3 of https://arxiv.org/abs/2212.00563

Meta-data

Diameter of Adult Cedar tree: The diameter of an adult cedar tree was measured using a tape rule. it was found based on random footsteps measured using a footstep count app on a cell phone. The measurement of the diameter for the adult cedar tree was taken at breast-height. The criteria of what an adult cedar tree looked like was deduced by the height which had to be about 10 feet tall; the height if an average person. The measurements were done in meters and can therefore be considered as a quantitative variable. Also, this is a categorical data as it was either an adult tree or its sapling tree that was measured. In addition, the variable was continuous as the diameter of the adult cedar tree was measured using a tape rule as stated earlier.

Canopy Cover of adult cedar tree: A square was made with fingers which were used to look through the canopy of the tree in order to know how much sky was showing. This variable was visually estimated to know the percentage of the square that was covered by the canopy of the adult cedar tree. The adult cedar tree was encountered by taking random footsteps as mentioned earlier. This variable can be categorized as discrete due to the fact that this was an effective way to measure the canopy cover; it was mainly an estimate but it can still be considered a quantitative data which was recorded in percentage denoted by %. One can say this variable is a dependent variable, because the canopy cover is dependent on the diameter of the tree, in this case the adult cedar tree. This will be further explained in the hypothesis and prediction.

Distance to nearest sapling cedar tree: The distance to the nearest sapling cedar tree (which was considered to be under 10 feet tall) was measured using a transect tape and recorded in meters. It was determined by where the adult cedar tree was located and then the distance was measured. This variable is a quantitative variable. It is also a continuous variable as the distance from the adult tree to the nearest sapling tree was measured. This variable is also categorical as there was an adult cedar tree and a sapling cedar tree.

Diameter of sapling cedar tree: The diameter of the nearest sapling cedar tree was measured at breast-height in meters. A tape rule was used to derive these measurements. This variable is also continuous as well as quantitative. It can also be said to be categorical as it was either an adult cedar tree or a sapling cedar tree that was measured.

Description

In this data set, a transect tape and tape rule were used to measure and also the measurements were recorded on a piece of paper. All these data were collected on a hot, windy day on Monday September 19, 2016 at an abundant woodlot which had a large amount of trees both dead and alive as well as grasslands, where most of the trees were close together and barely any place to walk. In order to speed up the data collection, two individuals were involved in retrieving and measuring each variable used in this data set. The following variable were measured and recorded; diameter of adult cedar tree, canopy of the adult cedar tree, distance to nearest sapling cedar tree and the diameter of sapling cedar tree. All of these variables were measured in meters except for the canopy cover of the adult cedar tree which was measured in percentage denoted by %. The diameter of both the adult and the sapling cedar tree were measured suing a tape rule which was done at breast height. The tape rule was held from one end of the tree branch to the other. In regards to the distance to the nearest sapling cedar tree, this was done using a transect tape that was laid flat on the floor from the end of the adult cedar tree to its nearest sapling tree. The measurements as stated earlier were taken in meters. The adult trees were found by taking random footsteps counts with the use of a footsteps count app on a cell phone and according to this the nearest sapling tree was found. The canopy cover in percentage was simply measured by forming a one-by-one inch square with fingers and then used to look through the canopy of the tree to determine the how much blue sky can be seen from the adult cedar tree. It is obvious that the species of the tree chosen was a cedar tree, with point sharp leaves. This specific specie of tree was chosen because there was a vast majority if it in the woodland and it was easy to find its nearest sapling tree with its distinct and unique shape of leaves. The hypothesis of this data states that the diameter of the adult cedar tree will be greater than the diameter of the sapling cedar tree due to the difference in tree size. Furthermore, the canopy cover percentage of the adult cedar tree will be dependent on the diameter of the adult cedar tree, therefore as the diameter of the adult cedar tree gets larger or increases so does the canopy cover of the tree. If the hypothesis is true, then it can be predicted that it will be discovered that the diameter of the adult cedar tree will be greater than that of the sapling cedar tree and also that canopy cover of the adult cedar tree will be dependent on the diameter of the adult cedar tree, as when the diameter of the adult cedar tree increases, the canopy cover percentage also increases variably. After all of these data were collected and all observations were noted, the hypothesis and predictions were right as the adult cedar tree had a much greater diameter than the sapling cedar tree and also the larger the diameter of the adult cedar tree, the larger the canopy cover percentage was.

The qualitative data analysis software market is experiencing robust growth, driven by the increasing need for in-depth understanding of consumer behavior, market trends, and social dynamics. The market's expansion is fueled by the rising adoption of qualitative research methods across various industries, including market research, healthcare, social sciences, and academia. Technological advancements, such as improved AI-powered functionalities for data coding, thematic analysis, and automated transcription, are enhancing the efficiency and accuracy of qualitative analysis, further boosting market growth. The availability of user-friendly interfaces and cloud-based solutions is making these powerful tools accessible to a broader range of researchers and analysts. While the market is competitive, with established players like NVivo and MAXQDA alongside emerging solutions, the overall trend indicates significant future growth potential. This growth is expected to continue as organizations increasingly recognize the value of rich, nuanced insights derived from qualitative data for informed decision-making. A key factor influencing market segmentation is the type of qualitative data being analyzed (e.g., interviews, focus groups, social media data). Different software solutions cater to specific data types and analytical needs. The pricing models of these solutions also vary, with options ranging from subscription-based services to one-time purchases. Geographic distribution of the market shows strong growth in North America and Europe, driven by high research and development spending and a strong adoption of advanced analytical techniques. However, growth in Asia-Pacific and other emerging markets is also expected to contribute significantly to the overall market expansion in the coming years, as these regions experience increasing investment in research and data analysis capabilities. Competitive pressures will likely drive innovation, with continuous improvements in features, accessibility, and integration with other analytical tools. We anticipate sustained market expansion throughout the forecast period, driven by these factors.